ASY-VRNet: Waterway Panoptic Driving Perception Model based on Asymmetric Fair Fusion of Vision and 4D mmWave Radar

TL;DR

ASY-VRNet is a novel waterway perception model that fuses vision and radar data using asymmetric fair fusion modules, achieving state-of-the-art multitask performance for autonomous surface vehicle navigation.

Contribution

The paper introduces asymmetric fair fusion modules for effective multimodal feature interaction, tailored for multitask waterway perception in autonomous navigation.

Findings

Achieves state-of-the-art results on WaterScenes benchmark.

Effectively integrates vision and radar data for multiple perception tasks.

Demonstrates improved performance over existing lightweight models.

Abstract

Panoptic Driving Perception (PDP) is critical for the autonomous navigation of Unmanned Surface Vehicles (USVs). A PDP model typically integrates multiple tasks, necessitating the simultaneous and robust execution of various perception tasks to facilitate downstream path planning. The fusion of visual and radar sensors is currently acknowledged as a robust and cost-effective approach. However, most existing research has primarily focused on fusing visual and radar features dedicated to object detection or utilizing a shared feature space for multiple tasks, neglecting the individual representation differences between various tasks. To address this gap, we propose a pair of Asymmetric Fair Fusion (AFF) modules with favorable explainability designed to efficiently interact with independent features from both visual and radar modalities, tailored to the specific requirements of object detection and semantic segmentation tasks. The AFF modules treat image and radar maps as irregular point sets and transform these features into a crossed-shared feature space for multitasking, ensuring equitable treatment of vision and radar point cloud features. Leveraging AFF modules, we propose a novel and efficient PDP model, ASY-VRNet, which processes image and radar features based on irregular super-pixel point sets. Additionally, we propose an effective multitask learning method specifically designed for PDP models. Compared to other lightweight models, ASY-VRNet achieves state-of-the-art performance in object detection, semantic segmentation, and drivable-area segmentation on the WaterScenes benchmark. Our project is publicly available at https://github.com/GuanRunwei/ASY-VRNet.