MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection

TL;DR

MambaST introduces a plug-and-play cross-spectral spatial-temporal fusion pipeline that enhances pedestrian detection in low-light conditions, combining thermal and RGB data efficiently for real-time autonomous driving applications.

Contribution

It presents a novel Multi-head Hierarchical Patching and Aggregation (MHHPA) structure for effective cross-spectral fusion, improving detection accuracy and efficiency over existing methods.

Findings

Outperforms existing models in small-scale pedestrian detection.

Achieves superior accuracy in low-light conditions.

Offers an efficient alternative to Transformer-based models.

Abstract

This paper proposes MambaST, a plug-and-play cross-spectral spatial-temporal fusion pipeline for efficient pedestrian detection. Several challenges exist for pedestrian detection in autonomous driving applications. First, it is difficult to perform accurate detection using RGB cameras under dark or low-light conditions. Cross-spectral systems must be developed to integrate complementary information from multiple sensor modalities, such as thermal and visible cameras, to improve the robustness of the detections. Second, pedestrian detection models are latency-sensitive. Efficient and easy-to-scale detection models with fewer parameters are highly desirable for real-time applications such as autonomous driving. Third, pedestrian video data provides spatial-temporal correlations of pedestrian movement. It is beneficial to incorporate temporal as well as spatial information to enhance pedestrian detection. This work leverages recent advances in the state space model (Mamba) and proposes a novel Multi-head Hierarchical Patching and Aggregation (MHHPA) structure to extract both fine-grained and coarse-grained information from both RGB and thermal imagery. Experimental results show that the proposed MHHPA is an effective and efficient alternative to a Transformer model for cross-spectral pedestrian detection. Our proposed model also achieves superior performance on small-scale pedestrian detection. The code is available at https://github.com/XiangboGaoBarry/MambaST}{https://github.com/XiangboGaoBarry/MambaST.