Abstract: Technologies and techniques for vehicle perception. A contour extractor apparatus extracts contours from image data. Mapping offsets are determined between at least some of the grid points of a current image map and respective grid points of a next image map, and image velocity vectors are determined for at least some of mapping offsets. At least some of the grid points of the next image are warped to the respective grid points of the current image map. A determination is made if a contour of the warped grid points of the next image matches a contour of the respective grid points of the current map within a configured parameter. Object movement movement may then be determined from the image data, if the contour of the warped grid points of the next image matches the contour of the respective grid points of the current map within the configured parameter.

Abstract: A method is provided. The method includes generating a set of candidate training data based on a simulated environment and a first set of environmental parameters. The method also includes training a machine learning model based on the set of candidate training data. The method further includes obtaining a set of segmentations based on the machine learning model and a set of test data. The method further includes determining whether a mean intersection-over-union (MIOU) of the set of segmentations has increased by more than a threshold change. The method further includes generating a next set of candidate training data based on the simulated environment and a second set of environmental parameters for the simulated environment, in response to determining that the MIOU has increased by more than the threshold MIOU amount.

Abstract: Technologies and techniques for vehicle perception. A first contour of a current image a dna second contour of a next image are determined relative to an optical center. The current image is scaled to the next image relative to the optical center, wherein the scaling includes applying a scale vector to the first contour. A frame offset vector is determined, and the second contour is translated, based on the frame offset vector and the scale vector, to align the translated second contour to a focus of expansion. An image velocity is determined, based on the first contour and the translated second contour, wherein the image velocity is used to determine object movement from the image data.

Abstract: Technologies and techniques for vehicle perception. Contours are extracted from image data, and a first and second contour of a current image and next image are determined along a plurality of image row boundaries, wherein the contours includes a plurality of contour points linked to each other via respective edges. An image velocity vector is applied to project each of the plurality of first contour points to the next image, wherein at least some of the projected first contour points are not located on an image row boundary. The projected contour points are processed to determine projected edges forming a projected link between each projected contour point. The projected contour points are moved along the projected link to align each of the moved projected contour points to a respective image boundary. Each of the moved projected contour points are then linked to each of the second contour points.

Abstract: A method is provided. The method includes generating a set of candidate training data based on a training data generator. The method also includes training a first machine learning model based on the set of candidate training data. The first machine learning model generates a set of inferences during the training based on the set of candidate training data. The method further includes determining a set of importance factors based on the set of inferences and a second machine learning model. The method further includes updating the training data generator based on one or more distributions of properties determined based on the set of importance factors.

Abstract: Technologies and techniques for vehicle perception. A first contour of a current image a dna second contour of a next image are determined relative to an optical center. The current image is scaled to the next image relative to the optical center, wherein the scaling includes applying a scale vector to the first contour. A frame offset vector is determined, and the second contour is translated, based on the frame offset vector and the scale vector, to align the translated second contour to a focus of expansion. An image velocity is determined, based on the first contour and the translated second contour, wherein the image velocity is used to determine object movement from the image data.

Abstract: Technologies and techniques for vehicle perception. A contour extractor apparatus extracts contours from image data. Mapping offsets are determined between at least some of the grid points of a current image map and respective grid points of a next image map, and image velocity vectors are determined for at least some of mapping offsets. At least some of the grid points of the next image are warped to the respective grid points of the current image map. A determination is made if a contour of the warped grid points of the next image matches a contour of the respective grid points of the current map within a configured parameter. Object movement movement may then be determined from the image data, if the contour of the warped grid points of the next image matches the contour of the respective grid points of the current map within the configured parameter.

Abstract: Technologies and techniques for vehicle perception. Contours are extracted from image data, and a first and second contour of a current image and next image are determined along a plurality of image row boundaries, wherein the contours includes a plurality of contour points linked to each other via respective edges. An image velocity vector is applied to project each of the plurality of first contour points to the next image, wherein at least some of the projected first contour points are not located on an image row boundary. The projected contour points are processed to determine projected edges forming a projected link between each projected contour point. The projected contour points are moved along the projected link to align each of the moved projected contour points to a respective image boundary. Each of the moved projected contour points are then linked to each of the second contour points.

Abstract: In one embodiment, a method is provided. The method includes generating a set of candidate training data based on a simulated environment and a first set of environmental parameters. The method also includes training a machine learning model based on the set of candidate training data. The method further includes obtaining a set of segmentations based on the machine learning model and a set of test data. The method further includes determining whether a mean intersection-over-union (MIOU) of the set of segmentations has increased by more than a threshold change. The method further includes generating a next set of candidate training data based on the simulated environment and a second set of environmental parameters for the simulated environment, in response to determining that the MIOU has increased by more than the threshold MIOU amount.