Abstract: There is provided a method of detecting objects in surroundings of a LiDAR system, the method comprising executing, using a Markov Chain Monte Carlo (MCMC) model, an iterative process for automatically generating a target density parameter for an in-use point cloud, the executing including acquiring a performance score from an object detection model; generating, using the MCMC model, a new candidate density parameter based on the performance score and a previous candidate density parameter; during a subsequent iteration, updating, using the MCMC model, the new candidate density parameter, thereby determining the target density parameter, the updating being based on a new performance score and the new candidate density parameter; generating, using a density adjustment function, a modified in-use point cloud; and generating, using the object detection model, a predicted output indicative of detected objects in the surroundings using the modified in-use point cloud.

Abstract: Devices, systems, methods, and media are disclosed for performing an object detection task comprising: obtaining a semantic segmentation map representing a real-world space, the semantic segmentation map including an array of elements that each represent a respective location in the real-world space and are assigned a respective element classification label; clustering groups of the elements based on the assigned respective element classification labels to identify at least a first cluster of elements that have each been assigned the same respective element classification label; generating, based on a location of the first cluster within the semantic segmentation map, at least one anchor that defines a respective probable object location of a first dynamic object; and generating, based on the semantic segmentation map and the at least one anchor, a respective bounding box and object instance classification label for the first dynamic object.

Abstract: A method and system for localization of an autonomous vehicle in real-time disclosed. A particle filter process is used to generate an estimate of a pose of the autonomous vehicle based on a three-dimensional point cloud, a two-dimensional (2D) feature map and odometry data. A location of the autonomous vehicle in the environment is generated comprising a final pose of the vehicle determined based on the estimate of the pose of the autonomous vehicle and the odometry data, an elevation of the autonomous vehicle generated based on the final pose of the autonomous vehicle and the 2D feature map, and an orientation of the autonomous vehicle generated based on the odometry data.

Abstract: Provided is a method for calibrating a deformation pressure of a large-volume press. The method for calibrating the deformation pressure of the large-volume press includes: depositing a conductive layer onto a surface of a bevel plug to obtain a conductive bevel plug; assembling the conductive bevel plug, a molybdenum pillar, a magnesium oxide tube, a magnesium oxide sample chamber, a magnesium oxide octahedron and a calibration standard material, placing a resulting system in the large-volume press, and subjecting the resulting system to a large-volume press pressure correction experiment.

Abstract: Systems, methods and apparatus for sematic segmentation of 3D point clouds using deep neural networks. The deep neural network generally has two primary subsystems: a multi-branch cascaded subnetwork that includes an encoder and a decoder, and is configured to receive a sparse 3D point cloud, and capture and fuse spatial feature information in the sparse 3D point cloud at multiple scales and multi hierarchical levels; and a spatial feature transformer subnetwork that is configured to transform the cascaded features generated by the multi-branch cascaded subnetwork and fuse these scaled features using a shared decoder attention framework to assist in the prediction of sematic classes for the sparse 3D point cloud.

Abstract: A controllable rapid pressure loading technology for a large volume press is provided. A regular octahedra, plugs, diamond pistons, and a standard are included. The regular octahedra is provided with a cavity with openings at two ends of the cavity. The standard is placed in the cavity. The openings at two ends of the cavity are respectively blocked by the conductive plugs. The diamond piston is arranged between the standard and the plug. The diamond pistons arranged between the standard and the plug has high hardness and has the pressure transmission efficiency superior to that of a common ceramic plug, improving compression efficiency in sample cavity. A loading method of pre-charging a pressure to a pressure loading device first and then rapidly releasing to a pressure loading mold is used to match an improved pressure transmission component, which shortens the pressure loading time of the sample cavity.

Abstract: The present disclosure relates to a method for high pressure regulation and control of photoelectric detection based on BiOBr, and relates to the technical field of photoelectric detection. An exemplary method includes inserting an insulation layer into a pressure chamber of a diamond anvil cell and adding BiOBr, putting a pressure-calibrating substance on a culet of the diamond anvil cell; pressurizing the pressure chamber by rotating a press bolt on the diamond anvil cell; and conducting photoelectric detection using the pressurized BiOBr, where two platinum sheets are disposed on the BiOBr as an electrode. The present disclosure enhances the photo-response speed and photo-responsivity of photoelectric detection.

Abstract: A gas diaphragm driven rapid supercharging device based on a diamond anvil cell is provided which includes a gas diaphragm, a diamond anvil cell press, a hard steel shell and a gas release component. The gas diaphragm and the diamond anvil cell press are positioned inside the hard steel shell, the gas diaphragm is positioned below the diamond anvil cell press, a first opening is formed in a top of the hard steel shell, and a second opening is formed in a bottom of the hard steel shell. The gas release component passes through the second opening of the hard steel shell to be connected with the gas diaphragm through a gas path, and the gas release component is configured for releasing gas at a first inflation speed in a standard pressure experiment, and inflating the gas diaphragm at different driving pressures to obtain a pressure calibration curve.

Abstract: Methods and systems for performing semantic scene completion of sparse 3D data are described. A frame of sparse 3D data is preprocessed into a sparse 3D tensor and a sparse 2D tensor. A partially completed 3D tensor is generated from the sparse 3D tensor using a 3D prediction network, and a semantically completed 2D tensor is generated from the sparse 2D tensor using a 2D prediction network. The partially completed 3D tensor is completed to obtain a semantically completed 3D tensor by assigning a given class label, which has been assigned to a given pixel in the semantically completed 2D tensor, to a voxel at a corresponding x-y coordinate in the partially completed 3D tensor.

Abstract: The invention relates to a millimeter-sized bulk spa amorphous carbon material and a method of preparing the same, and the method comprises a step of performing a high-temperature and high-pressure (HTHP) treatment on C60 powder at a temperature of 450-1100° C., preferably 700-1000° C., more preferably 900-1000° C., and most preferably 1000° C., and a pressure of 20-37 GPa, preferably 20-30 GPa, and most preferably 27 GPa, so as to obtain the millimeter-sized bulk sp3 amorphous carbon material. The sp3 carbon content in the amorphous carbon material is adjustable by changing the temperature and pressure conditions, so that the sp3 content is greater than 80%, and the sp3 content of high-quality samples is close to 100%. The optical band gap and thermal conductivity of the series of amorphous carbon materials can be effectively adjusted. The obtained series of amorphous carbon materials have ultra-high hardnesses, high thermal conductivities, adjustable band gaps (1.90-2.

Abstract: System and method for semantic segmentation of point clouds. The method may include: generating, via a first neural network, a birds-eye-view (BEV) image of the environment from the aggregated point cloud; generating, via a second neural network, a labelled BEV image from the BEV image, wherein each pixel in the labelled BEV image is associated with a class label from a set of class labels; generating a BEV feature map; and generating, via a third neural network, the road surface segmentation map in the form of a refined labelled BEV image based on the labelled BEV image by smoothing the labelled BEV image using the BEV feature map, wherein each pixel in the refined labelled BEV image is associated with a class label from the set of class labels.

Abstract: Method and system for processing a point cloud frame representing a real-world scene that includes one or more objects, including assigning data-element-level classification labels to data elements that each respectively represent one or more points included in the point cloud frame, estimating an approximate position of a first object instance represented in the point cloud frame, assigning an object-instance-level classification label to the first object instance, selecting, for the first object instance, a subgroup of the data elements based on the approximate position, selecting from the subgroup a first cluster of data elements that have assigned data-element-level classification labels that match the object-instance-level classification label assigned to the first object instance, and outputting an object instance list that indicates, for the first object instance, the first cluster of data elements, and the object-instance-level classification label assigned to the first object instance.

Abstract: A system and method for processing a 3D point cloud to generate a segmented point cloud in real time are disclosed, the method includes: receiving a sparse 3D point cloud captured by a detection and ranging sensor mounted to a vehicle, the 3D point cloud comprising a plurality of data points, each data point in the 3D point cloud having a set of coordinates in a coordinate system of the detection and ranging sensor; generating, from the 3D point cloud, a range map comprising a plurality of elements, each of the plurality of data points of the 3D point cloud occupying a respective element of the plurality of elements; labelling the data point in each respective element of the range map as one of a pole-like data point or a vertical-plane-like data point; and generating the segmented point cloud including one or more of the labeled data points.

Abstract: Devices, systems, methods, and media are disclosed for performing an object detection task comprising: obtaining a semantic segmentation map representing a real-world space, the semantic segmentation map including an array of elements that each represent a respective location in the real-world space and are assigned a respective element classification label; clustering groups of the elements based on the assigned respective element classification labels to identify at least a first cluster of elements that have each been assigned the same respective element classification label; generating, based on a location of the first cluster within the semantic segmentation map, at least one anchor that defines a respective probable object location of a first dynamic object; and generating, based on the semantic segmentation map and the at least one anchor, a respective bounding box and object instance classification label for the first dynamic object.

Abstract: In methods and systems for graph-based panoptic segmentation of point clouds, points of a point cloud are received with a semantic label from a first category. Further, a plurality of unified cluster feature vectors from a second category are received, each being extracted from a cluster of points in the point cloud. Nodes of a constructed graph represent the unified feature vectors, and edges indicate the relationship between pairs of nodes. The edges are represented as an adjacency matrix indicating the existence or absence of an edge between pairs of nodes. A graph convolutional neural network uses the graph to predict an instance label for each node or an attribute for each edge, wherein the attribute of each edge is used for assigning the instance label to each node.

Abstract: A system and method for 3D object detection using multi-resolution features recovery using panoptic segmentation information. Panoptic segmentation predictions from a panoptic segmentation network and intermediate feature maps from one or more early layers of an object detection network are received. Feature vectors are retrieved from the intermediate feature maps using the panoptic segmentation predictions. The retrieved feature vectors are combined with feature maps from one or more late layers of the object detection network for generating object detection predictions.

Abstract: Devices, systems, methods, and media are disclosed for domain adaptation using data densification. Example embodiments described herein receives LiDAR 3D point clouds from a source-domain and introduces interpolated 3D points inferred by a trained deep learning neural network to output a denser version of the input 3D point cloud with increased resolution. The trained domain adaptation network reconstructs the source-domain 3D point cloud data, generates translation vectors to compute interpolated 3D point cloud data and merges the reconstructed 3D point cloud data and the interpolated 3D point cloud data to output a densified 3D point cloud resembling data 3D point clouds captured generated by the target LiDAR sensor from the source-domain.

Abstract: Provided are a solvent-free two-component type adhesive capable of guaranteeing a practical packaging property, with an excellent curing property and significantly shortening aging time, a laminated film using the same, and a polyol composition for an adhesive. An adhesive, characterized in comprising a polyisocyanate composition (X) containing a polyisocyanate (A), and a polyol composition (Y) containing a polyol (C) and a tertiary amine compound (B) having multiple hydroxyl groups, as necessary components.

Abstract: System and method for semantic segmentation of point clouds. The method may include: generating, via a first neural network, a birds-eye-view (BEV) image of the environment from the aggregated point cloud; generating, via a second neural network, a labelled BEV image from the BEV image, wherein each pixel in the labelled BEV image is associated with a class label from a set of class labels; generating a BEV feature map; and generating, via a third neural network, the road surface segmentation map in the form of a refined labelled BEV image based on the labelled BEV image by smoothing the labelled BEV image using the BEV feature map, wherein each pixel in the refined labelled BEV image is associated with a class label from the set of class labels.

Abstract: Methods and systems for deep neural networks using dynamically selected feature-relevant points from a point cloud are described. A plurality of multidimensional feature vectors arranged in a point-feature matrix are received. Each row of the point-feature matrix corresponds to a respective one of the multidimensional feature vectors, and each column of the point-feature matrix corresponds to a respective feature. Each multidimensional feature vector represents a respective unordered point from a point cloud and each multidimensional feature vector includes a respective plurality of feature-correlated values, each feature-correlated value represents a correlation extent of the respective feature. A reduced-max matrix having a selected plurality of feature-relevant vectors is generated.