Patent application number | Description | Published |
20130262455 | REAL TIME IMPLICIT USER MODELING FOR PERSONALIZED SEARCH - A method and apparatus for utilizing user behavior to immediately modify sets of search results so that the most relevant documents are moved to the top. In one embodiment of the invention, behavior data, which can come from virtually any activity, is used to infer the user's intent. The updated inferred implicit user model is then exploited immediately by re-ranking the set of matched documents to best reflect the information need of the user. The system updates the user model and immediately re-ranks documents at every opportunity in order to constantly provide the most optimal results. In another embodiment, the system determines, based on the similarity of results sets, if the current query belongs in the same information session as one or more previous queries. If so, the current query is expanded with additional keywords in order to improve the targeting of the results. | 10-03-2013 |
20140244240 | Determining Explanatoriness of a Segment - A technique may include generating a segment from a sentence using a probabilistic model or structure. The probabilistic model/structure may be based on a Hidden Markov Model (HMM). The technique may further include determining an explanatoriness score of the segment using the probabilistic model/structure. | 08-28-2014 |
20150032717 | REAL TIME IMPLICIT USER MODELING FOR PERSONALIZED SEARCH - A method and apparatus for utilizing user behavior to immediately modify sets of search results so that the most relevant documents are moved to the top. In one embodiment of the invention, behavior data, which can come from virtually any activity, is used to infer the user's intent. The updated inferred implicit user model is then exploited immediately by re-ranking the set of matched documents and advertisements to best reflect the information need of the user. The system updates the user model and immediately re-ranks documents and advertisements at every opportunity in order to constantly provide the most optimal results. In another embodiment, the system determines, based on the similarity of results sets, if the current query belongs in the same information session as one or more previous queries. If so, the current query is expanded with additional keywords in order to improve the targeting of the results. | 01-29-2015 |
Patent application number | Description | Published |
20100002946 | METHOD AND APPARATUS FOR COMPRESSING FOR DATA RELATING TO AN IMAGE OR VIDEO FRAME - A method and an apparatus for compressing image data. The method includes dividing a line of an image into equal length fragments to form a coding unit, transforming and performing entropy coding to the coding unit, and compressing the image data based on the transformed entropy coded coding unit. | 01-07-2010 |
20100002951 | METHOD AND APPARATUS FOR REDUCING RINGING ARTIFACTS - A method and apparatus for ringing artifacts reduction for compressed video signals. The method includes receiving luma data to the digital signal processor, calculating sum of gradient of the luma data; calculating SAD of the luma data; performing pixel classification based of the calculated SAD and sum of gradient, performing erosion on a detected edge pixel indicator on a detected flat pixel indicators, determining at least one of the strength or weakness of the an edge based on the determined edge erosion, performing horizontal dilation on the detected edge pixel indicators and edge strength; and performing at least one of sigma or bilateral filtering to the luma data according to the detected edge pixel indicator, flat pixel indicator, edge strength, the number of very flat pixel in the block. | 01-07-2010 |
20120008834 | Motion Detection in Video with Large Areas of Detail - A method for motion detection is provided that includes determining a first motion measure for a pixel based on differences between first neighboring pixels of the pixel, determining a detail measure for the pixel, wherein the detail measure is indicative of an amount of detail in second neighboring pixels of the pixel, adapting a first coring threshold and a first gain of a first transfer function based on the detail measure, and using the adapted first transfer function to map the first motion measure to a first motion parameter. | 01-12-2012 |
20120019727 | Efficient Motion-Adaptive Noise Reduction Scheme for Video Signals - A adaptive noise reduction filter is provided for reducing noise in a video signal. Each pixel in a portion of a video frame is evaluated to determine a likelihood L of impulse noise corruption to each pixel. A total number P of pixels in the video frame that have a likelihood of impulse noise corruption is determined. One of a plurality of spatial noise reduction filters is selected to use on the video frame based on the total number P and on the likelihood L of impulse noise corruption to a current pixel. A motion value for each of the pixels in the portion of the video frame may be determined and used to inhibit spatial noise reduction filtering of each pixel that has a low motion value. | 01-26-2012 |
20140147057 | CONTENT ADAPTIVE EDGE AND DETAIL ENHANCEMENT FOR IMAGE AND VIDEO PROCESSING - A content-adaptive edge and detail enhancement method is described for image/video processing. Both 2D peaking and LTI/CTI are used in sharpening pictures. Image analysis is performed to generate a mask to control the use of the two peaking techniques. The strength or likelihood of edges or transitions is measured and such a strength or likelihood measurement will be transformed into a blending factor controlling the blending of the LTI/CTI and peaking outputs. | 05-29-2014 |
20140254932 | CONTENT ADAPTIVE EDGE AND DETAIL ENHANCEMENT FOR IMAGE AND VIDEO PROCESSING - A content-adaptive edge and detail enhancement apparatus is described for image/video processing. Both 2D peaking and LTI/CTI are used in sharpening pictures. Image analysis is performed to generate a blending factor to control the use of the two peaking techniques. The strength or likelihood of edges or transitions is measured and such a strength or likelihood measurement will be transformed into the blending factor controlling the blending of the LTI/CTI and peaking outputs. | 09-11-2014 |
Patent application number | Description | Published |
20110013611 | APPARATUS AND METHOD FOR ENABLING DISCOVERY OF WIRELESS DEVICES - A method and apparatus discover hidden wireless devices in a wireless network using a directional antenna system, preventing partitioning of the wireless network. A first wireless device located in a first antenna sector is joined in response to an initial first beacon. First beacons are received from the joined first wireless device during corresponding first beacon periods. At least a second antenna sector is scanned during at least one first beacon period to listen for second beacons from a second wireless device in the second antenna sector, while remaining joined with the first wireless device. The first beacons are not received while the second antenna sector is scanned. The second wireless device is joined in response to an initial second beacon. Second beacons are then received from the joined second wireless device during corresponding second beacon periods, and the first beacons are received during the corresponding first beacon periods. | 01-20-2011 |
20110044280 | TECHNIQUES FOR IMPROVING THE SPATIAL REUSE OF WIRELESS NETWORKS | 02-24-2011 |
20110128854 | MEDIUM ACCESS CONTROL FORWARDING PROTOCOL | 06-02-2011 |
20110128881 | TECHNIQUES FOR MONITORING THE QUALITY OF SHORT-RANGE WIRELESS LINKS - A method for monitoring of a wireless link quality comprises measuring the link quality of a wireless link ( | 06-02-2011 |
20110128918 | METHOD FOR DISCOVERING HIGH THROUGHPUT ROUTES IN WIRELESS MESH NETWORKS | 06-02-2011 |
20110158199 | GROUP SHARED DISTRIBUTED RESERVATION PROTOCOL | 06-30-2011 |
20110176487 | METHOD FOR DISCOVERING PATHS WITH SUFFICIENT MEDIUM TIME IN WIRELESS MESH NETWORKS | 07-21-2011 |
20110176580 | TECHNIQUES FOR ENABLING COMPATIBILITY OF ULTRA WIDEBAND DEVICES | 07-21-2011 |
20110255438 | TECHNIQUES FOR PERFORMING EFFICIENT LINK ADAPTATION IN WIRELESS PERSONAL NETWORKS | 10-20-2011 |
20120039255 | FRAME CONCATENATION IN WIRELESS UWB DEVICES - A method and system is provided for transmitting data frames from a first device to a second device in a wireless network. The method includes concatenating a plurality of data frames ( | 02-16-2012 |
20130023214 | CENTRALIZED DYNAMIC CHANNEL ALLOCATION FOR MEDICAL BODY AREA NETWORKS - A centralized frequency agility technique is employed in conjunction with a plurality of medical body area network (MBAN) systems ( | 01-24-2013 |
20130285556 | POLICY-BASED OLN LIGHT MANAGEMENT SYSTEM - A policy-based OLN (outdoor lighting network) light management system including a central control apparatus ( | 10-31-2013 |
20130297197 | VEHICLE POSITIONING AND GUIDANCE SYSTEM - A system for guiding a driver of a vehicle is disclosed. The system comprises a light sensor configured to detect light; and a processor configured to determine a position of vehicle on a roadway based on a characteristic of the detected light. | 11-07-2013 |
20130316652 | METHOD TO USE AUXILIARY CHANNEL TO ACHIEVE FAST AND POWER-EFFICIENT ASSOCIATION IN WIRELESS NETWORKS - A medical system includes one or more MBAN devices that acquire and communicate patient data. The medical system further including one or more medical body area network (MBAN) systems, each MBAN system including the one or more MBAN devices that communicate the patient data with a hub device via short-range wireless communication, the communication of the patient data via the short-range wireless communication being within a predefined spectrum. The hub device receives patient data communicated from the one or more MBAN devices and communicates with a central monitoring station via a longer range communication. The one or more MBAN devices transmit an association request to the hub device on one or more auxiliary channels to associate each MBAN device with the MBAN system, the auxiliary channels being outside the predefined spectrum. | 11-28-2013 |
20130337749 | SPECTRUM REALLOCATION WITH PRIORITIZED SCHEDULE - A medical system includes one or more medical body area network (MBAN) systems. Each MBAN system including one or more MBAN devices which acquire and communicate patient data via a hub device via a short-range wireless communication channel. The communication of the patient data via the short-range wireless communication channel within a predefined spectra. One of the spectra being a spectrum belonging to a third party primary user. The hub device receives patient data communicated from the one or more MBAN devices and communicates with a central monitoring station via a longer range communication. In response to the third party primary user requesting the third party primary user spectrum, the hub device reallocates to other spectra based on a priority of an acuity level of services communicated by each hub device. | 12-19-2013 |
20140028216 | OLN LIGHT CHANGE/OPTIMIZATION SYSTEM - Light management system for an outdoor lighting network (OLN) having lighting units, the system including a central control apparatus ( | 01-30-2014 |
Patent application number | Description | Published |
20090115970 | HIGH EFFICIENCY COMPACT OLED MICRODISPLAY PROJECTION ENGINE - A compact micro-display engine having improved efficiency for, e.g., projection displays or personal displays. It includes an emissive micro-display without the need for external illumination, a collimation optic plate on top of micro-display and a low F/# projection optics after the collimation optic plate. The collimation optical plate may be a micro-structure lenses array or a collimation prism film, and is used to collimate wide divergent light from the emissive micro-display device into a small cone angle light which will be efficiently collected by the projection optics. A reflective mirror is deposited on the top of substrate and underneath the light emitting layer for recycling the reflected back light from the collimation optic plate. The compact micro-display projection engine controls the divergence angle of the emitted light, and provides the controlled light to the objective plane of a projection optics subsystem. | 05-07-2009 |
20100148191 | High Luminous Flux Warm White Solid State Lighting Device - A high luminous flux warm white solid state lighting device with a high color rendering is disclosed. The device comprising two groups of semiconductor light emitting components to emit and excite four narrow-band spectrums of lights at high luminous efficacy, wherein the semiconductor light emitting components are directly mounted on a thermal effective dissipation member; a mixing cavity for blending the multi-spectrum of lights; a back-transferred light recycling member deposited on top of an LED driver and around the semiconductor light emitters; and a diffusive member to diffuse the mixture of output light from the solid state lighting device. The solid state lighting device produces a warm white light with luminous efficacy at least 80 lumens per watt and a color rendering index at least 85 for any lighting application. | 06-17-2010 |
20100149814 | Semiconductor Lighting Device With Wavelength Conversion on Back-Transferred Light Path - A semiconductor lighting device includes a semiconductor light emitter packaged on a reflective substrate to emit a first light and a remote wavelength conversion layer on a back-transferred light path to convert the back-transferred first light into a forward second light. A filter is disposed on a light emitting forward path with a space to the semiconductor light emitter to reflect back at least a portion of the first light. A diffusive member may be positioned outside of the filter to diffuse the forward passing light before it exits from the semiconductor lighting device. As a second aspect of this invention, a solid state lighting device includes a short wavelength semiconductor emitter; a long wavelength semiconductor emitter with wavelength in reddish orange range; a filter on a light emitting forward path to reflect back a portion of short wavelength first light; and a wavelength conversion component on a back-transferred light path. The device produces a mixture of warm white light in a correlated color temperature from 2700˜3500 K and color rendering index at least 85 for any indoor lighting application. | 06-17-2010 |
20100295069 | High Luminous Flux Warm White Solid State Lighting Device - A high luminous flux warm white solid state lighting device with a high color rendering is disclosed. The device comprising two groups of semiconductor light emitting components to emit and excite four narrow-band spectrums of lights at high luminous efficacy, wherein the semiconductor light emitting components are directly mounted on a thermal effective dissipation member; a mixing cavity for blending the multi-spectrum of lights; a back-transferred light recycling member deposited on top of an LED driver and around the semiconductor light emitters; and a diffusive member to diffuse the mixture of output light from the solid state lighting device. The solid state lighting device produces a warm white light with luminous efficacy at least 80 lumens per watt and a color rendering index at least 85 for any lighting application. | 11-25-2010 |
20140028934 | METHOD FOR DESPECKLING IN LASER DISPLAY SYSTEMS - A device used in laser display systems for despeckling includes a liquid crystal cell disposed in sandwiched relation between an input and a grounded electrode. A glass cover overlies each electrode. In a first embodiment, the cell may include vertically or randomly oriented liquid crystal molecules and the liquid crystal cell is larger than a laser beam in size for random phase modulation or retardation. Light loss due to diffraction and scattering are substantially eliminated in the absence of pixel structures. In another embodiment, the input electrode is divided into two separate parts. Vertically aligned liquid crystal molecules rotate and follow field fringes created by applying a first voltage to the input electrodes. Additional embodiments include a device that has two wedge-shaped liquid crystal layers, a device that includes plural field-induced gradient index prisms, a device including a tilted mirror, and composite devices. | 01-30-2014 |
Patent application number | Description | Published |
20090001325 | POLYMER COMPOSITES HAVING HIGHLY DISPERSED CARBON NANOTUBES AND METHODS FOR FORMING SAME - A method of forming carbon nanotube-polymer composites includes the steps of forming a mixture solution including a plurality of carbon nanotubes dispersed in a co-solvent. The co-solvent includes an organic solvent and a second solvent being a short chain fluorinated carboxylic acid having a boiling point below 150° C. which is less oxidizing than nitric acid, and is soluble in both the organic solvent and water. The first polymer is mixed with the mixture solution to form a polymer including mixture. The co-solvent is removed from the polymer mixture to form a dispersed nanotube-polymer composite. The second solvent can be trifluoroacetic acid. | 01-01-2009 |
20090118420 | DISPERSIONS OF CARBON NANOTUBES IN COPOLYMER SOLUTIONS AND FUNCTIONAL COMPOSITE MATERIALS AND COATINGS THEREFROM - A dispersion includes a plurality of non-chemically modified carbon nanotubes, a soluble block copolymer providing at least one block of a conjugated polymer and at least one block of a non-conjugated polymer, and at least one solvent. At 25° C. exclusive of any mechanical force and after one hour, at least 90% of the plurality of carbon nanotubes exist in the dispersion as isolated carbon nanotubes. The components of the dispersion can be combined with a polymer miscible with the block copolymer to form a carbon nanotube polymer composite upon removal of the solvent. The dispersion can be cast on a substrate and then dried to form a coating, including forming a superhydrophobic coating on the substrate. The non-conjugated polymer of the block copolymer or another miscible conjugated polymer including a copolymer can include functionalities that non-covalently attach to the carbon nanotube surface, such as for manipulating carbon nanotube properties including for enhanced solubility or enhanced biocompatibility. | 05-07-2009 |
20110180140 | SUPRAMOLECULAR STRUCTURES COMPRISING AT LEAST PARTIALLY CONJUGATED POLYMERS ATTACHED TO CARBON NANOTUBES OR GRAPHENES - A composition of matter includes at least one carbon nanotube (CNT) or a graphene type structure having an outer surface, and a plurality of crystalline polymer supramolecular structures that include a conjugated polymer that are non-covalently secured to the outer surface of the CNTs or the graphene type structure. The conjugated polymer can be a conjugated homopolymer or a block copolymer including at least one conjugated block. The supramolecular structures extend outward from the outer surface of the CNTs or graphene type structures. | 07-28-2011 |
20110224376 | CARBON NANOTUBE OR GRAPHENE-BASED AEROGELS - An aerogel includes a plurality of supramolecular structures bound to one another. Each supramolecular structure includes a carbon nanotube (CNT) or graphene type structure having an outer surface, and a plurality of polymers or aromatic molecules secured to the outer surface of the CNT or graphene type structure. The plurality of polymers or aromatic molecules have at least one crosslinkable structure. The supramolecular structures are crosslinked together by chemical bonding between the crosslinkable structures. The polymers can be block copolymers including at least one conjugated polymer block and at least one block of a crosslinkable non-conjugated polymer that provides the cross linkable structure, where the conjugated polymer block is non-covalently bonded to the outer surface of the CNT or graphene type structure. | 09-15-2011 |
20110303882 | POLYMER COMPOSITES HAVING HIGHLY DISPERSED CARBON NANOTUBES - A carbon nanotube-polymer composite includes a polymer continuous phase having at least a first polymer, and a plurality of carbon nanotubes dispersed in the polymer continuous phase. The carbon nanotubes are non-functionalized nanotubes. The carbon nanotubes are between 0.05 and 40 weight % of the composite. At least 98% of the carbon nanotubes are not involved in nanotube bundles. | 12-15-2011 |
20130115457 | POLYPEPTIDE ELECTROSPUN NANOFIBRILS OF DEFINED COMPOSITION - Electrospun nanofibrils and methods of preparing the same are provided. The electrospun nanofibrils comprise at least one polypeptide. A polypeptide can be dissolved in a solution, and the solution can be electrospun into a nanofibril. The solution can be added to a syringe or syringe pump, and an electric field can be applied to electrospin the at least one polypeptide. | 05-09-2013 |
20140072704 | METHOD OF FORMING COMPOSITE MATERIALS INCLUDING CONJUGATED MATERIALS ATTACHED TO CARBON NANOTUBES OR GRAPHENES - A method of forming composite materials includes dispersing a conjugated material, a solvent for the conjugated material, and a plurality of carbon nanotubes (CNTs) or graphene including structures having an outer surface to form a dispersion. The solvent is evaporated from the dispersion to yield a CNT or graphene composite including a plurality of crystalline supramolecular structures having the conjugated material non-covalently secured to the outer surface of the CNT or the graphene including structure. The supramolecular structures have an average length which extends outward in a length direction from the outer surface of the CNT or graphene including structure, where the average length is greater than an average width of the supramolecular structures. | 03-13-2014 |
Patent application number | Description | Published |
20110086858 | Compounds for the Treatment of Hepatitis C - The disclosure provides compounds of formula I, including pharmaceutically acceptable salts, as well as compositions and methods of using the compounds. The compounds have activity against hepatitis C virus (HCV) and may be useful in treating those infected with HCV. | 04-14-2011 |
20120093766 | Compounds for the Treatment of Hepatitis C - The disclosure provides compounds of formula I, including pharmaceutically acceptable salts, as well as compositions and methods of using the compounds. The compounds have activity against hepatitis C virus (HCV) and may be useful in treating those infected with HCV. | 04-19-2012 |
20120093767 | Compounds for the Treatment of Hepatitis C - The disclosure provides compounds of formula I, including pharmaceutically acceptable salts, as well as compositions and methods of using the compounds. The compounds have activity against hepatitis C virus (HCV) and may be useful in treating those infected with HCV. | 04-19-2012 |
20120238539 | NOVEL PIPERAZINE ANALOGS AS BROAD-SPECTRUM INFLUENZA ANTIVIRALS - A compound of Formula I is set forth, including pharmaceutically acceptable salts thereof: | 09-20-2012 |
20120245176 | NOVEL PIPERAZINE ANALOGS WITH SUBSTITUTED HETEROARYL GROUPS AS BROAD-SPECTRUM INFLUENZA ANTIVIRALS - A compound of Formula I is set forth, including pharmaceutically acceptable salts thereof: | 09-27-2012 |
20130231331 | Inhibitors of Human Immunodeficiency Virus Replication - The disclosure generally relates to compounds of formula I, including compositions and methods for treating human immunodeficiency virus (HIV) infection. The disclosure provides novel inhibitors of HIV, pharmaceutical compositions containing such compounds, and methods for using these compounds in the treatment of HIV infection. | 09-05-2013 |
Patent application number | Description | Published |
20130150632 | PROCESS FOR CIS-1-CHLORO-3,3,3-TRIFLUOROPROPENE - Disclosed is a process for the preparation of cis-1-chloro-3,3,3-trifluoropropene (cis-1233zd) comprising the steps of (a) providing CF | 06-13-2013 |
20130150633 | PROCESS FOR MAKING CIS-1-CHLORO-3,3,3-TRIFLUOROPROPENE - Disclosed is a process for making cis-1-chloro-3,3,3-trifluoropropene comprising reacting 3,3,3-trifluoropropyne with HCl in a reaction vessel at a yield of at least about 80%. | 06-13-2013 |
20130150634 | PROCESS FOR 1,1,2-TRICHLORO-3,3,3-TRIFLUOROPROPANE - Disclosed is a process for making the compound 1,1,2-trichloro-3,3,3-trifluoro-propane (233da) by the catalytic fluorination of 1,1,1,2,3,3-hexachloropropane. 233da is a starting material used in the production cis-1-chloro-3,3,3-trifluoropropene (cis-1233zd). | 06-13-2013 |
20140179960 | SYNTHESIS OF 1-BROMO-3,3,3-TRIFLUOROPROPENE - In accordance with the present invention, processes for producing bromofluoropropenes in commercial quantities by reacting 3,3,3-trifluoropropyne with hydrogen bromide at elevated temperatures are provided. | 06-26-2014 |
20140179961 | SYNTHESIS OF 3,3,3-TRIFLUOROPROPYNE - In accordance with the present invention, processes of synthesizing 3,3,3-trifluoropropyne from 1,3,3,3-tetrafluoropropene, 1-chloro-3,3,3-trifluoropropene, and/or 1,1,1,3,3-pentafluoropropane are provided. | 06-26-2014 |
20150045588 | PROCESS FOR 1-CHLORO-3,3,3-TRIFLUOROPROPENE FROM TRIFLUOROMETHANE - The present invention provides routes for making 1-chloro-3,3,3-trifluoropropene (HCFO-1233zd) from commercially available raw materials. More specifically, this invention provides routes for HCFO-1233zd from inexpensive and commercially available trifluoromethane (HFC-23). | 02-12-2015 |
20150045590 | PROCESS FOR 1-CHLORO-3,3,3-TRIFLUOROPROPENE FROM TRIFLUOROPROPENE - The present invention provides routes for making 1-chloro-3,3,3-trifluoropropene (HCFO-1233zd) from commercially available raw materials. More specifically, this invention provides several routes for forming HCFO-1233zd from 3,3,3-trifluoropropene (FC-1234zf). | 02-12-2015 |
Patent application number | Description | Published |
20140343330 | DEHALOGENATION OF TRANS-1-CHLORO-3,3,3-TRIFLUOROPROPENE - The present invention is related to making hydrofluorocarbons (HCFCs), more specifically, 3,3,3-trifluoropropyne (TFP), from trans-1-chloro-3,3,3-trifluoropropene (trans-1233zd) by contacting the trans-1233zd with a base. Preferably, the base is potassium hydroxide or potassium tert-butoxide, which may or may not be dissolved in as solvent. | 11-20-2014 |
20150065746 | FLUOROSURFACTANTS HAVING IMPROVED BIODEGRADABILITY - To address the problem of insufficient biodegradability of perfluorinated surfactants, the present invention provides biodegradable fluorosurfactants derived from olefins having —CHR, —CHRf, —CHF, and/or —CH | 03-05-2015 |
20160023973 | FLUOROSURFACTANTS HAVING IMPROVED BIODEGRADABILITY - To address the problem of insufficient biodegradability of perfluorinated surfactants, the present invention provides biodegradable fluorosurfactants derived from olefins having —CHR, —CHRf, —CHF, and/or —CH | 01-28-2016 |
Patent application number | Description | Published |
20140133746 | BACKGROUND UNDERSTANDING IN VIDEO DATA - Long-term understanding of background modeling includes determining first and second dimension gradient model derivatives of image brightness data of an image pixel along respective dimensions of two-dimensional, single channel image brightness data of a static image scene. The determined gradients are averaged with previous determined gradients of the image pixels, and with gradients of neighboring pixels as a function of their respective distances to the image pixel, the averaging generating averaged pixel gradient models for each of a plurality of pixels of the video image data of the static image scene that each have mean values and weight values. Background models for the static image scene are constructed as a function of the averaged pixel gradients and weights, wherein the background model pixels are represented by averaged pixel gradient models having similar orientation and magnitude and weights meeting a threshold weight requirement. | 05-15-2014 |
20140376775 | ESTIMATION OF OBJECT PROPERTIES IN 3D WORLD - Objects within two-dimensional video data are modeled by three-dimensional models as a function of object type and motion through manually calibrating a two-dimensional image to the three spatial dimensions of a three-dimensional modeling cube. Calibrated three-dimensional locations of an object in motion in the two-dimensional image field of view of a video data input are determined and used to determine a heading direction of the object as a function of the camera calibration and determined movement between the determined three-dimensional locations. The two-dimensional object image is replaced in the video data input with an object-type three-dimensional polygonal model having a projected bounding box that best matches a bounding box of an image blob, the model oriented in the determined heading direction. The bounding box of the replacing model is then scaled to fit the object image blob bounding box, and rendered with extracted image features. | 12-25-2014 |
20150023560 | MULTI-CUE OBJECT ASSOCIATION - Multiple discrete objects within a scene image captured by a single camera track are distinguished as un-labeled from a background model within a first frame of a video data input. Object position, object appearance and/or object size attributes are determined for each of the blobs, and costs determined to assign to existing blobs of existing object tracks as a function of the determined attributes. The un-labeled object blob that has a lowest cost of association with any of the existing object tracks is labeled with the label of that track having the lowest cost, said track is removed from consideration for labeling remaining un-labeled object blobs, and the process iteratively repeated until each of the track labels have been used to label one of the un-labeled blobs. | 01-22-2015 |
20150055830 | AUTOMATICALLY DETERMINING FIELD OF VIEW OVERLAP AMONG MULTIPLE CAMERAS - Field of view overlap among multiple cameras are automatically determined as a function of the temporal overlap of object tracks determined within their fields-of-view. Object tracks with the highest similarity value are assigned into pairs, and portions of the assigned object track pairs having a temporally overlapping period of time are determined. Scene entry points are determined from object locations on the tracks at a beginning of the temporally overlapping period of time, and scene exit points from object locations at an ending of the temporally overlapping period of time. Boundary lines for the overlapping fields-of-view portions within the corresponding camera fields-of-view are defined as a function of the determined entry and exit points in their respective fields-of-view. | 02-26-2015 |
20150154457 | OBJECT RETRIEVAL IN VIDEO DATA USING COMPLEMENTARY DETECTORS - Automatic object retrieval from input video is based on learned, complementary detectors created for each of a plurality of different motionlet clusters. The motionlet clusters are partitioned from a dataset of training vehicle images as a function of determining that vehicles within each of the scenes of the images in each cluster share similar two-dimensional motion direction attributes within their scenes. To train the complementary detectors, a first detector is trained on motion blobs of vehicle objects detected and collected within each of the training dataset vehicle images within the motionlet cluster via a background modeling process; a second detector is trained on each of the training dataset vehicle images within the motionlet cluster that have motion blobs of the vehicle objects but are misclassified by the first detector; and the training repeats until all of the training dataset vehicle images have been eliminated as false positives or correctly classified. | 06-04-2015 |
20150178570 | DETECTION OF STATIC OBJECT ON THOROUGHFARE CROSSINGS - Foreground object image features are extracted from input video via application of a background subtraction mask, and optical flow image features from a region of the input video image data defined by the extracted foreground object image features. If estimated movement features indicate that the underlying object is in motion, a dominant moving direction of the underlying object is determined. If the dominant moving direction is parallel to an orientation of the second, crossed thoroughfare, an event alarm indicating that a static object is blocking travel on the crossing second thoroughfare is not generated. If the estimated movement features indicate that the underlying object is static, or that its determined dominant moving direction is not parallel to the second thoroughfare, an appearance of the foreground object region is determined and a static-ness timer run while the foreground object region comprises the extracted foreground object image features. | 06-25-2015 |
20150242692 | DETERMINATION OF TRAIN PRESENCE AND MOTION STATE IN RAILWAY ENVIRONMENTS - Foreground feature data and motion feature data is determined for frames of video data acquired from a train track area region of interest. The frames are labeled as “train present” if the determined foreground feature data value meets a threshold value, else as “train absent; and as “motion present” if the motion feature data meets a motion threshold, else as “static.” The labels are used to classify segments of the video data comprising groups of consecutive video frames, namely as within a “no train present” segment for groups with “train absent” and “static” labels; within a “train present and in transition” segment for groups “train present” and “motion present” labels; and within a “train present and stopped” segment for groups with “train present” and “static” labels. The presence or motion state of a train at a time of inquiry is thereby determined from the respective segment classification. | 08-27-2015 |
20150278631 | FILTERING METHODS FOR VISUAL OBJECT DETECTION - Machine logic that pre-processes and post-processes images for visual object detection by performing the following steps: receiving a set of image(s); filtering the set of image(s) using a set of multimodal integral filter(s), thereby removing at least a portion of the set of image(s) and resulting in a filtered set of image(s); performing object detection on the filtered set of image(s) to generate a set of object-detected image(s); assembling a first plurality of object-detected image(s) from the set of object-detected image(s); and upon assembling the first plurality of object-detected image(s), performing non-maximum suppression on the assembled first plurality of object-detected image(s). | 10-01-2015 |
20150339831 | MULTI-MODE VIDEO EVENT INDEXING - Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode. | 11-26-2015 |
20150356352 | BACKGROUND UNDERSTANDING IN VIDEO DATA - Long-term understanding of background modeling includes determining first and second dimension gradient model derivatives of image brightness data of an image pixel along respective dimensions of two-dimensional, single channel image brightness data of a static image scene. The determined gradients are averaged with previous determined gradients of the image pixels, and with gradients of neighboring pixels as a function of their respective distances to the image pixel, the averaging generating averaged pixel gradient models for each of a plurality of pixels of the video image data of the static image scene that each have mean values and weight values. Background models for the static image scene are constructed as a function of the averaged pixel gradients and weights, wherein the background model pixels are represented by averaged pixel gradient models having similar orientation and magnitude and weights meeting a threshold weight requirement. | 12-10-2015 |
20150356745 | MULTI-MODE VIDEO EVENT INDEXING - Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode. | 12-10-2015 |
20150379357 | EFFICIENT RETRIEVAL OF ANOMALOUS EVENTS WITH PRIORITY LEARNING - Local models learned from anomaly detection are used to rank detected anomalies. The local models include image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by failures to fit to applied anomaly detection module local models. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies. | 12-31-2015 |
20150379729 | AUTOMATICALLY DETERMINING FIELD OF VIEW OVERLAP AMONG MULTIPLE CAMERAS - Field of view overlap among multiple cameras are automatically determined as a function of the temporal overlap of object tracks determined within their fields-of-view. Object tracks with the highest similarity value are assigned into pairs, and portions of the assigned object track pairs having a temporally overlapping period of time are determined. Scene entry points are determined from object locations on the tracks at a beginning of the temporally overlapping period of time, and scene exit points from object locations at an ending of the temporally overlapping period of time. Boundary lines for the overlapping fields-of-view portions within the corresponding camera fields-of-view are defined as a function of the determined entry and exit points in their respective fields-of-view. | 12-31-2015 |
20150379768 | ESTIMATION OF OBJECT PROPERTIES IN 3D WORLD - Objects within two-dimensional video data are modeled by three-dimensional models as a function of object type and motion through manually calibrating a two-dimensional image to the three spatial dimensions of a three-dimensional modeling cube. Calibrated three-dimensional locations of an object in motion in the two-dimensional image field of view of a video data input are determined and used to determine a heading direction of the object as a function of the camera calibration and determined movement between the determined three-dimensional locations. The two-dimensional object image is replaced in the video data input with an object-type three-dimensional polygonal model having a projected bounding box that best matches a bounding box of an image blob, the model oriented in the determined heading direction. The bounding box of the replacing model is then scaled to fit the object image blob bounding box, and rendered with extracted image features. | 12-31-2015 |
20160034766 | OPTIMIZING VIDEO STREAM PROCESSING - Transaction units of video data and transaction data captured from different checkout lanes are prioritized as a function of lane priority values of respective ones of the different checkout lanes from which the transaction units are acquired. Each of the checkout lanes has a different lane priority value. The individual transaction units are processed in the prioritized processing order to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed individual transaction units. | 02-04-2016 |
Patent application number | Description | Published |
20120263346 | VIDEO-BASED DETECTION OF MULTIPLE OBJECT TYPES UNDER VARYING POSES - Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object. | 10-18-2012 |
20120269383 | RELIABILITY IN DETECTING RAIL CROSSING EVENTS - A method, data processing system, apparatus, and computer program product for monitoring objects. A plurality of images of an area is received. An object in the area is identified from the plurality of images. A plurality of points in a region within the area is identified from a first image in the plurality of images. The plurality of points has a fixed relationship with each other and the region. The object in the area is monitored to determine whether the object has entered the region. A determination that the object has not entered the region is made in response to identifying an absence of a number of the plurality of points in a second image in the plurality of images. | 10-25-2012 |
20120294511 | EFFICIENT RETRIEVAL OF ANOMALOUS EVENTS WITH PRIORITY LEARNING - Local models learned from anomaly detection are used to rank detected anomalies. The local models include image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by failures to fit to applied anomaly detection module local models. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies. | 11-22-2012 |
20120314030 | ESTIMATION OF OBJECT PROPERTIES IN 3D WORLD - Objects within two-dimensional (2D) video data are modeled by three-dimensional (3D) models as a function of object type and motion through manually calibrating a 2D image to the three spatial dimensions of a 3D modeling cube. Calibrated 3D locations of an object in motion in the 2D image field of view of a video data input are computed and used to determine a heading direction of the object as a function of the camera calibration and determined movement between the computed 3D locations. The 2D object image is replaced in the video data input with an object-type 3D polygonal model having a projected bounding box that best matches a bounding box of an image blob, the model oriented in the determined heading direction. The bounding box of the replacing model is then scaled to fit the object image blob bounding box, and rendered with extracted image features. | 12-13-2012 |
20130101208 | BACKGROUND UNDERSTANDING IN VIDEO DATA - Long-term understanding of background modeling includes determining first and second dimension gradient model derivatives of image brightness data of an image pixel along respective dimensions of two-dimensional, single channel image brightness data of a static image scene. The determined gradients are averaged with previous determined gradients of the image pixels, and with gradients of neighboring pixels as a function of their respective distances to the image pixel, the averaging generating averaged pixel gradient models for each of a plurality of pixels of the video image data of the static image scene that each have mean values and weight values. Background models for the static image scene are constructed as a function of the averaged pixel gradients and weights, wherein the background model pixels are represented by averaged pixel gradient models having similar orientation and magnitude and weights meeting a threshold weight requirement. | 04-25-2013 |
20130336534 | MULTI-MODE VIDEO EVENT INDEXING - Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode. | 12-19-2013 |
20130336535 | MULTI-MODE VIDEO EVENT INDEXING - Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode. | 12-19-2013 |
20140003708 | OBJECT RETRIEVAL IN VIDEO DATA USING COMPLEMENTARY DETECTORS | 01-02-2014 |
20140003724 | DETECTION OF STATIC OBJECT ON THOROUGHFARE CROSSINGS | 01-02-2014 |
20140050356 | MULTI-MODE VIDEO EVENT INDEXING - Multi-mode video event indexing includes determining a quality of object distinctiveness with respect to images from a video stream input. A high-quality analytic mode is selected from multiple modes and applied to video input images via a hardware device to determine object activity within the video input images if the determined level of detected quality of object distinctiveness meets a threshold level of quality, else a low-quality analytic mode is selected and applied to the video input images via a hardware device to determine object activity within the video input images, wherein the low-quality analytic mode is different from the high-quality analytic mode. | 02-20-2014 |
20140056479 | DETERMINATION OF TRAIN PRESENCE AND MOTION STATE IN RAILWAY ENVIRONMENTS - Foreground feature data and motion feature data is determined for frames of video data acquired from a train track area region of interest. The frames are labeled as “train present” if the determined foreground feature data value meets a threshold value, else as “train absent; and as “motion present” if the motion feature data meets a motion threshold, else as “static.” The labels are used to classify segments of the video data comprising groups of consecutive video frames, namely as within a “no train present” segment for groups with “train absent” and “static” labels; within a “train present and in transition” segment for groups “train present” and “motion present” labels; and within a “train present and stopped” segment for groups with “train present” and “static” labels. The presence or motion state of a train at a time of inquiry is thereby determined from the respective segment classification. | 02-27-2014 |
20140098989 | MULTI-CUE OBJECT ASSOCIATION - Multiple discrete objects within a scene image captured by a single camera track are distinguished as un-labeled from a background model within a first frame of a video data input. Object position and object appearance and/or object size attributes are determined for each of the blobs, and costs determined to assign to existing blobs of existing object tracks as a function of the determined attributes and combined to generate respective combination costs. The un-labeled object blob that has a lowest combined cost of association with any of the existing object tracks is labeled with the label of that track having the lowest combined cost, said track is removed from consideration for labeling remaining un-labeled object blobs, and the process iteratively repeated until each of the track labels have been used to label one of the un-labeled blobs. | 04-10-2014 |
20140164306 | PATHWAY MANAGEMENT USING MODEL ANALYSIS AND FORCASTING - A computer generates a three dimensional map of a pathway area using a plurality of overhead images. The computer determines a forecasted weather pattern to occur in the pathway area. The computer analyzes the three dimensional map and the forecasted weather pattern to predict one or more violations of the pathway. The computer generates a priority for the one or more predicted violations of the pathway. The computer generates a plan for pathway management of the pathway area. | 06-12-2014 |
20140185925 | BOOSTING OBJECT DETECTION PERFORMANCE IN VIDEOS - A method and system for training a special object detector to distinguish a foreground object appearing in a sequence of frames for a target domain. The sequence of frames depicts motion of the foreground object in a non-uniform background. The foreground object is detected in a high-confidence subwindow of an initial frame of the sequence, which includes computing a measure of confidence that the high-confidence subwindow includes the foreground object and determining that the measure of confidence exceeds a specified confidence threshold. The foreground object is tracked in respective positive subwindows of subsequent frames appearing after the initial frame. The subsequent frames are within a specified short period of time. The positive subwindows are used to train the special object detector to detect the foreground object in the target domain. The positive subwindows include the subwindow of the initial frame and the respective subwindows of the subsequent frames. | 07-03-2014 |
20140193042 | SURFACE CONTAMINATION DETERMINATION SYSTEM - A computer receives a first set of spectral information for a first surface, wherein the first set of spectral information includes a pixel count for each color value of a range of color values, with regard to each color, measured at time one. The computer determines, with regard to the first set, whether dispersion of the pixel count across the range of color values, with regard to each color, exceeds a first threshold value. The computer determines, with regard to the first set, a surface contamination level based on at least whether the dispersion of the pixel count across the range of color values, with regard to each color, exceeds the first threshold value. | 07-10-2014 |
20140267738 | VISUAL MONITORING OF QUEUES USING AUXILLARY DEVICES - Methods and system are provided for monitoring a queue. A method includes receiving by sensors a non-visual identifier at predefined locations of a queue. Further, the method includes capturing by image capture devices images of an object possessing the non-visual identifier at the predefined locations of the queue. Further, the method includes visually tracking another object in the queue based on transformations of a predefined feature extracted from the images of the object possessing the non-visual identifier at the predefined locations. | 09-18-2014 |
20140293043 | DETERMINING CAMERA HEIGHT USING DISTRIBUTIONS OF OBJECT HEIGHTS AND OBJECT IMAGE HEIGHTS - A camera at a fixed vertical height positioned above a reference plane, with an axis of a camera lens at an acute angle with respect to a perpendicular of the reference plane. One or more processors receive images of different people. The vertical measurement values of the images of different people are determined. The one or more processors determine a first statistical measure associated with a statistical distribution of the vertical measurement values. The known heights of people from a known statistical distribution of heights of people are transformed to normalized measurements, based in part on a focal length of the camera lens, the angle of the camera, and a division operator in an objective function of differences between the normalized measurements and the vertical measurement values. The fixed vertical height of the camera is determined, based at least on minimizing the objective function. | 10-02-2014 |
20140294231 | AUTOMATICALLY DETERMINING FIELD OF VIEW OVERLAP AMONG MULTIPLE CAMERAS - Field of view overlap among multiple cameras is automatically determined as a function of the temporal overlap of object tracks determined within their fields-of-view. Object tracks with the highest similarity value are assigned into pairs, and portions of the assigned object track pairs having a temporally overlapping period of time are determined. Scene entry points are determined from object locations on the tracks at a beginning of the temporally overlapping period of time, and scene exit points from object locations at an ending of the temporally overlapping period of time. Boundary lines for the overlapping fields-of-view portions within the corresponding camera fields-of-view are defined as a function of the determined entry and exit points in their respective fields-of-view. | 10-02-2014 |
20150062340 | High Occupancy Toll Lane Compliance - A method and system for demonstrating compliance with a requirement of a high occupancy lane in a vehicle for a reduced toll charge for the vehicle is provided. The system includes a housing, an infrared camera within the housing, a GPS unit, a transceiver and a control within the housing. The infrared camera images one or more people in the vehicle. The transceiver detects an RF signal indicating that the vehicle is located at or near a toll booth for the high occupancy lane. The control triggers the infrared camera to image the one or more people and transmit a current time, a current location of the vehicle from the GPS unit, and the triggered image of the one or more people, to a server to demonstrate compliance with the requirement of the high occupancy lane for the reduced toll charge for the vehicle. | 03-05-2015 |
Patent application number | Description | Published |
20110188701 | OPTIMIZING VIDEO STREAM PROCESSING - The present invention involves implementation of an intelligent switching program, whereby the processing power required to monitor check-out stations is considerably reduced. The present invention monitors a subset of check-out stations at any given time, instead of monitoring all check-out stations at all times. The subset of check-out stations is determined dynamically according to, but not limited to, cashier records, input parameters from the user, current lane activity, past lane activity, time of day, etc. Statistical models (e.g., effective population sampling and/or population hypothesis tests) are developed along these lines that guide the lane selection process, whereby increases in the false-negative rate due to failure to monitor particular lanes when events of interest occur are controlled. By monitoring fewer check-out stations, while maintaining target performance accuracy, the amount of data that end users must deal with is significantly reduced. | 08-04-2011 |
20120293661 | OPTIMIZING VIDEO STREAM PROCESSING - An approach to reduce the processing power required to monitor check-out stations. A subset of check-out stations may be monitored at any given time, instead of monitoring all check-out stations at all times. The subset of check-out stations is determined dynamically according to, but not limited to, cashier records, input parameters from the user, current lane activity, past lane activity, time of day, etc. Statistical models (e.g., effective population sampling and/or population hypothesis tests) are developed along these lines that guide the lane selection process, whereby increases in the false-negative rate due to failure to monitor particular lanes when events of interest occur are controlled. By monitoring fewer check-out stations, while maintaining target performance accuracy, the amount of data that end users must deal with is significantly reduced. | 11-22-2012 |
20130336531 | SEQUENTIAL EVENT DETECTION FROM VIDEO - Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing primitive images of images of a video stream, and also of idle states associated with the respective primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices. | 12-19-2013 |