Abstract: A system and method for multitask processing for autonomous vehicle computation and control includes: receiving training image data from a training image data collection system; performing a training phase to train a plurality of tasks associated with features of the training image data, the training phase including extracting common features from the training image data, causing the plurality of tasks to generate task-specific predictions based on the training image data, determining a bias between the task-specific prediction for each task and corresponding task-specific ground truth data, and adjusting parameters of each of the plurality of tasks to cause the bias to meet a pre-defined confidence level; receiving image data from an image data collection system associated with an autonomous vehicle; and performing an operational phase including extracting common features from the image data, causing the plurality of trained tasks to concurrently generate task-specific predictions based on the image data.

Abstract: A system and method for three-dimensional (3D) object detection is disclosed. A particular embodiment can be configured to: receive image data from a camera associated with a vehicle, the image data representing an image frame; use a machine learning module to determine at least one pixel coordinate of a two-dimensional (2D) bounding box around an object in the image frame; use the machine learning module to determine at least one vertex of a three-dimensional (3D) bounding box around the object; obtain camera calibration information associated with the camera; and determine 3D attributes of the object using the 3D bounding box and the camera calibration information.

Abstract: A system and method for fisheye image processing can be configured to: receive fisheye image data from at least one fisheye lens camera associated with an autonomous vehicle, the fisheye image data representing at least one fisheye image frame; partition the fisheye image frame into a plurality of image portions representing portions of the fisheye image frame; warp each of the plurality of image portions to map an arc of a camera projected view into a line corresponding to a mapped target view, the mapped target view being generally orthogonal to a line between a camera center and a center of the arc of the camera projected view; combine the plurality of warped image portions to form a combined resulting fisheye image data set representing recovered or distortion-reduced fisheye image data corresponding to the fisheye image frame; generate auto-calibration data representing a correspondence between pixels in the at least one fisheye image frame and corresponding pixels in the combined resulting fisheye image

Abstract: A system and method for vehicle occlusion detection is disclosed.

Abstract: A system and method for image localization based on semantic segmentation are disclosed. A particular embodiment includes: receiving image data from an image generating device mounted on an autonomous vehicle; performing semantic segmentation or other object detection on the received image data to identify and label objects in the image data and produce semantic label image data; identifying extraneous objects in the semantic label image data; removing the extraneous objects from the semantic label image data; comparing the semantic label image data to a baseline semantic label map; and determining a vehicle location of the autonomous vehicle based on information in a matching baseline semantic label map.

Abstract: A system and method for three-dimensional (3D) object detection is disclosed. A particular embodiment can be configured to: receive image data from at least one camera associated with an autonomous vehicle, the image data representing at least one image frame; use a trained deep learning module to determine pixel coordinates of a two-dimensional (2D) bounding box around an object detected in the image frame; use the trained deep learning module to determine vertices of a three-dimensional (3D) bounding box around the object; use a fitting module to obtain geological information related to a particular environment associated with the image frame and to obtain camera calibration information associated with the at least one camera; and use the fitting module to determine 3D attributes of the object using the 3D bounding box, the geological information, and the camera calibration information.

Abstract: A system and method for taillight signal recognition using a convolutional neural network is disclosed. An example embodiment includes: receiving a plurality of image frames from one or more image-generating devices of an autonomous vehicle; using a single-frame taillight illumination status annotation dataset and a single-frame taillight mask dataset to recognize a taillight illumination status of a proximate vehicle identified in an image frame of the plurality of image frames, the single-frame taillight illumination status annotation dataset including one or more taillight illumination status conditions of a right or left vehicle taillight signal, the single-frame taillight mask dataset including annotations to isolate a taillight region of a vehicle; and using a multi-frame taillight illumination status dataset to recognize a taillight illumination status of the proximate vehicle in multiple image frames of the plurality of image frames, the multiple image frames being in temporal succession.

Abstract: A system and method for fisheye image processing is disclosed.

Abstract: A system and method for vehicle occlusion detection is disclosed.

Abstract: A system and method for actively selecting and labeling images for semantic segmentation are disclosed. A particular embodiment includes: receiving image data from an image generating device; performing semantic segmentation or other object detection on the received image data to identify and label objects in the image data and produce semantic label image data; determining the quality of the semantic label image data based on prediction probabilities associated with regions or portions of the image; and identifying a region or portion of the image for manual labeling if an associated prediction probability is below a pre-determined threshold.

Abstract: A system and method for semantic segmentation using hybrid dilated convolution (HDC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and producing multiple convolution layers; grouping the multiple convolution layers into a plurality of groups; applying different dilation rates for different convolution layers in a single group of the plurality of groups; and applying a same dilation rate setting across all groups of the plurality of groups.

Abstract: A system and method for online real-time multi-object tracking is disclosed. A particular embodiment can be configured to: receive image frame data from at least one camera associated with an autonomous vehicle; generate similarity data corresponding to a similarity between object data in a previous image frame compared with object detection results from a current image frame; use the similarity data to generate data association results corresponding to a best matching between the object data in the previous image frame and the object detection results from the current image frame; cause state transitions in finite state machines for each object according to the data association results; and provide as an output object tracking output data corresponding to the states of the finite state machines for each object.

Abstract: A system and method for lateral vehicle detection is disclosed. A particular embodiment can be configured to: receive lateral image data from at least one laterally-facing camera associated with an autonomous vehicle; warp the lateral image data based on a line parallel to a side of the autonomous vehicle; perform object extraction on the warped lateral image data to identify extracted objects in the warped lateral image data; and apply bounding boxes around the extracted objects.

Abstract: A system and method for vehicle wheel detection is disclosed. A particular embodiment can be configured to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; perform a training phase to train one or more classifiers for processing images of the training image data to detect vehicle wheel objects in the images of the training image data; receive operational image data from an image data collection system associated with an autonomous vehicle; and perform an operational phase including applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and produce vehicle wheel object data.

Abstract: A system and method for taillight signal recognition using a convolutional neural network is disclosed. An example embodiment includes: receiving a plurality of image frames from one or more image-generating devices of an autonomous vehicle; using a single-frame taillight illumination status annotation dataset and a single-frame taillight mask dataset to recognize a taillight illumination status of a proximate vehicle identified in an image frame of the plurality of image frames, the single-frame taillight illumination status annotation dataset including one or more taillight illumination status conditions of a right or left vehicle taillight signal, the single-frame taillight mask dataset including annotations to isolate a taillight region of a vehicle; and using a multi-frame taillight illumination status dataset to recognize a taillight illumination status of the proximate vehicle in multiple image frames of the plurality of image frames, the multiple image frames being in temporal succession.

Abstract: A system and method for online real-time multi-object tracking is disclosed. A particular embodiment can be configured to: receive image frame data from at least one camera associated with an autonomous vehicle; generate similarity data corresponding to a similarity between object data in a previous image frame compared with object detection results from a current image frame; use the similarity data to generate data association results corresponding to a best matching between the object data in the previous image frame and the object detection results from the current image frame; cause state transitions in finite state machines for each object according to the data association results; and provide as an output object tracking output data corresponding to the states of the finite state machines for each object.

Abstract: A system and method for lateral vehicle detection is disclosed. A particular embodiment can be configured to: receive lateral image data from at least one laterally-facing camera associated with an autonomous vehicle; warp the lateral image data based on a line parallel to a side of the autonomous vehicle; perform object extraction on the warped lateral image data to identify extracted objects in the warped lateral image data; and apply bounding boxes around the extracted objects.

Abstract: A system and method for semantic segmentation using hybrid dilated convolution (HDC) are disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image; performing a convolution operation on the feature map and producing multiple convolution layers; grouping the multiple convolution layers into a plurality of groups; applying different dilation rates for different convolution layers in a single group of the plurality of groups; and applying a same dilation rate setting across all groups of the plurality of groups.

Abstract: A system and method for determining car to lane distance is provided. In one aspect, the system includes a camera configured to generate an image, a processor, and a computer-readable memory. The processor is configured to receive the image from the camera, generate a wheel segmentation map representative of one or more wheels detected in the image, and generate a lane segmentation map representative of one or more lanes detected in the image. For at least one of the wheels in the wheel segmentation map, the processor is also configured to determine a distance between the wheel and at least one nearby lane in the lane segmentation map. The processor is further configured to determine a distance between a vehicle in the image and the lane based on the distance between the wheel and the lane.

Abstract: A system and method for vehicle wheel detection is disclosed. A particular embodiment can be configured to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; perform a training phase to train one or more classifiers for processing images of the training image data to detect vehicle wheel objects in the images of the training image data; receive operational image data from an image data collection system associated with an autonomous vehicle; and perform an operational phase including applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and produce vehicle wheel object data.