Abstract: An example driver assistance system includes an object detection (OD) network, a semantic segmentation network, a processor, and a memory. In an example method, an image is received and stored in the memory. An object detection (OD) polygon is generated for each object detected in the image, and each OD polygon encompasses at least a portion of the corresponding object detected in the image. A region of interest (ROI) is associated with each OD polygon. Such method may further comprise generating a mask for each ROI, each mask configured as a bitmap approximating a size of the corresponding ROI; generating at least one boundary polygon for each mask based on the corresponding mask, each boundary polygon having multiple vertices and enclosing the corresponding mask; and reducing a number of vertices of the boundary polygons based on a comparison between points of the boundary polygons and respective points on the bitmaps.

Abstract: An example driver assistance system includes an object detection (OD) network, a semantic segmentation network, a processor, and a memory. In an example method, an image is received and stored in the memory. An object detection (OD) polygon is generated for each object detected in the image, and each OD polygon encompasses at least a portion of the corresponding object detected in the image. A region of interest (ROI) is associated with each OD polygon. Such method may further comprise generating a mask for each ROI, each mask configured as a bitmap approximating a size of the corresponding ROI; generating at least one boundary polygon for each mask based on the corresponding mask, each boundary polygon having multiple vertices and enclosing the corresponding mask; and reducing a number of vertices of the boundary polygons based on a comparison between points of the boundary polygons and respective points on the bitmaps.

Abstract: A method for video object detection includes detecting an object in a first video frame, and selecting a first interest point and a second interest point of the object. The first interest point is in a first region of interest located at a first corner of a box surrounding the object. The second interest point is in a second region of interest located at a second corner of the box. The second corner is diagonally opposite the first corner. A first optical flow of the first interest point and a second optical flow of the second interest point are determined. A location of the object in a second video frame is estimated by determining, in the second video frame, a location of the first interest point based on the first optical flow and a location of the second interest point based on the second optical flow.

Abstract: In described examples, an apparatus includes an object detection (OD) network that is configured to generate OD polygons in response to a received at least one camera image and a semantic segmentation (SS) network that is configured to generate SS data in response to the received at least one camera image. A processor is configured to generate an updated occupancy grid in response to the OD polygons and the SS data. A vehicle is optionally configured to respond to a driving action generated in response to the updated occupancy grid.

Abstract: Disclosed examples include image processing methods and systems to process image data, including computing a plurality of scaled images according to input image data for a current image frame, computing feature vectors for locations of the individual scaled images, classifying the feature vectors to determine sets of detection windows, and grouping detection windows to identify objects in the current frame, where the grouping includes determining first clusters of the detection windows using non-maxima suppression grouping processing, determining positions and scores of second clusters using mean shift clustering according to the first clusters, and determining final clusters representing identified objects in the current image frame using non-maxima suppression grouping of the second clusters.

Abstract: Techniques for localizing a vehicle include obtaining an image from a camera, identifying a set of image feature points in the image, obtaining an approximate location of the vehicle, determining a set of sub-volumes (SVs) of a map to access based on the approximate location, obtaining map feature points and associated map feature descriptors associated with the set of SVs, determining a set of candidate matches between the set of image feature points and the obtained map feature points, determining a set of potential poses of the camera from candidate matches from the set of candidate matches and an associated reprojection error estimated for remaining points to select a first pose of the set of potential poses having a lowest associated reprojection error, determining the first pose is within a threshold value of an expected vehicle location, and outputting a vehicle location based on the first pose.

Abstract: A computer vision system is provided that includes a camera capture component configured to capture an image from a camera, a memory, and an image compression decompression engine (ICDE) coupled to the memory and configured to receive each line of the image, and compress each line to generate a compressed bit stream. To compress a line, the ICDE is configured to divide the line into compression units, and compress each compression unit, wherein to compress a compression unit, the ICDE is configured to perform delta prediction on the compression unit to generate a delta predicted compression unit, compress the delta predicted compression unit using exponential Golomb coding to generate a compressed delta predicted compression unit, and add the compressed delta predicted compression unit to the compressed bit stream.

Abstract: A method for multi-label image classification in a convolutional neural network (CNN) is provided that includes forming a composite image from a plurality of clipped images, and processing the composite image by the CNN to generate a probability vector for each clipped image of the plurality of clipped images, wherein a length of a probability vector is equal to a number of classes the CNN is designed to classify.

Abstract: Techniques for localizing a vehicle including obtaining an image from a camera, identifying a set of image feature points in the image, obtaining an approximate location of the vehicle, determining a set of sub-volumes (SVs) of a map to access based on the approximate location, obtaining map feature points and associated map feature descriptors associated with the set of SVs, determining a set of candidate matches between the set of image feature points and the obtained map feature points, determining a set of potential poses of the camera from candidate matches from the set of candidate matches and an associated reprojection error estimated for remaining points to select a first pose of the set of potential poses having a lowest associated reprojection error, determining the first pose is within a threshold value of an expected vehicle location, and outputting a vehicle location based on the first pose.

Abstract: A computer vision system is provided that includes a camera capture component configured to capture an image from a camera, a memory, and an image compression decompression engine (ICDE) coupled to the memory and configured to receive each line of the image, and compress each line to generate a compressed bit stream. To compress a line, the ICDE is configured to divide the line into compression units, and compress each compression unit, wherein to compress a compression unit, the ICDE is configured to perform delta prediction on the compression unit to generate a delta predicted compression unit, compress the delta predicted compression unit using exponential Golomb coding to generate a compressed delta predicted compression unit, and add the compressed delta predicted compression unit to the compressed bit stream.

Abstract: An image processing system includes a processor and optical flow (OF) determination logic for quantifying relative motion of a feature present in a first frame of video and a second frame of video that provide at least one of temporally and spatially ordered images with respect to the two frames of video. The OF determination logic configures the processor to implement performing OF estimation between the first frame and second frame using a pyramidal block matching (PBM) method to generate an initial optical flow (OF) estimate at a base pyramid level having integer pixel resolution, and refining the initial OF estimate using at least one pass of a modified Lucas-Kanade (LK) method to provide a revised OF estimate having fractional pixel resolution.

Abstract: In described examples of a method for quantizing data for a convolutional neural network (CNN) is provided. A set of data is received and quantized the using a power-of-2 parametric activation (PACT2) function. The PACT2 function arranges the set of data as a histogram and discards a portion of the data corresponding to a tail of the histogram to form a remaining set of data. A clipping value is determined by expanding the remaining set of data to a nearest power of two value. The set of data is then quantized using the clipping value. With PACT2, a model can be quantized either using post training quantization or using quantization aware training. PACT2 helps a quantized model to achieve close accuracy compared to the corresponding floating-point model.

Abstract: A method for video object detection includes detecting an object in a first video frame, and selecting a first interest point and a second interest point of the object. The first interest point is in a first region of interest located at a first corner of a box surrounding the object. The second interest point is in a second region of interest located at a second corner of the box. The second corner is diagonally opposite the first corner. A first optical flow of the first interest point and a second optical flow of the second interest point are determined. A location of the object in a second video frame is estimated by determining, in the second video frame, a location of the first interest point based on the first optical flow and a location of the second interest point based on the second optical flow.

Abstract: A method for video object detection includes detecting an object in a first video frame, and selecting a first interest point and a second interest point of the object. The first interest point is in a first region of interest located at a first corner of a box surrounding the object. The second interest point is in a second region of interest located at a second corner of the box. The second corner is diagonally opposite the first corner. A first optical flow of the first interest point and a second optical flow of the second interest point are determined. A location of the object in a second video frame is estimated by determining, in the second video frame, a location of the first interest point based on the first optical flow and a location of the second interest point based on the second optical flow.

Abstract: Techniques for localizing a vehicle are provided that include obtaining an image from a camera, identifying a set of image feature points in the image, obtaining an approximate location of the vehicle, determining a set of sub-volumes (SVs) of a map to access based on the approximate location, obtaining map feature points and associated map feature descriptors associated with the set of SVs, determining a set of candidate matches between the set of image feature points and the obtained map feature points, determining a set of potential poses of the camera from candidate matches from the set of candidate matches and an associated reprojection error estimated for remaining points to select a first pose of the set of potential poses having a lowest associated reprojection error, determining the first pose is within a threshold value of an expected vehicle location, and outputting a vehicle location based on the first pose.

Abstract: A computer vision system is provided that includes a camera capture component configured to capture an image from a camera, a memory, and an image compression decompression engine (ICDE) coupled to the memory and configured to receive each line of the image, and compress each line to generate a compressed bit stream. To compress a line, the ICDE is configured to divide the line into compression units, and compress each compression unit, wherein to compress a compression unit, the ICDE is configured to perform delta prediction on the compression unit to generate a delta predicted compression unit, compress the delta predicted compression unit using exponential Golomb coding to generate a compressed delta predicted compression unit, and add the compressed delta predicted compression unit to the compressed bit stream.

Abstract: In described examples, an apparatus includes an object detection (OD) network that is configured to generate OD polygons in response to a received at least one camera image and a semantic segmentation (SS) network that is configured to generate SS data in response to the received at least one camera image. A processor is configured to generate an updated occupancy grid in response to the OD polygons and the SS data. A vehicle is optionally configured to respond to a driving action generated in response to the updated occupancy grid.

Abstract: Disclosed examples include image processing methods and systems to process image data, including computing a plurality of scaled images according to input image data for a current image frame, computing feature vectors for locations of the individual scaled images, classifying the feature vectors to determine sets of detection windows, and grouping detection windows to identify objects in the current frame, where the grouping includes determining first clusters of the detection windows using non-maxima suppression grouping processing, determining positions and scores of second clusters using mean shift clustering according to the first clusters, and determining final clusters representing identified objects in the current image frame using non-maxima suppression grouping of the second clusters.

Abstract: A computer vision system is provided that includes a camera capture component configured to capture an image from a camera, a memory, and an image compression decompression engine (ICDE) coupled to the memory and configured to receive each line of the image, and compress each line to generate a compressed bit stream. To compress a line, the ICDE is configured to divide the line into compression units, and compress each compression unit, wherein to compress a compression unit, the ICDE is configured to perform delta prediction on the compression unit to generate a delta predicted compression unit, compress the delta predicted compression unit using exponential Golomb coding to generate a compressed delta predicted compression unit, and add the compressed delta predicted compression unit to the compressed bit stream.

Abstract: Disclosed examples include image processing methods and systems to process image data, including computing a plurality of scaled images according to input image data for a current image frame, computing feature vectors for locations of the individual scaled images, classifying the feature vectors to determine sets of detection windows, and grouping detection windows to identify objects in the current frame, where the grouping includes determining first clusters of the detection windows using non-maxima suppression grouping processing, determining positions and scores of second clusters using mean shift clustering according to the first clusters, and determining final clusters representing identified objects in the current image frame using non-maxima suppression grouping of the second clusters.