The present invention provides a loop closure detection method and system, a multi-sensor fusion SLAM system, a robot, and a medium. Said system runs on a mobile robot, and comprises a similarity detection unit, a visual pose solving unit, and a laser pose solving unit. According to the loop closure detection system, the multi-sensor fusion SLAM system and the robot provided in the present invention, the speed and accuracy of loop closure detection in cases of a change in a viewing angle of the robot, a change in the environmental brightness, a weak texture, etc. can be significantly improved.

The present invention provides a loop closure detection method and system, a multi-sensor fusion SLAM system, a robot, and a medium. Said system runs on a mobile robot, and comprises a similarity detection unit, a visual pose solving unit, and a laser pose solving unit. According to the loop closure detection system, the multi-sensor fusion SLAM system and the robot provided in the present invention, the speed and accuracy of loop closure detection in cases of a change in a viewing angle of the robot, a change in the environmental brightness, a weak texture, etc. can be significantly improved.

A high-definition map creation method includes: obtaining point cloud data collected with respect to a target region, the point cloud data including K frames of point clouds and an initial pose of each frame of point cloud, K being an integer greater than 1; associating the K frames of point clouds with each other in accordance with the initial pose to obtain a first point cloud relation graph of the K frames of point clouds; performing point cloud registration on the K frames of point clouds in accordance with the first point cloud relation graph and the initial pose to obtain a target relative pose of each frame of point cloud in the K frames of point clouds; and splicing the K frames of point clouds in accordance with the target relative pose to obtain a point cloud map of the target region.

The system includes a metric map creation unit configured to create a metric map using first image data received from a 3D sensor, an image processing unit configured to recognize an object by creating and classifying a point cloud using second image data received from an RGB camera; a probability-based map production unit configured to create an object location map and a spatial semantic map in a probabilistic expression method using a processing result of the image processing unit, a question creation unit configured to extract a portion of high uncertainty about an object class from a produced map on the basis of entropy and ask a user about the portion, and a map update unit configured to receive a response from the user and update a probability distribution for spatial information according to a change in probability distribution for classification of the object.

The system includes a metric map creation unit configured to create a metric map using first image data received from a 3D sensor, an image processing unit configured to recognize an object by creating and classifying a point cloud using second image data received from an RGB camera; a probability-based map production unit configured to create an object location map and a spatial semantic map in a probabilistic expression method using a processing result of the image processing unit, a question creation unit configured to extract a portion of high uncertainty about an object class from a produced map on the basis of entropy and ask a user about the portion, and a map update unit configured to receive a response from the user and update a probability distribution for spatial information according to a change in probability distribution for classification of the object.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a surfel map to generate a prediction for a state of an environment. One of the methods includes obtaining surfel data comprising a plurality of surfels, wherein each surfel corresponds to a respective different location in an environment, and each surfel has associated data that comprises an uncertainty measure; obtaining sensor data for one or more locations in the environment, the sensor data having been captured by one or more sensors of a first vehicle; determining one or more particular surfels corresponding to respective locations of the obtained sensor data; and combining the surfel data and the sensor data to generate a respective object prediction for each of the one or more locations of the obtained sensor data.

A network for category-level 6D pose and size estimation, including a 3D-OCR module for 3D Orientation-Consistent Representation, a GeoReS module for Geometry-constrained Reflection Symmetry, and a MPDE module for Mirror-Paired Dimensional Estimation; wherein the 3D-OCR module and the GeoReS module are incorporated in parallel; the 3D-OCR module receives a canonical template shape including canonical category-specific keypoints; the GeoReS module receives an original input depth observation including pre-processed predicted category labels and potential masks of the target instances; the MPDE module receives the output from the GeoReS module as well as the original input depth observation; and the network outputs the estimation results based on the output of the MPDE module, the output of the 3D-OCR module, as well as the canonical template shape. Also provided are corresponding systems and methods.

Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.

The present invention provides an auxiliary berthing method and system for a vessel. In the berthing method, by a solar blind ultraviolet imaging method, a position and an attitude of a vessel relative to a shoreline of a port berth during berthing are calculated by at least two solar blind ultraviolet imaging modules according to light signals received by a solar blind ultraviolet light source array arranged in advance on the shore. Further, when more than three solar blind ultraviolet imaging modules are used, in the method and device of the present invention, a normalized correlation algorithm and a data fusion algorithm are used to improve the accuracy of the position and attitude data of the vessel.

Processes, systems, and devices for occlusion detection for video-based object tracking (VBOT) are described herein. Embodiments process video frames to compute histogram data and depth level data for the object to detect a subset of video frames for occlusion events and generate output data that identifies each video frame of the subset of video frames for the occlusion events. Threshold measurement values are used to attempt to reduce or eliminate false positives to increase processing efficiency.