Abstract: Described herein are systems and methods for determining if a vehicle is parked. In one example, a system includes a processor, a sensor system, and a memory. Both the sensor system and the memory are in communication with the processor. The memory includes a parking determination module having instructions that, when executed by the processor, cause the processor to determine, using a random forest model, when the vehicle is parked based on vehicle estimated features, vehicle learned features, and vehicle taillight features of the vehicle that are based on sensor data from the sensor system.

Abstract: A method for 3D object modeling includes linking 2D semantic keypoints of an object within a video stream into a 2D structured object geometry. The method includes inputting, to a neural network, the object to generate a 2D NOCS image and a shape vector, the shape vector being mapped to a continuously traversable coordinate shape. The method includes applying a differentiable shape renderer to the SDF shape and the 2D NOCS image to render a shape of the object corresponding to a 3D object model in the continuously traversable coordinate shape space. The method includes lifting the linked, 2D semantic keypoints of the 2D structured object geometry to a 3D structured object geometry. The method includes geometrically and projectively aligning the 3D object model, the 3D structured object geometry, and the rendered shape to form a rendered object. The method includes generating 3D bounding boxes from the rendered object.

Abstract: Systems and methods for detecting and matching keypoints between different views of a scene are disclosed herein. One embodiment acquires first and second images; subdivides the first and second images into first and second pluralities of cells, respectively; processes both pluralities of cells using a neural keypoint detection network to identify a first keypoint for a particular cell in the first plurality of cells and a second keypoint for a particular cell in the second plurality of cells, at least one of the first and second keypoints lying in a cell other than the particular cell in the first or second plurality of cells for which it was identified; and classifies the first keypoint and the second keypoint as a matching keypoint pair based, at least in part, on a comparison between a first descriptor associated with the first keypoint and a second descriptor associated with the second keypoint.

Abstract: Systems, methods, computer-readable media, techniques, and methodologies are disclosed for performing end-to-end, learning-based keypoint detection and association. A scene graph of a signalized intersection is constructed from an input image of the intersection. The scene graph includes detected keypoints and linkages identified between the keypoints. The scene graph can be used along with a vehicle's localization information to identify which keypoint that represents a traffic signal is associated with the vehicle's current travel lane. An appropriate vehicle action may then be determined based on a transition state of the traffic signal keypoint and trajectory information for the vehicle. A control signal indicative of this vehicle action may then be output to cause an autonomous vehicle, for example, to implement the appropriate vehicle action.

Abstract: Systems and methods for self-supervised learning for visual odometry using camera images captured on a camera, may include: using a key point network to learn a keypoint matrix for a target image and a context image captured by the camera; using the learned descriptors to estimate correspondences between the target image and the context image; based on the keypoint correspondences, lifting a set of 2D keypoints to 3D, using a learned neural camera model; estimating a transformation between the target image and the context image using 3D-2D keypoint correspondences; and projecting the 3D keypoints into the context image using the learned neural camera model.

Abstract: Systems and methods are provided for implementing soft model assertions (SMA) system and techniques designed to monitor and improve Machine Learning (ML) model quality by to detecting errors within the one or more ML models. SMA techniques and systems are distinctly designed to leverage: 1) a user's ability to specify features over data; and 2) large, existing datasets of organizations, in a manner that can improve the accuracy and quality of predicting potential errors in Machine Learning (ML) models. A SMA system can include a controller device receiving predictions generated based on the ML models and output from the SMA system. The controller performs autonomous operations of the system in response to determining that the one or more detected errors within the one or more ML models yield a high certainty of errors in the predictions. The SMA system also includes a domain specific language and a severity score module.

Abstract: A method for 3D object detection is described. The method includes detecting semantic keypoints from monocular images of a video stream capturing a 3D object. The method also includes inferring a 3D bounding box of the 3D object corresponding to the detected semantic vehicle keypoints. The method further includes scoring the inferred 3D bounding box of the 3D object. The method also includes detecting the 3D object according to a final 3D bounding box generated based on the scoring of the inferred 3D bounding box.

Abstract: Datasets for autonomous driving systems and multi-modal scenes may be automatically labeled using previously trained models as priors to mitigate the limitations of conventional manual data labeling. Properly versioned models, including model weights and knowledge of the dataset on which the model was previously trained, may be used to run an inference operation on unlabeled data, thus automatically labeling the dataset. The newly labeled dataset may then be used to train new models, including sparse data sets, in a semi-supervised or weakly-supervised fashion.

Abstract: Acquiring labeled data can be a significant bottleneck in the development of machine learning models that are accurate and efficient enough to enable safety-critical applications, such as automated driving. The process of labeling of driving logs can be automated. Unlabeled real-world driving logs, which include data captured by one or more vehicle sensors, can be automatically labeled to generate one or more labeled real-world driving logs. The automatic labeling can include analysis-by-synthesis on the unlabeled real-world driving logs to generate simulated driving logs, which can include reconstructed driving scenes or portions thereof. The automatic labeling can further include simulation-to-real automatic labeling on the simulated driving logs and the unlabeled real-world driving logs to generate one or more labeled real-world driving logs. The automatically labeled real-world driving logs can be stored in one or more data stores for subsequent training, validation, evaluation, and/or model management.

Abstract: A method for 3D object modeling includes linking 2D semantic keypoints of an object within a video stream into a 2D structured object geometry. The method includes inputting, to a neural network, the object to generate a 2D NOCS image and a shape vector, the shape vector being mapped to a continuously traversable coordinate shape. The method includes applying a differentiable shape renderer to the SDF shape and the 2D NOCS image to render a shape of the object corresponding to a 3D object model in the continuously traversable coordinate shape space. The method includes lifting the linked, 2D semantic keypoints of the 2D structured object geometry to a 3D structured object geometry. The method includes geometrically and projectively aligning the 3D object model, the 3D structured object geometry, and the rendered shape to form a rendered object. The method includes generating 3D bounding boxes from the rendered object.

Abstract: A method for 3D object tracking is described. The method includes inferring first 2D semantic keypoints of a 3D object within a sparsely annotated video stream. The method also includes matching the first 2D semantic keypoints of a current frame with second 2D semantic keypoints in a next frame of the sparsely annotated video stream using embedded descriptors within the current frame and the next frame. The method further includes warping the first 2D semantic keypoints to the second 2D semantic keypoints to form warped 2D semantic keypoints in the next frame. The method also includes labeling a 3D bounding box in the next frame according to the warped 2D semantic keypoints in the next frame.

Abstract: In one embodiment, a vehicle light classification system captures a sequence of images of a scene that includes a front/rear view of a vehicle with front/rear-side lights, determines semantic keypoints, in the images and associated with the front/rear-side lights, based on inputting the images into a first neural network, obtains multiple difference images that are each a difference between successive images from among the sequence of images, the successive images being aligned based on their respective semantic keypoints, and determines a classification of the front/rear-side lights based at least in part on the difference images by inputting the difference images into a second neural network.

Abstract: System, methods, and other embodiments described herein relate to semi-supervised training of a depth model using a neural camera model that is independent of a camera type. In one embodiment, a method includes acquiring training data including at least a pair of training images and depth data associated with the training images. The method includes training the depth model using the training data to generate a self-supervised loss from the pair of training images and a supervised loss from the depth data. Training the depth model includes learning the camera type by generating, using a ray surface model, a ray surface that approximates an image character of the training images as produced by a camera having the camera type. The method includes providing the depth model to infer depths from monocular images in a device.

Abstract: Systems, methods, computer-readable media, techniques, and methodologies are disclosed for performing end-to-end, learning-based keypoint detection and association. A scene graph of a signalized intersection is constructed from an input image of the intersection. The scene graph includes detected keypoints and linkages identified between the keypoints. The scene graph can be used along with a vehicle's localization information to identify which keypoint that represents a traffic signal is associated with the vehicle's current travel lane. An appropriate vehicle action may then be determined based on a transition state of the traffic signal keypoint and trajectory information for the vehicle. A control signal indicative of this vehicle action may then be output to cause an autonomous vehicle, for example, to implement the appropriate vehicle action.

Abstract: A method for semantic keypoint detection is described. The method includes linking, using a keypoint graph neural network (KGNN), semantic keypoints of an object within a first image of a video stream into a 2D graph structure corresponding to a category of the object. The method also includes embedding descriptors within the semantic keypoints of the 2D graph structure corresponding to the category of the object. The method further includes tracking the object within subsequent images of the video stream using the embedded descriptors within the semantic keypoints of the 2D graph structure corresponding to the category of the object.

Abstract: Systems and methods for self-supervised learning for visual odometry using camera images, may include: estimating correspondences between keypoints of a target camera image and keypoints of a context camera image; based on the keypoint correspondences, lifting a set of 2D keypoints to 3D, using a neural camera model; and projecting the 3D keypoints into the context camera image using the neural camera model. Some embodiments may use the neural camera model to achieve the lifting and projecting of keypoints without a known or calibrated camera model.

Abstract: A method for 3D object modeling includes linking 2D semantic keypoints of an object within a video stream into a 2D structured object geometry. The method includes inputting, to a neural network, the object to generate a 2D NOCS image and a shape vector, the shape vector being mapped to a continuously traversable coordinate shape. The method includes applying a differentiable shape renderer to the SDF shape and the 2D NOCS image to render a shape of the object corresponding to a 3D object model in the continuously traversable coordinate shape space. The method includes lifting the linked, 2D semantic keypoints of the 2D structured object geometry to a 3D structured object geometry. The method includes geometrically and projectively aligning the 3D object model, the 3D structured object geometry, and the rendered shape to form a rendered object. The method includes generating 3D bounding boxes from the rendered object.

Abstract: System, methods, and other embodiments described herein relate to semi-supervised training of a depth model for monocular depth estimation. In one embodiment, a method includes training the depth model according to a first stage that is self-supervised and that includes using first training data that comprises pairs of training images. Respective ones of the pairs including separate frames depicting a scene of a monocular video. The method includes training the depth model according to a second stage that is weakly supervised and that includes using second training data to produce depth maps according to the depth model. The second training data comprising individual images with corresponding sparse depth data. The second training data providing for updating the depth model according to second stage loss values that are based, at least in part, on the depth maps and the depth data.

Abstract: In one embodiment, a traffic light classification system for a vehicle, includes an image capture device to capture an image of a scene that includes a traffic light with multiple light signals, a processor, and a memory communicably coupled to the processor and storing a first neural network module including instructions that when executed by the processor cause the processor to determine, based on inputting the image into a neural network, a semantic keypoint for each light signal in the traffic light, and determine, based on each semantic keypoint, a classification state of each light signal.

Abstract: A method for monocular depth/pose estimation in a camera agnostic network is described. The method includes projecting lifted 3D points onto an image plane according to a predicted ray vector based on a monocular depth model, a monocular pose model, and a camera center of a camera agnostic network. The method also includes predicting a warped target image from a predicted depth map of the monocular depth model, a ray surface of the predicted ray vector, and a projection of the lifted 3D points according to the camera agnostic network.