Rides
Our service
Phoenix
San Francisco
Los Angeles
Austin
Rides
Our service
Phoenix
San Francisco
Los Angeles
Austin
Technology
Technology
About
Our History
Waymo Leadership
Latest Updates
Press Resources
About
Our History
Waymo Leadership
Latest Updates
Press Resources
Safety
Safety
Community
Community Voices
Community Partners
Community Impact
Community
Community Voices
Community Partners
Community Impact
Careers
Benefits
Values
People
Open Roles
Careers
Benefits
Values
People
Open Roles
StarNet: Targeted Computation for Object Detection in Point Clouds
Jiquan Ngiam
Benjamin Caine
Wei Han
Brandon Yang
Yuning Chai
Pei Sun
Yin Zhou
Xi Yi
Ouais Alsharif
Patrick Nguyen
Zhifeng Chen
Jonathon Shlens
Vijay Vasudevan
Abstract
Detecting objects from LiDAR point clouds is an important component of self-driving car technology as LiDAR provides high resolution spatial information. Previous work on point-cloud 3D object detection has re-purposed convolutional approaches from traditional camera imagery. In this work, we present an object detection system called StarNet designed specifically to take advantage of the sparse and 3D nature of point cloud data. StarNet is entirely point-based, uses no global information, has data dependent anchors, and uses sampling instead of learned region proposals. We demonstrate how this design leads to competitive or superior performance on the large Waymo Open Dataset and the KITTI detection dataset, as compared to convolutional baselines. In particular, we show how our detector can outperform a competitive baseline on Pedestrian detection on the Waymo Open Dataset by more than 7 absolute mAP while being more computationally efficient. We show how our redesign---namely using only local information and using sampling instead of learned proposals---leads to a significantly more flexible and adaptable system: we demonstrate how we can vary the computational cost of a single trained StarNet without retraining, and how we can target proposals towards areas of interest with priors and heuristics. Finally, we show how our design allows for incorporating temporal context by using detections from previous frames to target computation of the detector, which leads to further improvements in performance without additional computational cost.
Share
Links
Download PDF
ArXiv
Copy BibTeX
Copied!
Publication
NeurIPS 2019 ML4AD
Topics
Perception
NeurIPS
2019