Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection

TL;DR

This paper introduces PASS, a novel point cloud-based sample selection method that improves anchor-based LiDAR 3D object detection accuracy, addressing training sample ambiguity and achieving state-of-the-art results.

Contribution

The paper proposes PASS, a new training sample selection technique leveraging point cloud distribution to enhance LiDAR 3D detection performance.

Findings

PASS improves average precision of detectors

Achieves state-of-the-art detection accuracy

Validated on multiple datasets

Abstract

3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity in training sample allocation based on box Intersection over Union (IoU_box). This problem impedes further enhancements in the performance of anchor-based LiDAR 3D object detectors. To tackle this challenge, this paper introduces a new training sample selection method that utilizes point cloud distribution for anchor sample quality measurement, named Point Assisted Sample Selection (PASS). This method has undergone rigorous evaluation on two widely utilized datasets. Experimental results demonstrate that the application of PASS elevates the average precision of anchor-based LiDAR 3D object detectors to a novel state-of-the-art, thereby proving the effectiveness of the proposed approach. The codes will be made available at https://github.com/XJTU-Haolin/Point_Assisted_Sample_Selection.