Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios
This work addresses the problem of enhanced environmental perception in autonomous driving under challenging conditions, representing an incremental improvement in spectral feature extraction.
The paper tackles the challenge of efficiently processing high-dimensional hyperspectral imaging data for autonomous driving by introducing a Multi-scale Spectral Attention Module (MSAM) integrated into UNet, achieving average improvements of 3.61% in mean IoU and 3.80% in mF1 across three datasets with minimal computational overhead.
Recent advances in autonomous driving (AD) have highlighted the potential of Hyperspectral Imaging (HSI) for enhanced environmental perception, particularly in challenging weather and lighting conditions. However, efficiently processing its high-dimensional spectral data remains a significant challenge. This paper introduces a Multi-scale Spectral Attention Module (MSAM) that enhances spectral feature extraction through three parallel 1D convolutions with varying kernel sizes between 1 to 11, coupled with an adaptive feature aggregation mechanism. By integrating MSAM into UNet's skip connections (UNet-SC), our proposed UNet-MSAM achieves significant improvements in semantic segmentation performance across multiple HSI datasets: HyKo-VIS v2, HSI-Drive v2, and Hyperspectral City v2. Our comprehensive experiments demonstrate that with minimal computational overhead (on average 0.02% in parameters and 0.82% GFLOPS), UNet-MSAM consistently outperforms UNet-SC, achieving average improvements of 3.61% in mean IoU and 3.80% in mF1 across the three datasets. Through extensive ablation studies, we have established that multi-scale kernel combinations perform better than single-scale configurations. These findings demonstrate the potential of HSI processing for AD and provide valuable insights into designing robust, multi-scale spectral feature extractors for real-world applications.