Influence of Camera-LiDAR Configuration on 3D Object Detection for Autonomous Driving

TL;DR

This paper investigates how different camera and LiDAR sensor configurations affect 3D object detection performance in autonomous driving, proposing a new evaluation metric and validating it through extensive simulations and experiments.

Contribution

It introduces a unified information-theoretic surrogate metric for sensor configuration evaluation and demonstrates its effectiveness in correlating sensor setup with detection accuracy.

Findings

Sensor configurations can cause up to 30% variation in detection accuracy.

The proposed surrogate metric effectively predicts detection performance based on sensor placement.

Experimental validation on nuScenes confirms the importance of sensor arrangement in autonomous perception.

Abstract

Cameras and LiDARs are both important sensors for autonomous driving, playing critical roles in 3D object detection. Camera-LiDAR Fusion has been a prevalent solution for robust and accurate driving perception. In contrast to the vast majority of existing arts that focus on how to improve the performance of 3D target detection through cross-modal schemes, deep learning algorithms, and training tricks, we devote attention to the impact of sensor configurations on the performance of learning-based methods. To achieve this, we propose a unified information-theoretic surrogate metric for camera and LiDAR evaluation based on the proposed sensor perception model. We also design an accelerated high-quality framework for data acquisition, model training, and performance evaluation that functions with the CARLA simulator. To show the correlation between detection performance and our surrogate metrics, We conduct experiments using several camera-LiDAR placements and parameters inspired by self-driving companies and research institutions. Extensive experimental results of representative algorithms on nuScenes dataset validate the effectiveness of our surrogate metric, demonstrating that sensor configurations significantly impact point-cloud-image fusion based detection models, which contribute up to 30% discrepancy in terms of the average precision.