Hyperspectral Object Detection Based on Spatial–Spectral Fusion and Visual Mamba

Abstract

Hyperspectral object-detection algorithms based on deep learning have been receiving increasing attention due to their ability to operate without relying on prior spectral information about the target and their strong real-time inference performance. However, current methods are unable to efficiently extract both spatial and spectral information from hyperspectral image data simultaneously. In this study, an innovative hyperspectral object-detection algorithm is proposed that improves the detection accuracy compared to benchmark algorithms and state-of-the-art hyperspectral object-detection algorithms. Specifically, to achieve the integration of spectral and spatial information, we propose an innovative edge-preserving dimensionality reduction (EPDR) module. This module applies edge-preserving dimensionality reduction, based on spatial texture-weighted fusion, to the raw hyperspectral data, producing hyperspectral data that integrate both spectral and spatial information. Subsequently, to enhance the network’s perception of aggregated spatial and spectral data, we integrate a CNN with Visual Mamba to construct a spatial feature enhancement module (SFEM) with linear complexity. The experimental results demonstrate the effectiveness of our method.