Huawei Technologies Co., Limited

Yuan Ren

Bingbing Liu

Ran Cheng

Christopher George-R Agia

Ehsan Taghavi

Keyvan Golestan Irani

Xinhai Li

Haiwei Dong

A computer-implemented method, a computing system, and a non-transitory machine-readable medium for semantic segmentation of a point cloud frame are provided. Point cloud frames including a target point cloud frame are received. For each sequence of a sliding set of sequences of point cloud frames, the sequence including the target point cloud frame, each point cloud frame in the sequence of point cloud frames is semantically segmented to apply semantic labels to points. A most prevalent semantic label is determined for each point in the target point cloud frame across the sliding set of sequences of point cloud frames.

Systems, methods, and media for semantic segmentation of a point cloud frame

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.

Method and system for localization of an autonomous vehicle in real-time

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.

Methods and systems for semantic scene completion for sparse 3D data

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.

Systems and methods for generating a road surface semantic segmentation map from a sequence of point clouds

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.

Method and system for real-time landmark extraction from a sparse three-dimensional point cloud

Devices, systems, methods, and media are described for adaptive scene augmentation of a point cloud frame for inclusion in a labeled point cloud dataset used for training a machine learned model for a prediction task for point cloud frames, such as object detection or segmentation. A formal method is described for generating new point cloud frames based on pre-existing annotated large-scale labeled point cloud frames included in a point cloud dataset to generate new, augmented point cloud frames. A policy is generated for large-scale data augmentation using detailed quantitative metrics such as confusion matrices. The policy is a detailed and stepwise set of rules, procedures, and/or conditions that may be used to generate augmented data specifically targeted to mitigate the existing inaccuracies in the trained model. The augmented point cloud frames may then be used to further train the model to improve the prediction accuracy of the model.

Devices, systems, methods, and media for adaptive augmentation for a point cloud dataset used for training

A system and method for localization of an autonomous vehicle based on 3D point cloud are disclosed. The system includes a processor and a memory coupled to the processor, the memory tangibly storing thereon executable instructions that, when executed by the processor, cause the processor to: receive an initial position of a vehicle; receive a data file representative of a three-dimensional (3D) point cloud from a LIDAR scanning subsystem of the vehicle; divide the 3D point cloud into a plurality of tiles and compute a plurality of key points for each tile; generate an estimated low frequency 2D position and yaw angle for the vehicle based on a particle filter process and a dynamically downloaded 2D reference map; and generate a position and orientation of the vehicle.

Method and system for localization of an autonomous vehicle in real time

A group optimization method for constructing a 3D feature map is disclosed. In one embodiment, the method comprises determining correspondence information for a plurality of environmental features for each image in a group of images in which a respective environmental feature is present and relative position and alignment of each camera. Depth information is determined for each environmental feature in the plurality of environmental features for each image in the group of images in which a respective environmental feature is present based on the correspondence information of the environmental features. Group optimized depth information is determined for each environmental feature in the plurality of environmental features using the determined depth information of each respective environmental feature.

Growing community of inventors

Vaughan, Canada

Yuan Ren