Abstract: Systems and methods for detecting and tracking objects using radar data are disclosed. The methods include receiving measurement data corresponding to an environment of a vehicle from a radar sensor associated with the vehicle, and identifying one or more object tracks of a plurality of object tracks that lie within an extended field of view (FOV) of the radar sensor. The extended FOV may be determined based on an original FOV of the radar sensor. The methods further include performing association of the measurement data with the one or more object tracks to identify an associated object track, and outputting the associated object track and the measurement data to a navigation system of the vehicle.

Abstract: This document discloses system, method, and computer program product embodiments for mitigating the addition of false object information to a track that provides a spatial description of an object, such as a track of radar data or lidar data. The system will analyze two or more frames captured in a relatively small time period and determine whether one or more parameters of an object detected in the frames remain consistent in a specified model. Models that the system may consider include a constant velocity model, a surface model, a constant speed rate model or a constant course rate model. If one or more parameters of the detected object are not consistent over the sequential frames in the specified model, the system may prune the track to exclude one or more of the sequential frames from the track.

Abstract: Systems may include at least one processor configured to determine a predicted value of an unwrap factor using a machine learning model, wherein the machine learning model is a trained machine learning model configured to provide a predicted value of an unwrap factor for dealiasing a measurement of range rate of a target object as an output, dealiase a measurement value of range rate from a radar of an autonomous vehicle (AV) based on the predicted value of the unwrap factor to provide a true value of range rate, and control an operation of the AV in a real-time environment based on the true value of range rate. Methods, computer program products, and autonomous vehicles are also disclosed.

Abstract: Disclosed herein are systems, methods, and computer program products for operating a sensor system. The methods comprise: receiving, by a computing device, a track for an object; classifying, by the computing device, the track as an infant track or a mature track based on a type of sensor detection used to generate the track, a total number of cycles in which the lidar detections were generated, a total number of sensor detections included in the track, an object type associated with the track, an object speed, and/or a distance between the object and the sensor system; using, by the computing device, radar data to modify a speed of the track in response to the track being classified as an infant track.

Abstract: Disclosed herein are systems, methods, and computer program products for controlling a mobile platform. The methods comprise: obtaining loose-fit cuboids overlaid on 3D graphs so as to each encompass lidar data points associated with an object; defining an amodal cuboid based on the loose-fit cuboids; checking whether or not the object is static through a time period; identifying a center for the amodal cuboid based on the checking; and causing operations of the mobile platform to be controlled based on the amodal cuboid having the center which was identified.

Abstract: A screen defect detection method and apparatus and an electronic device are disclosed. The method comprises the following steps: identifying a number of suspected defective pixel points(S110) from a detection image of a target screen; determining a suspected defect region(S120) corresponding to a suspected defective pixel point in the detection image; dividing the suspected defect region into a general region and a core region(S130); and judging whether the target screen has a transparent defect(S140) according to a mean gray value of the suspected defect region, a mean gray value of the general region and a minimum gray value of the core region.

Abstract: Methods, systems, and products for resolving level ambiguity for radar systems of autonomous vehicles may include detecting a plurality of objects with a radar system. Each first detected object may be associated with an existing tracked object based on a first position thereof. First tracked object data based on a first height determined for each first detected object may be stored. The first height may be based on the position of the detected object, the existing tracked object, and a tile map. Second tracked object data based on a second height determined for each second detected object not associated with the existing tracked object(s) may be stored. The second height may be based on a position of each second detected object, a vector map, and the tile map. A command to cause the autonomous vehicle to perform at least one autonomous driving operation may be issued.

Abstract: Systems may include at least one processor configured to determine a predicted value of an unwrap factor using a machine learning model, wherein the machine learning model is a trained machine learning model configured to provide a predicted value of an unwrap factor for dealiasing a measurement of range rate of a target object as an output, dealiase a measurement value of range rate from a radar of an autonomous vehicle (AV) based on the predicted value of the unwrap factor to provide a true value of range rate, and control an operation of the AV in a real-time environment based on the true value of range rate. Methods, computer program products, and autonomous vehicles are also disclosed.

Abstract: This document discloses system, method, and computer program product embodiments for mitigating the addition of false object information to a track that provides a spatial description of an object, such as a track of radar data or lidar data. The system will analyze two or more frames captured in a relatively small time period and determine whether one or more parameters of an object detected in the frames remain consistent in a specified model. Models that the system may consider include a constant velocity model, a surface model, a constant speed rate model or a constant course rate model. If one or more parameters of the detected object are not consistent over the sequential frames in the specified model, the system may prune the track to exclude one or more of the sequential frames from the track.

Abstract: Systems and methods for operating radar systems. The methods comprise, by a processor: receiving point cloud information generated by at least one radar device; generating a radar track initializer using the point cloud information; determining whether the radar track initializer includes false information; generating a radar track for a detected object when a determination is made that the radar track initializer does not include false information; and/or using the radar track to control operations of a vehicle.

Abstract: A target recognition method and device based on a MASK RCNN network model are disclosed. The method comprises: determining a multi-stage network as a basic network; selecting at least one intermediate layer capable of extracting a feature map from the basic network, and inputting respectively a feature map output by the intermediate layer and a feature map output by an end layer of the basic network to corresponding MASK RCNN recognition networks to construct a network model based on the MASK RCNN, wherein the feature map output by the intermediate layer and the feature map output by the end layer have different sizes; training the MASK RCNN recognition networks with a data set and stopping training until a preset training end condition is satisfied; and recognizing the target using the MASK RCNN recognition networks after trained. This solution is very suitable for small target recognition of a flying UAV.

Abstract: Systems and methods for operating radar systems. The methods comprise, by a processor: receiving point cloud information generated by at least one radar device and a spatial description for an object; generating a plurality of point cloud segments by grouping data points of the point cloud information based on the spatial description; arranging the point cloud segments in a temporal order to define a radar tentative track; performing dealiasing operations using the radar tentative track to generate tracker initialization information; and using the tracker initialization information to generate a track for the object.

Abstract: Systems and methods for detecting and tracking objects using radar data are disclosed. The methods include receiving measurement data corresponding to an environment of a vehicle from a radar sensor associated with the vehicle, and identifying one or more object tracks of a plurality of object tracks that lie within an extended field of view (FOV) of the radar sensor. The extended FOV may be determined based on an original FOV of the radar sensor. The methods further include performing association of the measurement data with the one or more object tracks to identify an associated object track, and outputting the associated object track and the measurement data to a navigation system of the vehicle.

Abstract: Methods, systems, and products for resolving level ambiguity for radar systems of autonomous vehicles may include detecting a plurality of objects with a radar system. Each first detected object may be associated with an existing tracked object based on a first position thereof. First tracked object data based on a first height determined for each first detected object may be stored. The first height may be based on the position of the detected object, the existing tracked object, and a tile map. Second tracked object data based on a second height determined for each second detected object not associated with the existing tracked object(s) may be stored. The second height may be based on a position of each second detected object, a vector map, and the tile map. A command to cause the autonomous vehicle to perform at least one autonomous driving operation may be issued.

Abstract: Systems and methods for operating radar systems. The methods comprise, by a processor: receiving point cloud information generated by radar devices; grouping data points of the point cloud to form at least one segment; computing possible true range-rate values for each data point in the at least one segment; identifying a scan window including possible true range-rate values for a largest number of data points; determining whether at least two modulus of the data points associated with the possible true range-rate values included in the identified scan window have moduli values that are different by a certain amount; determining a new range-rate value for each data point of the segment, when a determination is made that at least two modulus of the data points do have moduli values that are different by the certain amount; and modifying the point cloud information in accordance with the new range-rate value.

Abstract: A method and system for detecting signal spoofing are disclosed. According to certain embodiments, the spoofing detection method may include receiving one or more position signals indicative of a first position of a vehicle at a first time. The method may also include receiving one or more reference signals indicative of a second position of the vehicle at the first time. The method may also include determining a difference between the first position and the second position. The method may also include determining that the difference is above a predetermined tolerance. The method may further include notifying the vehicle positioning system.

Abstract: A target recognition method and device based on a MASK RCNN network model are disclosed. The method comprises: determining a multi-stage network as a basic network; selecting at least one intermediate layer capable of extracting a feature map from the basic network, and inputting respectively a feature map output by the intermediate layer and a feature map output by an end layer of the basic network to corresponding MASK RCNN recognition networks to construct a network model based on the MASK RCNN, wherein the feature map output by the intermediate layer and the feature map output by the end layer have different sizes; training the MASK RCNN recognition networks with a data set and stopping training until a preset training end condition is satisfied; and recognizing the target using the MASK RCNN recognition networks after trained. This solution is very suitable for small target recognition of a flying UAV.

Abstract: Systems and methods for operating radar systems. The methods comprise, by a processor: receiving point cloud information generated by at least one radar device and a spatial description for an object; generating a plurality of point cloud segments by grouping data points of the point cloud information based on the spatial description; arranging the point cloud segments in a temporal order to define a radar tentative track; performing dealiasing operations using the radar tentative track to generate tracker initialization information; and using the tracker initialization information to generate a track for the object.

Abstract: Systems and methods for operating radar systems. The methods comprise, by a processor: receiving point cloud information generated by at least one radar device; generating a radar track initializer using the point cloud information; determining whether the radar track initializer includes false information; generating a radar track for a detected object when a determination is made that the radar track initializer does not include false information; and/or using the radar track to control operations of a vehicle.

Abstract: Systems and methods for operating radar systems. The methods comprise, by a processor: receiving point cloud information generated by radar devices; grouping data points of the point cloud to form at least one segment; computing possible true range-rate values for each data point in the at least one segment; identifying a scan window including possible true range-rate values for a largest number of data points; determining whether at least two modulus of the data points associated with the possible true range-rate values included in the identified scan window have moduli values that are different by a certain amount; determining a new range-rate value for each data point of the segment, when a determination is made that at least two modulus of the data points do have moduli values that are different by the certain amount; and modifying the point cloud information in accordance with the new range-rate value.