MMPFNet: A Novel Lightweight Road Target Detection Method of FMCW Radar Based on Hypergraph Mechanism and Attention Enhancement

TL;DR

This paper introduces MMPFNet, a lightweight radar-based road target detection model that improves accuracy and efficiency for automotive systems.

Contribution

The novel MMPFNet model combines hypergraph mechanisms and attention enhancement for improved road target detection using FMCW radar data.

Findings

MMPFNet improves mAP50-95 by 16% and precision by 6% over YOLOv13n on radar datasets.

The model achieves state-of-the-art results on non-visible light datasets like CRUW-ONRD.

MMPFNet maintains a lightweight design while enhancing detection accuracy for road targets.

Abstract

Road target detection is a crucial aspect of current research in automotive advanced driver assistance systems and intelligent transportation systems, where accuracy, speed, and lightweight design are key considerations. Compared to various sensors employed in driving assistance systems, millimeter-wave radar offers advantages such as all-weather operation, low hardware cost, strong penetration capability, and the ability to extract rich spatial information about targets. This paper tackles the challenges posed by the characteristics of Range-Angle map data from 77 GHz Frequency-Modulated Continuous Wave radar—namely, non-visible light imagery, abstract representation, rich fine details, and overlapping features. To this end, this paper proposes MMPFNet, a lightweight model based on the hypergraph mechanism with attention enhancement, as an extension of YOLOv13. First, an M-DSC3k2 module is proposed based on the hypergraph mechanism to enhance attention toward small targets. Second, a detection head with a double-bottleneck inverted MBConv-block structure is designed to improve the model’s accuracy and generalization capability. Third, a lightweight PPLConv module is customized to transform the backbone network, enhancing the model’s lightweight design while slightly reducing its accuracy. Considering the differences from traditional visible light datasets, the Focus Expansion-IoU loss function is introduced into the model to focus attention on different regression samples. The MMPFNet model achieves significant improvements in detecting common road targets such as pedestrians, bicycles, cars, and trucks on the Frequency-Modulated Continuous Wave radar Range-Angle dataset compared to the baseline YOLOv13n model: mAP50-95 increases by 16%, precision improves by 6%, and recall rises by 8.7%. MMPFNet is also evaluated on other non-visible light datasets such as CRUW-ONRD and soundprint datasets. Compared to commonly used detection models like FCOS and RetinaNet, MMPFNet achieves significant performance gains, attaining state-of-the-art results.

Figures