MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detection

TL;DR

MUFASA is a novel radar object detection framework that improves feature extraction using a plug-and-play module and multi-view attention, achieving state-of-the-art results in autonomous driving scenarios.

Contribution

The paper introduces GeoSPA and DEMVA modules for enhanced radar feature extraction and multi-view attention, advancing radar-based object detection methods.

Findings

Achieved 50.24% mAP on VoD dataset, outperforming previous methods.

Demonstrated effectiveness of GeoSPA and DEMVA modules in real-world datasets.

Enhanced detection robustness under adverse weather conditions.

Abstract

In recent years, approaches based on radar object detection have made significant progress in autonomous driving systems due to their robustness under adverse weather compared to LiDAR. However, the sparsity of radar point clouds poses challenges in achieving precise object detection, highlighting the importance of effective and comprehensive feature extraction technologies. To address this challenge, this paper introduces a comprehensive feature extraction method for radar point clouds. This study first enhances the capability of detection networks by using a plug-and-play module, GeoSPA. It leverages the Lalonde features to explore local geometric patterns. Additionally, a distributed multi-view attention mechanism, DEMVA, is designed to integrate the shared information across the entire dataset with the global information of each individual frame. By employing the two modules, we present our method, MUFASA, which enhances object detection performance through improved feature extraction. The approach is evaluated on the VoD and TJ4DRaDSet datasets to demonstrate its effectiveness. In particular, we achieve state-of-the-art results among radar-based methods on the VoD dataset with the mAP of 50.24%.