The Boeing Company

Theboeing Company

Michael Brandon Schwiesow

Anthony Wayne Baker

A method is provided that includes receiving points of an image in which objects are depicted. The method includes performing a greedy nearest-neighbor (GNN) cluster analysis of the image to group the points of the image. The GNN cluster analysis includes grouping the points into a plurality of local GNN clusters, from a greedy analysis using a k-d tree in which the points are organized. The plurality of local GNN clusters are then extended into a plurality of global GNN clusters. This evaluating similarity of the local GNN clusters, merging the local GNN clusters into a global GNN cluster when each of the defined similarity criteria is evaluated to true, and passing the local GNN clusters as global GNN clusters when any of the defined similarity criteria is evaluated to false. The method then includes detecting the objects depicted in the image based on the global GNN clusters.

Rapid object detection for vehicle situational awareness

A method for navigation of a vehicle using point cloud decimation includes generating, by a processor circuit, a ground plane point cloud and an object point cloud. Generating the ground plane point cloud and the object point cloud includes performing point cloud decimation of a 3-D point cloud using ground plane segmentation. The further includes navigating, by the processor circuit, the vehicle using at least the object point cloud.

Vehicle navigation using point cloud decimation

In one or more embodiments, a system for calibration between a camera and a ranging sensor comprises a ranging sensor to obtain ranging measurements for a target located at N number of locations with an emitter at M number of rotation positions. The system further comprises a camera to image the target to generate imaging measurements corresponding to the ranging measurements. Further, the system comprises a processor(s) to determine replacement ranging measurements that all lie in the same plane; to sample the replacement ranging measurements to produce sampled replacement ranging measurements; to determine sampled replacement imaging measurements corresponding to the sampled replacement ranging measurements; and to calculate calibration parameters by using some of the sampled replacement ranging measurements and the sampled replacement imaging measurements corresponding to the sampled replacement ranging measurements that are used, where the calibration parameters estimate the relationship of the camera to the ranging sensor.

High accuracy extrinsic calibration procedure for cameras and range sensors

In one or more embodiments, a method for calibration between a lidar sensor and a camera comprises determining translation parameters of extrinsic calibration parameters by using a location of the camera with respect to the lidar sensor. The method further comprises orienting a target chessboard such that it is aligned with axes of a lidar coordinate system. Also, the method comprises optimizing a best fit transformation between a camera coordinate system and a target chessboard coordinate system. In addition, the method comprises determining a rotation matrix using the best fit transformation between the camera coordinate system and the target chessboard coordinate system. Additionally, the method comprises extracting Euler angles of the extrinsic calibration parameters from the rotation matrix. Also, the method comprises collecting, by the lidar sensor and the camera, calibration scenes using the target chessboard. Further, the method comprises optimizing the extrinsic calibration parameters by using the calibration scenes.

Growing community of inventors

Madison, AL, United States of America

Michael Brandon Schwiesow