Recent years have witnessed an increasing interest in improving theperception performance of LiDARs on autonomous vehicles . We propose an easy-to-computeinformation-theoretic surrogate cost metric based on Probabilistic OccupancyGrids . We show acorrelation between our surrogate function and common object detectionperformance metrics . We demonstrate the efficacy of our approach by verifying our results in a robust and reproducible data collection and extraction framework based on the CARLA simulator . Our results confirm that sensorplacement is an important factor in 3D point cloud-based object detection and could lead to a variation of performance by 10% ~ 20% on the state-of-the-art algorithms . We believe that this is one of the first studies to useLiDAR placement to improve the performance of perception

Author(s) : Sharad Chitlangia, Zuxin Liu, Akhil Agnihotri, Ding Zhao

Links : PDF - Abstract

Code :
Coursera

Keywords : performance - based - results - object - surrogate -

Leave a Reply

Your email address will not be published. Required fields are marked *