Motional Ad LLC

Samsung Electronics Co., Ltd.

Qi Chen

Sourabh Vora

Lin Sun

A system is configured to segment instances of objects in a pseudo-image. The pseudo-image can be generated from a 3D image coupled to a vehicle. The system can receive the pseudo-image, which can include multiple sections. The system can determine an object classification for a section and determine an instance portion classification for the section. The system can group the section with another section based on the object classification and the instance portion classification. The grouping can correspond to an instance of an object in the image. The system can use the grouping to navigate the vehicle.

Instance segmentation in a pseudo-image

Among other things, techniques for detecting objects in the environment surrounding a vehicle are described. A computer system is configured to receive a set of measurements from a sensor of a vehicle. The set of measurements includes a plurality of data points that represent a plurality of objects in a 3D space surrounding the vehicle. The system divides the 3D space into a plurality of pillars. The system then assigns each data point of the plurality of data points to a pillar in the plurality of pillars. The system generates a pseudo-image based on the plurality of pillars. The pseudo-image includes, for each pillar of the plurality of pillars, a corresponding feature representation of data points assigned to the pillar. The system detects the plurality of objects based on an analysis of the pseudo-image. The system then operates the vehicle based upon the detecting of the objects.

Streaming object detection and segmentation with polar pillars

A system and method for three-dimensional (3D) object classification are disclosed. A computing system receives point cloud data from an input source. The point cloud data may include first and second points in 3D space. The first point may represent a feature of an object. The computing system invokes a neural network for classifying the first point with a first label, and regresses a bounding box based on classifying the first point with the first label. Regressing the bounding box includes predicting at least a location of the bounding box. The computing system may control an autonomous vehicle based on regressing the bounding box.

Growing community of inventors

Baltimore, MD, United States of America

Qi Chen