Abstract: The present disclosure is related to systems and methods for processing X-ray images. A method for processing an X-ray image may include obtaining an X-ray image; and determining a metal image based on the X-ray image by using a trained metal detection model. The metal image includes information of a metal object in the X-ray image.

Abstract: Apparatuses, systems, and techniques to perform non-maximum suppression (NMS) in parallel to remove redundant bounding boxes. In at least one embodiment, two or more parallel circuits to perform two or more portions of a NMS algorithm in parallel to remove one or more redundant bounding boxes corresponding to one or more objects within one or more digital images.

Abstract: A method and an apparatus optimizes scan data obtained by sensors on vehicle, and corrects trajectory for a vehicle/robot based on the optimized scan data.

Abstract: A method for segmentation of a point cloud includes receiving a first frame of point cloud from a sensor; segmenting the first frame of point cloud to obtain a first set of point clusters representing a segmentation result for the first frame of point cloud; receiving a second frame of point cloud from the sensor; mapping the first set of point clusters to the second frame of point cloud; determining points within the second frame of point cloud which do not belong to the mapped first set of point clusters; segmenting the points within the second frame of point cloud which do not belong to the mapped first set of point clusters to obtain a second set of point clusters; and generating a segmentation result for the second frame of point cloud by combining the first set of point clusters and the second set of point clusters.

Abstract: Apparatuses, systems, and techniques to identify bounding boxes of objects with in an image. In at least one embodiment, bounding boxes are determined in an image using an intersection over union threshold that is based at least in part on a size of an object.

Abstract: A method for determining driving strategy of a vehicle includes obtaining localization information of the vehicle, a driving route of the vehicle, and a current driving velocity of the vehicle. The method further includes detecting and interpreting a current status of a traffic light. The method further includes recognizing a duration of the current status of the traffic light. The method further includes detecting a relevant stop line. The method further includes obtaining a distance between the stop line and the vehicle. The method further includes determining whether to change the current driving velocity according to the current status of the traffic light, the duration of the current status of the traffic light, the distance between the traffic stop line and the vehicle, and the current driving velocity. A data processing device for determining driving strategy of a vehicle is also provided.

Abstract: A method and apparatus for selecting a map from a plurality of maps having different resolutions for a moving object includes dynamically selecting an appropriate map from maps having different levels of details according to environment information, such that a minimum amount of required map is loaded, thereby effectively improving the data processing efficiency of vehicles.

Abstract: Apparatuses, systems, and techniques to perform non-maximum suppression (NMS) in parallel to remove redundant bounding boxes. In at least one embodiment, two or more parallel circuits to perform two or more portions of a NMS algorithm in parallel to remove one or more redundant bounding boxes corresponding to one or more objects within one or more digital images.

Abstract: Apparatuses, systems, and techniques to generate bounding box information. In at least one embodiment, for example, bounding box information is generated based, at least in part, on a plurality of candidate bounding box information.

Abstract: A computer-implemented method for representing environmental elements includes receiving scan data comprising at least a point cloud representing at least an environmental element from a sensor, segmenting the point cloud into point clusters, and partitioning the point clusters into hierarchical grids. The method also includes establishing a Gaussian distribution for points in each cell of each of the hierarchical grids, and constructing a Gaussian Mixture Model based on the Gaussian distribution for representing the environmental element.

Abstract: A method for segmentation of a point cloud, includes: receiving a first frame of point cloud from a sensor; segmenting the first frame of point cloud using a segmentation algorithm to obtain a first set of point clusters representing a segmentation result for the first frame of point cloud; receiving a second frame of point cloud from the sensor; mapping the first set of point clusters to the second frame of point cloud; determining points within the second frame of point cloud which do not belong to the mapped first set of point clusters; segmenting the points within the second frame of point cloud which do not belong to the mapped first set of point clusters using the segmentation algorithm to obtain a second set of point clusters; and generating a segmentation result for the second frame of point cloud by combining the first set of point clusters and the second set of point clusters.

Abstract: A method for configuring a sensor, which is adapted to be installed on a moving object, includes obtaining localization information of the sensor from a localization device, obtaining characteristic information and localization information of at least one element from a digital map, and choosing one or more elements of the at least one element in the digital map. The method also includes configuring the sensor according to the characteristic information and/or the localization information of the one or more chosen elements.

Abstract: A method for determining driving strategy of a vehicle includes obtaining localization information of the vehicle, a driving route of the vehicle, and a current driving velocity of the vehicle. The method further includes detecting and interpreting a current status of a traffic light. The method further includes recognizing a duration of the current status of the traffic light. The method further includes detecting a relevant stop line. The method further includes obtaining a distance between the stop line and the vehicle. The method further includes determining whether to change the current driving velocity according to the current status of the traffic light, the duration of the current status of the traffic light, the distance between the traffic stop line and the vehicle, and the current driving velocity. A data processing device for determining driving strategy of a vehicle is also provided.

Abstract: A method and an apparatus for uncertainty modeling of a point cloud and a non-transient storage medium are provided. The method finds the neighboring points for each point; fits a local quadratic surface for each point; and generates a Gaussian Model (GM) for representing the uncertainty modeling of the local surface at each point. The GM is constructed in a piece-wise manner on the underlying surface of the point cloud, which will accurately model the surface uncertainty.

Abstract: A computer-implemented method for constructing an environment model includes generating a first Signatured Gaussian Mixture (SGM) model corresponding to a first part of the environment based on a first sensor data, receiving a second SGM model corresponding to a second part of the environment, and constructing a third SGM model comprising the first SGM model and the second SGM model.

Abstract: A method and an apparatus are provided for representing a map element and for locating a vehicle/robot based thereupon. The method for representing a map element includes: generating a Gaussian Mixture Model for the map element; generating a signature for identifying the map element, wherein the signature includes properties of the map element; and generating a Signatured Gaussian Mixture Model for representing the map element, wherein the Signatured Gaussian Mixture Model includes the Gaussian Mixture Model and the signature.

Abstract: A method and apparatus for selecting a map from a plurality of maps having different resolutions for a moving object includes dynamically selecting an appropriate map from maps having different levels of details according to environment information, such that a minimum amount of required map is loaded, thereby effectively improving the data processing efficiency of vehicles.

Abstract: A computer-implemented method for representing environmental elements includes receiving scan data comprising at least a point cloud representing at least an environmental element from a sensor, segmenting the point cloud into point clusters, and partitioning the point clusters into hierarchical grids. The method also includes establishing a Gaussian distribution for points in each cell of each of the hierarchical grids, and constructing a Gaussian Mixture Model based on the Gaussian distribution for representing the environmental element.

Abstract: A method and an apparatus optimizes scan data obtained by sensors on vehicle, and corrects trajectory for a vehicle/robot based on the optimized scan data.

Abstract: A method for localization of a moving object includes obtaining a digital map comprising road feature information, receiving position change information of the moving object, and obtaining trace feature information of the moving object by processing the position change information of the moving object. The method further includes determining a localization of the moving object according to similarity between the trace feature information of the moving object and the road feature information.