Bandwidth-Adaptive Feature Sharing for Cooperative LIDAR Object Detection

TL;DR

This paper introduces a bandwidth-adaptive feature sharing framework for cooperative LIDAR object detection in autonomous vehicles, enhancing robustness and scalability by dynamically adjusting to communication constraints.

Contribution

It proposes a novel adaptive mechanism and decentralized data alignment method to improve cooperative detection performance under varying network capacities.

Findings

Outperforms previous FS-COD method in average precision

Effectively adapts to communication channel capacity variations

Improves cooperative object detection robustness

Abstract

Situational awareness as a necessity in the connected and autonomous vehicles (CAV) domain is the subject of a significant number of researches in recent years. The driver's safety is directly dependent on the robustness, reliability, and scalability of such systems. Cooperative mechanisms have provided a solution to improve situational awareness by utilizing high speed wireless vehicular networks. These mechanisms mitigate problems such as occlusion and sensor range limitation. However, the network capacity is a factor determining the maximum amount of information being shared among cooperative entities. The notion of feature sharing, proposed in our previous work, aims to address these challenges by maintaining a balance between computation and communication load. In this work, we propose a mechanism to add flexibility in adapting to communication channel capacity and a novel decentralized shared data alignment method to further improve cooperative object detection performance. The performance of the proposed framework is verified through experiments on Volony dataset. The results confirm that our proposed framework outperforms our previous cooperative object detection method (FS-COD) in terms of average precision.