Patent application number | Description | Published |
20100060736 | Vehicle Interior Classification System And Method - A vehicle interior classification system and method in accordance with the present invention determines a classification relating to the interior of the vehicle, such as the occupancy status of a vehicle seat or the state of alertness of a vehicle driver, from one or more images of an appropriate portion of the interior of the vehicle acquired with an image capture device. The acquired images are preferably processed to limit the dynamic range of the images to obtain a resultant image which can comprise one or more regions of interest which are less than the total field of view of the image capture device. The resultant images are processed to extract information about features in the image and, in one embodiment, this processing is achieved with a two-dimensional complex discrete wavelet transform which produces a set of coefficients corresponding to the presence and/or location of the features in the resultant image. The set of coefficients produced with such a transform is potentially quite large and can be reduced, through described techniques, to a subset of the total number of coefficients, the members of the subset being selected for their ability to discriminate between the classifications defined for the system. By selecting a subset of the possible coefficients, computational requirements are reduced, as are hardware requirements in the system, such as memory. The selected set of coefficients (whether comprising all of the coefficients or a subset thereof) are provided to a classifier which processes the coefficients with a set of calibration vectors, that were determined when the system was calibrated, to determine the most probable classification for the portion of the vehicle interior. | 03-11-2010 |
20140043473 | METHOD AND SYSTEM FOR DYNAMICALLY CALIBRATING VEHICULAR CAMERAS - A method of dynamically ascertaining the alignment of a vehicular camera. The method involves acquiring a sequence of images provided by the camera whilst the vehicle is in motion. For each range of steering angles, the method (i) selects a plurality of feature points in the images, (ii) tracks a motion trajectory for each selected feature point, and (iii) determines a vanishing point in the image plane based on the tracked motion trajectories. The method determines a vanishing line in the image plane based on a locus of these vanishing points and determines the alignment of the camera based on the position of a central vanishing point (corresponding to the zero degree angle) and the vanishing line. | 02-13-2014 |
20140063254 | METHOD FOR CALIBRATING VEHICULAR VISION SYSTEM - A method for calibrating a vehicular vision system includes providing a camera at a vehicle, with the camera having a field of view. Images are captured with the camera and a set of resultant images are acquired for a classification. Information is extracted related to image features in the set of resultant images, and an appropriate subset of coefficients is determined. For each classification, a classification vector of at least one appropriate weight is stored that corresponds to the determined subset of coefficients. | 03-06-2014 |
20140169627 | IMAGE PROCESSING METHOD FOR DETECTING OBJECTS USING RELATIVE MOTION - An image based obstacle detection method. A camera mounted on a vehicle provides a set of image frames whilst the vehicle is in motion. The image frames define an image plane having a vertical aspect and a horizontal aspect. The relevancy of an object is determined by (i) selecting first and second feature points from the object that are spaced apart vertically in a first image frame; (ii) tracking the positions of the first and second feature points over at least a second image frame; and (iii) deciding the object to be relevant if the first and second feature points move dissimilar distances in physical space, within a tolerance, and deciding the object to be irrelevant otherwise. The motion of relevant objects is then estimated to determine if any relevant object is likely to become an obstacle to the vehicle. | 06-19-2014 |
20140247352 | MULTI-CAMERA DYNAMIC TOP VIEW VISION SYSTEM - A dynamic image stitching system for stitching images captured by multiple cameras of a vision system of a vehicle includes a first camera disposed at a vehicle and having a first field of view exterior the vehicle and a second camera disposed at the vehicle and having a second field of view exterior the vehicle. The first and second fields of view at least partially overlap. A processor is operable to process image data captured by the first and second cameras. The processor processes captured image data to determine characteristics of features or objects present in the overlapping region of the first and second fields of view. The processor is operable to adjust a stitching algorithm responsive to a determination of a difference between a characteristic of a feature as captured by the first camera and the characteristic of the feature as captured by the second camera. | 09-04-2014 |
20150049193 | METHOD AND SYSTEM FOR DYNAMICALLY CALIBRATING VEHICULAR CAMERAS - A method of dynamically calibrating a given camera relative to a reference camera of a vehicle includes identifying an overlapping region in an image frame provided by the given camera and an image frame provided by the reference camera and selecting at least a portion of an object in the overlapped region of the reference image frame. Expected pixel positions of the selected object portion in the given image frame is determined based on the location of the selected object portion in the reference image frame, and pixel positions of the selected object portion are located as detected in the given image frame. An alignment of the given camera is determined based on a comparison of the pixel positions of the selected object portion in the given image frame to the expected pixel positions of the selected object portion in the given image frame. | 02-19-2015 |
20150178576 | VEHICLE VISION SYSTEM WITH ENHANCED PEDESTRIAN DETECTION - A vision system of a vehicle includes a camera disposed at a vehicle and having a field of view that encompasses first and second regions exterior of the vehicle. The camera captures image data that includes a first set of image data representative of the first region of the field of view and a second set of image data representative of the second region of the field of view. An image processor processes the first set of image data to detect a pedestrian present in the first region based on a first predetermined orientation of a pedestrian. The image processor processes the second set of image data to detect a pedestrian present in the second region based on a second predetermined orientation of a pedestrian. | 06-25-2015 |
20150179074 | VEHICLE VISION SYSTEM WITH CROSS TRAFFIC DETECTION - A vision system of a vehicle includes a camera disposed at a vehicle and having a field of view exterior of the vehicle. The camera may have a wide angle lens with more distortion at the side regions of the field of view than at a center region of the field of view. An image processor processes captured image data to determine gradient information of captured image data, and responsive to processing gradient information, determines a potential cross traffic object at one of the side regions of the field of view. The image processor processes multiple frames of captured image data to determine movement of an upper portion and a lower portion of a gradient of the determined potential cross traffic object and, responsive to such processing, determines if the detected potential cross traffic object is a cross traffic object that is moving into the path of the vehicle. | 06-25-2015 |