Provided is a method and apparatus for identifying a vehicle cross-line. The method may include: determining, in each road condition image of a plurality of road condition images, position information of a target lane line and position information of a target vehicle; determining, based on the position information of the target lane line and the position information of the target vehicle, a relative positional relationship between the target vehicle and the target lane line corresponding to the each road condition image; and determining that the target vehicle crosses the line, if the relative positional relationships corresponding to the plurality of road condition images meet a preset condition.

A system and method for completing joint risk localization and reasoning in driving scenarios that include receiving a plurality of images associated with a driving scene of an ego agent. The system and method also include inputting image data associated with the plurality of images to an encoder and inputting concatenated features to a decoder that identifies at least one of: an important traffic agent and an important traffic infrastructure that is located within the driving scene of the ego agent. The system and method further include controlling at least one system of the ego agent to provide a response to account for the at least one of: the important traffic agent and the important traffic infrastructure that is located within the driving scene of the ego agent.

Systems and methods for obstacle detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having obstacles. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

Unmanned aerial vehicles (UAVs) may facilitate insurance-related tasks. UAVs may actively be dispatched to an area surrounding a property, and collect data related to property. A location for an inspection of a property to be conducted by a UAV may be received, and one or more images depicting a view of the location may be displayed via a user interface. Additionally, a geofence boundary may be determined based on an area corresponding to a property boundary, where the geofence boundary represents a geospatial boundary in which to limit flight of the UAV. Furthermore, a navigation route may be determined which corresponds to the geofence boundary for inspection of the property by the UAV, the navigation route having waypoints, each waypoint indicating a location for the UAV to obtain drone data. The UAV may be directed around the property using the determined navigation route.

A 3D bounding box reconstruction method includes obtaining masks corresponding to a target object in images, obtaining a trajectory direction of the target object according to the masks, generating a target contour according to one of the masks, transforming the target contour into a transformed contour using a transformation matrix, obtaining a first bounding box according to the transformed contour and the trajectory direction, transforming the first bounding box into a second bounding box corresponding to the target contour using the transformation matrix, obtaining first reference points according to the target contour and the second bounding box, transforming the first reference points into second reference points using the transformation matrix, obtaining a third bounding box using the second reference points, transforming the third bounding box into a fourth bounding box using the transformation matrix, and obtaining a 3D bounding box using the second bounding box and the fourth bounding box.

Various embodiments for systems and methods of evaluating perception systems for autonomous vehicles using a quality temporal logic are disclosed herein.

Techniques are described for estimating intentions of pedestrians and other road users in vicinity of a vehicle. In certain embodiments, the techniques comprise obtaining, by a computer system of a vehicle equipped with one or more sensors, a sequence of video frames corresponding to a scene external to the vehicle, detecting one or more vulnerable road users (VRUs) in the sequence of video frames, wherein the detecting comprises estimating pose of each of the detected one or more VRUs. The techniques further include generating a segmentation map of the scene using one or more of the video frames; estimating one or more intention probabilities using estimated pose of the one or more VRUs and the segmentation map, each intention probability corresponding to one of the detected one or more VRUs, and adjusting one or more automated driving actions based on the estimated one or more intention probabilities.

Systems and methods involve detecting objects using a radar system of a vehicle. Tracks of the objects are initiated in a track database. The tracks store data, respectively, for the objects and are updated based on additional detections of the objects. The tracks of the objects are initially unclassified tracks. Two tracks corresponding to two of the objects are selected as a candidate pair. Criteria are applied to the candidate pair to determine whether one track is of a ghost object and another track is of a true object corresponding with the ghost object. The ghost object represents detection of the true object in an incorrect location. The candidate pair is classified as tracks of a true object and ghost object pair based on determining that the one track is of the ghost object and the other track is of the true object corresponding with the ghost object.

A method for assessing possible trajectories of road users in a traffic environment includes capturing the traffic environment with static and dynamic features, identifying at least one traffic user, determining at least one possible trajectory for at least one road user in the traffic environment, and assessing the at least one determined possible trajectory for the at least one road user with an adapted/trained recommendation service and the captured traffic environment.

Methods are disclosed for providing Lawful Intercept (LI) for vehicles. In one embodiment the method includes providing, to at least one autonomous vehicle, at least one vehicle number of a vehicle being tracked and using a camera of the at least one autonomous vehicle, determining a vehicle number of the a vehicle the autonomous vehicle has encountered. The method further includes comparing the vehicle number of the vehicle the autonomous vehicle encountered to the vehicle number of the vehicle being tracked, and when the vehicle number of the vehicle the autonomous vehicle encountered matches the vehicle number of the vehicle being tracked, sending a message to law enforcement that the vehicle being tracked has been encountered.