MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent training target, inevitably resulting in a lack of useful informa...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Yongjian, Tai, Lei, Sun, Kai, Li, Mingyang
Format: Conference Proceeding
Language:English
Subjects:
Autonomous vehicles
Cameras
Feature extraction
Object detection
Three-dimensional displays
Two dimensional displays
Uncertainty
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent training target, inevitably resulting in a lack of useful information for occluded samples. To this end, we propose a novel method to improve the monocular 3D object detection by considering the relationship of paired samples. This allows us to encode spatial constraints for partially-occluded objects from their adjacent neighbors. Specifically, the proposed detector computes uncertainty-aware predictions for object locations and 3D distances for the adjacent object pairs, which are subsequently jointly optimized by nonlinear least squares. Finally, the one-stage uncertainty-aware prediction structure and the post-optimization module are dedicatedly integrated for ensuring the run-time efficiency. Experiments demonstrate that our method yields the best performance on KITTI 3D detection benchmark, by outperforming state-of-the-art competitors by wide margins, especially for the hard samples.
ISSN:2575-7075
DOI:10.1109/CVPR42600.2020.01211