Patent application number | Description | Published |
20090184847 | VEHICLE LANE DISCRIMINATION IN AN ELECTRONIC TOLL COLLECTION SYSTEM - A vehicle position determination system for determining the position of a moving vehicle in a multi-lane roadway. Two or more roadway antennas each periodically transmit an identifier that is associated with and unique to the antenna to a transponder located in the moving vehicle. As the moving vehicle passes through the coverage zone of the antennas, the transponder counts the number of times that it receives each unique identifier and reports this information to a roadside controller. Based on this information, the roadside controller can determine a probable location of the moving vehicle. The vehicle location information can be provided to an imaging system to discriminate between transponder and non-transponder equipped vehicles. | 07-23-2009 |
20090201169 | Real-Time Location Systems and Methods - A real-time location system for identifying and locating tagged items. The system may include an identification protocol that tracks in-network transponders and assigns dynamic in-network identification numbers to in-network transponders. The system includes a locator function that employs time-of-arrival analysis. Rather than attempt to synchronize the time base at each reader, the system and process eliminate the need to sync the readers and also eliminate the impact of differential receive delays in the respective readers. Both the transponder and a master reader transmit locate signals, which are measured at slave readers. The system relies on differences in time-of-arrival of the two signals at the respective slave readers to determine the likely location of the transponder. | 08-13-2009 |
20100022202 | TRANSCEIVER REDUNDANCY IN AN ELECTRONIC TOLL COLLECTION SYSTEM - An electronic toll collection system wherein the reader includes a switching network and a plurality of transceivers operating under the control of a controller. The reader further includes failure detection circuitry for determining whether any of the transceivers have failed based upon the RF outputs of the transceivers. If the controller determines that a transceiver has failed, then it alters the switching pattern such that the switching network excludes the failed transceiver from being connected to the antennas. The reader thereby provides for adaptive RF channel assignment, as the particular transceiver used to excite a particular antenna may be dynamically altered, and the provision of at least two transceivers in the reader ensures transceiver redundancy. | 01-28-2010 |
20100085213 | HIGH OCCUPANCY VEHICLE STATUS SIGNALING USING ELECTRONIC TOLL COLLECTION INFRASTRUCTURE - An electronic toll collection system, reader, method and transponder for communicating occupancy status. The vehicle-mounted transponder includes a selection device that permits a user to select between a normal and high occupancy state. The transponder reports its occupancy status to a reader. If the electronic toll collection system processes a toll transaction and the transponder claims high occupancy status during the toll transaction, the fact that high occupancy status was claimed during the transaction is recorded in memory within the transponder for later enforcement and verification purposes. | 04-08-2010 |
20100237998 | ADAPTIVE COMMUNICATION IN AN ELECTRONIC TOLL COLLECTION SYSTEM - An adaptive communication system and method for use in an electronic toll collection system utilizing transponders located in vehicles travelling on a toll roadway. A transponder memory stores configuration type data that identifies the type of the vehicle carrying the transponder, the transponder or the transponder's mounting. The transponder transmits the configuration type data to the communication system. The communication system includes a memory which contains a database of predetermined communication parameters for various types of configuration types. The communication system looks up the predetermined communication parameters for the configuration type and adjusts variable communication parameters accordingly. Predetermined communication variables may include the transmit power of an antenna, or the receive sensitivity of the antenna or the position of the vehicle in order to maximize the likelihood of a successful communication. | 09-23-2010 |
20100245126 | ENHANCED TRANSPONDER PROGRAMMING IN AN OPEN ROAD TOLL SYSTEM - A transponder communication system and method for communicating with a transponder in an electronic toll collection system. A roadside reader attempts to program the transponder in a normal mode in which a programming signal is transmitted to a first coverage area. If the programming attempt in the normal mode is unsuccessful, the reader attempts to program the transponder in an enhanced mode in which a programming signal is transmitted to a second coverage area. The coverage area is adjusted after the programming attempt in the normal mode by using an adjacent antenna to the antenna used to transmit in the normal mode or by increasing the power of the programming signal to a level that is greater than the level used to transmit the programming signal in the normal mode. | 09-30-2010 |
20110304434 | MULTI-PROTOCOL ELECTRONIC TOLL COLLECTION SYSTEM - A system and method for dynamically selecting a communication protocol in an electronic toll collection system. A first reader communicating under a primary communication protocol is connected to a roadway antenna. If a transponder of the primary protocol is detected within a predetermined duration, then the first reader maintains its access to the roadway antenna so that it may perform an electronic toll transaction with the detected transponder. If a transponder of the primary protocol is not detected within a predetermined duration, then the first reader will switch over access of the antenna to a second reader operating under a secondary protocol so that the second reader may perform an electronic toll transaction with a detected secondary protocol transponder. | 12-15-2011 |
20110307305 | MULTI-PROTOCOL ELECTRONIC TOLL COLLECTION SYSTEM - A system and method for dynamically selecting a communication protocol in an electronic toll collection system. A reader includes two or more multiprotocol transceivers operating under the control of a processor, each transceiver having a dedicated antenna. The system uses a fixed frame duration. A first communications protocol is used in a first portion of the fixed frame duration. If a response signal is not detected within the first portion, then the system ceases using the first communication protocol and instead uses the second communications protocol for the remainder of the fixed frame duration. The fixed frame duration is shorter than the sum of the durations normally used by the first and second communications protocol to conduct electronic toll transaction communications. | 12-15-2011 |
20120169516 | METHOD AND SYSTEM FOR TRIGGERING COMMERCIAL VEHICLE INSPECTION - A system and method for triggering a vehicle inspection in a vehicle inspection bypass system. A handheld device transmits a signal containing the driver information in response to detecting an activation of an actuator on the handheld device. A vehicle mounted transponder detects the signal when the handheld device is in close proximity, and the driver information is stored in the transponder memory. Upon detecting an interrogation signal from a roadside reader, the transponder transmits a signal containing the driver information to the roadside reader. Based on the received driver information, a roadside controller determines whether a vehicle may bypass a vehicle inspection station. | 07-05-2012 |
20140285360 | ENHANCED TRANSPONDER PROGRAMMING IN AN OPEN ROAD TOLL SYSTEM - Systems, Methods, and Apparatus for enhanced transponder programming in an open road toll system are disclosed. An example method includes transmitting, in a normal mode, a programming signal from one of the antennas over a first coverage area to instruct the transponder to store data in its memory, the data being contained in the programming signal. The example method further includes determining that the transponder did not store the data in its memory. Based on the determination that the transponder did not store the data in its memory the programming signal is transmitted in an enhanced mode, from one antennas over a second coverage area. | 09-25-2014 |
20150054675 | METHODS AND SYSTEMS FOR DETERMINING A RANGE RATE FOR A BACKSCATTER TRANSPONDER - Methods for determining a range rate of a backscatter transponder and readers implementing the methods are described. The reader transmits a continuous wave signal and receives a modulated reflected response signal from the transponder, mixes the modulated reflected response signal with the carrier frequency to produce a downconverted signal, bandpass filters the downconverted signal to pass a bandpass filtered signal containing at least the modulation frequency, applies a non-linear amplitude transfer function to produce a modulation-suppressed signal, and measures the frequency of the modulation-suppressed signal and determines the range rate from the measured frequency. | 02-26-2015 |
20150054676 | METHODS AND SYSTEMS FOR DETERMINING VEHICLE POSITION IN AN AUTOMATIC VEHICLE IDENTIFICATION SYSTEM - Methods of estimating vehicle location in a roadway using an automatic vehicle identification system are described. The methods involve receiving a set of response signals from a vehicle-mounted transponder at points in time and determining a range rate of the transponder relative to the antenna at each point in time; identifying a minima in the magnitude of the range rate; estimating a first position of the transponder at a first time corresponding to the occurrence of the minima; estimating a velocity of the vehicle based upon one or more of the determined range rates; and estimating a second position of the transponder based upon the first position and the velocity. | 02-26-2015 |
Patent application number | Description | Published |
20090285544 | Video Processing - A method and apparatus for processing video is disclosed. In an embodiment, image features of an object within a frame of video footage are identified and the movement of each of these features is tracked throughout the video footage to determine its trajectory (track). The tracks are analyzed, the maximum separation of the tracks is determined and used to determine a texture map, which is in turn interpolated to provide an unwrap mosaic for the object. The process may be iterated to provide an improved mosaic. Effects or artwork can be overlaid on this mosaic and the edited mosaic can be warped via the mapping, and combined with layers of the original footage. The effect or artwork may move with the object's surface. | 11-19-2009 |
20100322525 | Image Labeling Using Multi-Scale Processing - Multi-scale processing may be used to reduce the memory and computational requirements of optimization algorithms for image labeling, for example, for object segmentation, 3D reconstruction, stereo correspondence, optical flow and other applications. For example, in order to label a large image (or 3D volume) a multi-scale process first solves the problem at a low resolution, obtaining a coarse labeling of an original high resolution problem. This labeling is refined by solving another optimization on a subset of the image elements. In examples, an energy function for a coarse level version of an input image is formed directly from an energy function of the input image. In examples, the subset of image elements may be selected using a measure of confidence in the labeling. | 12-23-2010 |
20110210915 | Human Body Pose Estimation - Techniques for human body pose estimation are disclosed herein. Images such as depth images, silhouette images, or volumetric images may be generated and pixels or voxels of the images may be identified. The techniques may process the pixels or voxels to determine a probability that each pixel or voxel is associated with a segment of a body captured in the image or to determine a three-dimensional representation for each pixel or voxel that is associated with a location on a canonical body. These probabilities or three-dimensional representations may then be utilized along with the images to construct a posed model of the body captured in the image. | 09-01-2011 |
20120194516 | Three-Dimensional Environment Reconstruction - Three-dimensional environment reconstruction is described. In an example, a 3D model of a real-world environment is generated in a 3D volume made up of voxels stored on a memory device. The model is built from data describing a camera location and orientation, and a depth image with pixels indicating a distance from the camera to a point in the environment. A separate execution thread is assigned to each voxel in a plane of the volume. Each thread uses the camera location and orientation to determine a corresponding depth image location for its associated voxel, determines a factor relating to the distance between the associated voxel and the point in the environment at the corresponding location, and updates a stored value at the associated voxel using the factor. Each thread iterates through an equivalent voxel in the remaining planes of the volume, repeating the process to update the stored value. | 08-02-2012 |
20120194517 | Using a Three-Dimensional Environment Model in Gameplay - Use of a 3D environment model in gameplay is described. In an embodiment, a mobile depth camera is used to capture a series of depth images as it is moved around and a dense 3D model of the environment is generated from this series of depth images. This dense 3D model is incorporated within an interactive application, such as a game. The mobile depth camera is then placed in a static position for an interactive phase, which in some examples is gameplay, and the system detects motion of a user within a part of the environment from a second series of depth images captured by the camera. This motion provides a user input to the interactive application, such as a game. In further embodiments, automatic recognition and identification of objects within the 3D model may be performed and these identified objects then change the way that the interactive application operates. | 08-02-2012 |
20120194644 | Mobile Camera Localization Using Depth Maps - Mobile camera localization using depth maps is described for robotics, immersive gaming, augmented reality and other applications. In an embodiment a mobile depth camera is tracked in an environment at the same time as a 3D model of the environment is formed using the sensed depth data. In an embodiment, when camera tracking fails, this is detected and the camera is relocalized either by using previously gathered keyframes or in other ways. In an embodiment, loop closures are detected in which the mobile camera revisits a location, by comparing features of a current depth map with the 3D model in real time. In embodiments the detected loop closures are used to improve the consistency and accuracy of the 3D model of the environment. | 08-02-2012 |
20120194650 | Reducing Interference Between Multiple Infra-Red Depth Cameras - Systems and methods for reducing interference between multiple infra-red depth cameras are described. In an embodiment, the system comprises multiple infra-red sources, each of which projects a structured light pattern into the environment. A controller is used to control the sources in order to reduce the interference caused by overlapping light patterns. Various methods are described including: cycling between the different sources, where the cycle used may be fixed or may change dynamically based on the scene detected using the cameras; setting the wavelength of each source so that overlapping patterns are at different wavelengths; moving source-camera pairs in independent motion patterns; and adjusting the shape of the projected light patterns to minimize overlap. These methods may also be combined in any way. In another embodiment, the system comprises a single source and a mirror system is used to cast the projected structured light pattern around the environment. | 08-02-2012 |
20120195471 | Moving Object Segmentation Using Depth Images - Moving object segmentation using depth images is described. In an example, a moving object is segmented from the background of a depth image of a scene received from a mobile depth camera. A previous depth image of the scene is retrieved, and compared to the current depth image using an iterative closest point algorithm. The iterative closest point algorithm includes a determination of a set of points that correspond between the current depth image and the previous depth image. During the determination of the set of points, one or more outlying points are detected that do not correspond between the two depth images, and the image elements at these outlying points are labeled as belonging to the moving object. In examples, the iterative closest point algorithm is executed as part of an algorithm for tracking the mobile depth camera, and hence the segmentation does not add substantial additional computational complexity. | 08-02-2012 |
20120196679 | Real-Time Camera Tracking Using Depth Maps - Real-time camera tracking using depth maps is described. In an embodiment depth map frames are captured by a mobile depth camera at over 20 frames per second and used to dynamically update in real-time a set of registration parameters which specify how the mobile depth camera has moved. In examples the real-time camera tracking output is used for computer game applications and robotics. In an example, an iterative closest point process is used with projective data association and a point-to-plane error metric in order to compute the updated registration parameters. In an example, a graphics processing unit (GPU) implementation is used to optimize the error metric in real-time. In some embodiments, a dense 3D model of the mobile camera environment is used. | 08-02-2012 |
20120207346 | Detecting and Localizing Multiple Objects in Images Using Probabilistic Inference - An object detection system is disclosed herein. The object detection system allows detection of one or more objects of interest using a probabilistic model. The probabilistic model may include voting elements usable to determine which hypotheses for locations of objects are probabilistically valid. The object detection system may apply an optimization algorithm such as a simple greedy algorithm to find hypotheses that optimize or maximize a posterior probability or log-posterior of the probabilistic model or a hypothesis receiving a maximal probabilistic vote from the voting elements in a respective iteration of the algorithm. Locations of detected objects may then be ascertained based on the found hypotheses. | 08-16-2012 |
20120219209 | Image Labeling with Global Parameters - Image labeling with global parameters is described. In an embodiment a pose estimation system executes automatic body part labeling. For example, the system may compute joint recognition or body part segmentation for a gaming application. In another example, the system may compute organ labels for a medical imaging application. In an example, at least one global parameter, for example body height is computed for each of the images to be labeled. In an example, the global parameter is used to modify an image labeling process. For example the global parameter may be used to modify the input image to a canonical scale. In another example, the global parameter may be used to adaptively modify previously stored parameters of the image labeling process. In an example, the previously stored parameters may be computed from a reduced set of training data. | 08-30-2012 |
20120225719 | Gesture Detection and Recognition - A gesture detection and recognition technique is described. In one example, a sequence of data items relating to the motion of a gesturing user is received. A selected set of data items from the sequence are tested against pre-learned threshold values, to determine a probability of the sequence representing a certain gesture. If the probability is greater than a predetermined value, then the gesture is detected, and an action taken. In examples, the tests are performed by a trained decision tree classifier. In another example, the sequence of data items can be compared to pre-learned templates, and the similarity between them determined. If the similarity for a template exceeds a threshold, a likelihood value associated with a future time for a gesture associated with that template is updated. Then, when the future time is reached, the gesture is detected if the likelihood value is greater than a predefined value. | 09-06-2012 |
20120237127 | Grouping Variables for Fast Image Labeling - This application describes grouping variables together to minimize cost or time of performing computer vision analysis techniques on images. In one instance, the pixels of an image are represented by a lattice structure of nodes that are connected to each other by edges. The nodes are grouped or merged together based in part on the energy function associated with each edge that connects the nodes together. The energy function of the edge is based in part on the energy functions associated with each node. The energy functions of the node are based on the possible states in which the node may exist. The states of the node are representative of an object, image, or any other feature or classification that may be associated with the pixels in the image. | 09-20-2012 |
20120239174 | Predicting Joint Positions - Predicting joint positions is described, for example, to find joint positions of humans or animals (or parts thereof) in an image to control a computer game or for other applications. In an embodiment image elements of a depth image make joint position votes so that for example, an image element depicting part of a torso may vote for a position of a neck joint, a left knee joint and a right knee joint. A random decision forest may be trained to enable image elements to vote for the positions of one or more joints and the training process may use training images of bodies with specified joint positions. In an example a joint position vote is expressed as a vector representing a distance and a direction of a joint position from an image element making the vote. The random decision forest may be trained using a mixture of objectives. | 09-20-2012 |
20120251008 | Classification Algorithm Optimization - Classification algorithm optimization is described. In an example, a classification algorithm is optimized by calculating an evaluation sequence for a set of weighted feature functions that orders the feature functions in accordance with a measure of influence on the classification algorithm. Classification thresholds are determined for each step of the evaluation sequence, which indicate whether a classification decision can be made early and the classification algorithm terminated without evaluating further feature functions. In another example, a classifier applies the weighted feature functions to previously unseen data in the order of the evaluation sequence and determines a cumulative value at each step. The cumulative value is compared to the classification thresholds at each step to determine whether a classification decision can be made early without evaluating further feature functions. | 10-04-2012 |
20120257814 | IMAGE COMPLETION USING SCENE GEOMETRY - Image completion using scene geometry is described, for example, to remove marks from digital photographs or complete regions which are blank due to editing. In an embodiment an image depicting, from a viewpoint, a scene of textured objects has regions to be completed. In an example, geometry of the scene is estimated from a depth map and the geometry used to warp the image so that at least some surfaces depicted in the image are fronto-parallel to the viewpoint. An image completion process is guided using distortion applied during the warping. For example, patches used to fill the regions are selected on the basis of distortion introduced by the warping. In examples where the scene comprises regions having only planar surfaces the warping process comprises rotating the image. Where the scene comprises non-planar surfaces, geodesic distances between image elements may be scaled to flatten the non-planar surfaces. | 10-11-2012 |
20120288186 | SYNTHESIZING TRAINING SAMPLES FOR OBJECT RECOGNITION - An enhanced training sample set containing new synthesized training images that are artificially generated from an original training sample set is provided to satisfactorily increase the accuracy of an object recognition system. The original sample set is artificially augmented by introducing one or more variations to the original images with little to no human input. There are a large number of possible variations that can be introduced to the original images, such as varying the image's position, orientation, and/or appearance and varying an object's context, scale, and/or rotation. Because there are computational constraints on the amount of training samples that can be processed by object recognition systems, one or more variations that will lead to a satisfactory increase in the accuracy of the object recognition performance are identified and introduced to the original images. | 11-15-2012 |
20120306734 | Gesture Recognition Techniques - In one or more implementations, a static geometry model is generated, from one or more images of a physical environment captured using a camera, using one or more static objects to model corresponding one or more objects in the physical environment. Interaction of a dynamic object with at least one of the static objects is identified by analyzing at least one image and a gesture is recognized from the identified interaction of the dynamic object with the at least one of the static objects to initiate an operation of the computing device. | 12-06-2012 |
20120306876 | GENERATING COMPUTER MODELS OF 3D OBJECTS - Generating computer models of 3D objects is described. In one example, depth images of an object captured by a substantially static depth camera are used to generate the model, which is stored in a memory device in a three-dimensional volume. Portions of the depth image determined to relate to the background are removed to leave a foreground depth image. The position and orientation of the object in the foreground depth image is tracked by comparison to a preceding depth image, and the foreground depth image is integrated into the volume by using the position and orientation to determine where to add data derived from the foreground depth image into the volume. In examples, the object is hand-rotated by a user before the depth camera. Hands that occlude the object are integrated out of the model as they do not move in sync with the object due to re-gripping. | 12-06-2012 |
20130107010 | SURFACE SEGMENTATION FROM RGB AND DEPTH IMAGES | 05-02-2013 |
20130156297 | Learning Image Processing Tasks from Scene Reconstructions - Learning image processing tasks from scene reconstructions is described where the tasks may include but are not limited to: image de-noising, image in-painting, optical flow detection, interest point detection. In various embodiments training data is generated from a 2 or higher dimensional reconstruction of a scene and from empirical images of the same scene. In an example a machine learning system learns at least one parameter of a function for performing the image processing task by using the training data. In an example, the machine learning system comprises a random decision forest. In an example, the scene reconstruction is obtained by moving an image capture apparatus in an environment where the image capture apparatus has an associated dense reconstruction and camera tracking system. | 06-20-2013 |
20130156298 | Using High-Level Attributes to Guide Image Processing - Using high-level attributes to guide image processing is described. In an embodiment high-level attributes of images of people such as height, torso orientation, body shape, gender are used to guide processing of the images for various tasks including but not limited to joint position detection, body part classification, medical image analysis and others. In various embodiments one or more random decision forests are trained using images where global variable values such as player height are known in addition to ground-truth data appropriate for the image processing task concerned. In some examples sequences of images are used where global variables are static or vary smoothly over the sequence. In some examples one or more trained random decision forests are used to find global variable values as well as output values for the task concerned such as joint positions or body part classes. | 06-20-2013 |
20130166481 | DISCRIMINATIVE DECISION TREE FIELDS - A tractable model solves certain labeling problems by providing potential functions having arbitrary dependencies upon an observed dataset (e.g., image data). The model uses decision trees corresponding to various factors to map dataset content to a set of parameters used to define the potential functions in the model. Some factors define relationships among multiple variable nodes. When making label predictions on a new dataset, the leaf nodes of the decision tree determine the effective weightings for such potential functions. In this manner, decision trees define non-parametric dependencies and can represent rich, arbitrary functional relationships if sufficient training data is available. Decision trees training is scalable, both in the training set size and by parallelization. Maximum pseudolikelihood learning can provide for joint training of aspects of the model, including feature test selection and ordering, factor weights, and the scope of the interacting variable nodes used in the graph. | 06-27-2013 |
20130244782 | REAL-TIME CAMERA TRACKING USING DEPTH MAPS - Real-time camera tracking using depth maps is described. In an embodiment depth map frames are captured by a mobile depth camera at over 20 frames per second and used to dynamically update in real-time a set of registration parameters which specify how the mobile depth camera has moved. In examples the real-time camera tracking output is used for computer game applications and robotics. In an example, an iterative closest point process is used with projective data association and a point-to-plane error metric in order to compute the updated registration parameters. In an example, a graphics processing unit (GPU) implementation is used to optimize the error metric in real-time. In some embodiments, a dense 3D model of the mobile camera environment is used. | 09-19-2013 |
20130346844 | CHECKING AND/OR COMPLETION FOR DATA GRIDS - Checking and/or completing for data grids is described such as for grids having rows and columns of cells at least some of which contain data values such as numbers or categories. In various embodiments predictive probability distributions are obtained from an inference engine for one or more of the cells and the predictive probability distributions are used for various tasks such as to suggest values to complete blank cells, highlight cells having outlying values, identify potential errors, suggest corrections to potential errors, identify similarities between cells, identify differences between cells, cluster rows of the data grid, and other tasks. In various embodiments a graphical user interface displays a data grid and provides facilities for completing, error checking/correcting, and analyzing data in the data grid. | 12-26-2013 |
20140169444 | IMAGE SEQUENCE ENCODING/DECODING USING MOTION FIELDS - Compressing motion fields is described. In one example video compression may comprise computing a motion field representing the difference between a first image and a second image, the motion field being used to make a prediction of the second image. In various examples of encoding a sequence of video data the first image, motion field and a residual representing the error in the prediction may be encoded rather than the full image sequence. In various examples the motion field may represented by its coefficients in a linear basis, for example a wavelet basis, and an optimization may be carried out to minimize the cost of encoding the motion field and maximize the quality of the reconstructed image while also minimizing the residual error. In various examples the optimized motion field may quantized to enable encoding. | 06-19-2014 |
20140247212 | Gesture Recognition Techniques - In one or more implementations, a static geometry model is generated, from one or more images of a physical environment captured using a camera, using one or more static objects to model corresponding one or more objects in the physical environment. Interaction of a dynamic object with at least one of the static objects is identified by analyzing at least one image and a gesture is recognized from the identified interaction of the dynamic object with the at least one of the static objects to initiate an operation of the computing device. | 09-04-2014 |
20140307956 | IMAGE LABELING USING GEODESIC FEATURES - Image labeling is described, for example, to recognize body organs in a medical image, to label body parts in a depth image of a game player, to label objects in a video of a scene. In various embodiments an automated classifier uses geodesic features of an image, and optionally other types of features, to semantically segment an image. For example, the geodesic features relate to a distance between image elements, the distance taking into account information about image content between the image elements. In some examples the automated classifier is an entangled random decision forest in which data accumulated at earlier tree levels is used to make decisions at later tree levels. In some examples the automated classifier has auto-context by comprising two or more random decision forests. In various examples parallel processing and look up procedures are used. | 10-16-2014 |
20150134576 | MEMORY FACILITATION USING DIRECTED ACYCLIC GRAPHS - Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters. | 05-14-2015 |
20150213360 | CROWDSOURCING SYSTEM WITH COMMUNITY LEARNING - Crowdsourcing systems with machine learning are described, for example, to aggregate answers to a crowdsourced task in a manner achieving good accuracy even where observed data about past behavior of crowd members is sparse. In various examples a machine learning system jointly learns variables describing characteristics of both individual crowd workers and communities of the workers. In various examples, the machine learning system learns aggregated labels. In examples learnt variables describing characteristics of an individual crowd worker are related, by addition of noise, to learnt variables describing characteristics of a community of which the individual is a member. In examples the crowdsourcing system uses the learnt variables describing characteristics of individual workers and of communities of workers for any one or more of: active learning, targeted training of workers, targeted issuance of tasks, calculating and issuing rewards. | 07-30-2015 |
20150228114 | CONTOUR COMPLETION FOR AUGMENTING SURFACE RECONSTRUCTIONS - Surface reconstruction contour completion embodiments are described which provide dense reconstruction of a scene from images captured from one or more viewpoints. Both a room layout and the full extent of partially occluded objects in a room can be inferred using a Contour Completion Random Field model to augment a reconstruction volume. The augmented reconstruction volume can then be used by any surface reconstruction pipeline to show previously occluded objects and surfaces. | 08-13-2015 |
20150248764 | DEPTH SENSING USING AN INFRARED CAMERA - A method of sensing depth using an infrared camera. In an example method, an infrared image of a scene is received from an infrared camera. The infrared image is applied to a trained machine learning component which uses the intensity of image elements to assign all or some of the image elements a depth value which represents the distance between the surface depicted by the image element and the infrared camera. In various examples, the machine line component comprises one or more random decision forests. | 09-03-2015 |
20150248765 | DEPTH SENSING USING AN RGB CAMERA - A method of sensing depth using an RGB camera. In an example method, a color image of a scene is received from an RGB camera. The color image is applied to a trained machine learning component which uses features of the image elements to assign all or some of the image elements a depth value which represents the distance between the surface depicted by the image element and the RGB camera. In various examples, the machine learning component comprises one or more entangled geodesic random decision forests. | 09-03-2015 |
20150296152 | SENSOR DATA FILTERING - Filtering sensor data is described, for example, where filters conditioned on a local appearance of the signal are predicted by a machine learning system, and used to filter the sensor data. In various examples the sensor data is a stream of noisy video image data and the filtering process denoises the video stream. In various examples the sensor data is a depth image and the filtering process refines the depth image which may then be used for gesture recognition or other purposes. In various examples the sensor data is one dimensional measurement data from an electric motor and the filtering process denoises the measurements. In examples the machine learning system comprises a random decision forest where trees of the forest store filters at their leaves. In examples, the random decision forest is trained using a training objective with a data dependent regularization term. | 10-15-2015 |
20150302317 | NON-GREEDY MACHINE LEARNING FOR HIGH ACCURACY - Non-greedy machine learning for high accuracy is described, for example, where one or more random decision trees are trained for gesture recognition in order to control a computing-based device. In various examples, a random decision tree or directed acyclic graph (DAG) is grown using a greedy process and is then post-processed to recalculate, in a non-greedy process, leaf node parameters and split function parameters of internal nodes of the graph. In various examples the very large number of options to be assessed by the non-greedy process is reduced by using a constrained objective function. In examples the constrained objective function takes into account a binary code denoting decisions at split nodes of the tree or DAG. In examples, resulting trained decision trees are more compact and have improved generalization and accuracy. | 10-22-2015 |
20150347846 | TRACKING USING SENSOR DATA - Tracking using sensor data is described, for example, where a plurality of machine learning predictors are used to predict a plurality of complementary, or diverse, parameter values of a process describing how the sensor data arises. In various examples a selector selects which of the predicted values are to be used, for example, to control a computing device. In some examples the tracked parameter values are pose of a moving camera or pose of an object moving in the field of view of a static camera; in some examples the tracked parameter values are of a 3D model of a hand or other articulated or deformable entity. The machine learning predictors have been trained in series, with training examples being reweighted after training an individual predictor, to favour training examples on which the set of predictors already trained performs poorly. | 12-03-2015 |
20150356774 | LAYOUT DESIGN USING LOCALLY SATISFIABLE PROPOSALS - A “Layout Optimizer” provides various real-time iterative constraint-satisfaction methodologies that use constraint-based frameworks to generate optimized layouts that map or embed virtual objects into environments. The term environment refers to combinations of environmental characteristics, including, but not limited to, 2D or 3D scene geometry or layout, scene colors, patterns, and/or textures, scene illumination, scene heat sources, fixed or moving people, objects or fluids, etc., any of which may evolve or change over time. A set of parameters are specified or selected for each object. Further, the environmental characteristics are determined automatically or specified by users. Relationships between objects and/or the environment derived from constraints associated with objects and the environment are then used to iteratively determine optimized self-consistent and scene-consistent object layouts. This enables the Layout Optimizer to augment environments with arbitrary content in a structured constraint-based process that adapts to changing scenes or environments. | 12-10-2015 |
20160034840 | Adaptive Task Assignment - Crowdsourcing using active learning is described, for example, to select pairs of tasks and groups of workers so that information gained about answers to the tasks in the pool is optimized. In various examples a machine learning system learns variables describing characteristics of communities of workers, characteristics of workers, task variables and uncertainty of these variables. In various examples, the machine learning system predicts task variables and uncertainty of the predicted task variables for possible combinations of communities of workers and tasks. In examples the predicted variables and uncertainty are used to calculate expected information gain of the possible combinations and to rank the possible combinations. In examples, the crowdsourcing system uses the expected information gain to allocate tasks to worker communities and observe the results; the results may then be used to update the machine learning system. | 02-04-2016 |
20160085310 | TRACKING HAND/BODY POSE - Tracking hand or body pose from image data is described, for example, to control a game system, natural user interface or for augmented reality. In various examples a prediction engine takes a single frame of image data and predicts a distribution over a pose of a hand or body depicted in the image data. In examples, a stochastic optimizer has a pool of candidate poses of the hand or body which it iteratively refines, and samples from the predicted distribution are used to replace some candidate poses in the pool. In some examples a best candidate pose from the pool is selected as the current tracked pose and the selection processes uses a 3D model of the hand or body. | 03-24-2016 |
20160104031 | DEPTH FROM TIME OF FLIGHT CAMERA - Region of interest detection in raw time of flight images is described. For example, a computing device receives at least one raw image captured for a single frame by a time of flight camera. The raw image depicts one or more objects in an environment of the time of flight camera (such as human hands, bodies or any other objects). The raw image is input to a trained region detector and in response one or more regions of interest in the raw image are received. A received region of interest comprises image elements of the raw image which are predicted to depict at least part of one of the objects. A depth computation logic computes depth from the one or more regions of interest of the raw image. | 04-14-2016 |
20160104070 | INFERENCE ENGINE FOR EFFICIENT MACHINE LEARNING - An inference engine is described for efficient machine learning. For example, an inference engine executes a plurality of ordered steps to carry out inference on the basis of observed data. For each step, a plurality of inputs to the step are received. A predictor predicts an output of the step and computes uncertainty of the prediction. Either the predicted output or a known output is selected on the basis of the uncertainty. If the known output is selected, the known output is computed, (for example, using a resource intensive, accurate process). The predictor is retrained using the known output and the plurality of inputs of the step as training data. For example, computing the prediction is fast and efficient as compared with computing the known output. | 04-14-2016 |
20160127715 | MODEL FITTING FROM RAW TIME-OF-FLIGHT IMAGES - Model fitting from raw time of flight image data is described, for example, to track position and orientation of a human hand or other entity. In various examples, raw image data depicting the entity is received from a time of flight camera. A 3D model of the entity is accessed and used to render, from the 3D model, simulations of raw time of flight image data depicting the entity in a specified pose/shape. The simulated raw image data and at least part of the received raw image data are compared and on the basis of the comparison, parameters of the entity are computed. | 05-05-2016 |