Toward Robust LiDAR based 3D Object Detection via Density-Aware Adaptive Thresholding

TL;DR

This paper introduces a distance-aware adaptive thresholding post-processing method to improve the robustness of LiDAR-based 3D object detection in diverse urban and adverse weather scenarios, reducing false positives and negatives.

Contribution

It proposes a novel adaptive thresholding algorithm that dynamically adjusts detection thresholds based on object distance, enhancing detection accuracy in challenging real-world environments.

Findings

Improved detection accuracy across urban scenarios

Reduced false positives and negatives

Enhanced robustness in adverse weather conditions

Abstract

Robust 3D object detection is a core challenge for autonomous mobile systems in field robotics. To tackle this issue, many researchers have demonstrated improvements in 3D object detection performance in datasets. However, real-world urban scenarios with unstructured and dynamic situations can still lead to numerous false positives, posing a challenge for robust 3D object detection models. This paper presents a post-processing algorithm that dynamically adjusts object detection thresholds based on the distance from the ego-vehicle. 3D object detection models usually perform well in detecting nearby objects but may exhibit suboptimal performance for distant ones. While conventional perception algorithms typically employ a single threshold in post-processing, the proposed algorithm addresses this issue by employing adaptive thresholds based on the distance from the ego-vehicle, minimizing false negatives and reducing false positives in urban scenarios. The results show performance enhancements in 3D object detection models across a range of scenarios, not only in dynamic urban road conditions but also in scenarios involving adverse weather conditions.