PIXOR: Real-time 3D Object Detection from Point Clouds

We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in computation due to high dimensionality of point clouds. We utilize the 3D...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7652 - 7660
Main Authors Yang, Bin, Luo, Wenjie, Urtasun, Raquel
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Computer architecture
Detectors
Feature extraction
Object detection
Real-time systems
Three-dimensional displays
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary:We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in computation due to high dimensionality of point clouds. We utilize the 3D data more efficiently by representing the scene from the Bird's Eye View (BEV), and propose PIXOR, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions. The input representation, network architecture, and model optimization are specially designed to balance high accuracy and real-time efficiency. We validate PIXOR on two datasets: the KITTI BEV object detection benchmark, and a large-scale 3D vehicle detection benchmark. In both datasets we show that the proposed detector surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00798