Hyperspectral Image Cross-Domain Object Detection Method based on Spectral-Spatial Feature Alignment

TL;DR

The experimental results have proved the effectiveness of HSI cross-domain object detection, which has firstly demonstrated a significant and promising step towards HSI cross-domain object detection in the object detection community and secondly demonstrated the key observation is that the local spatial-spectral characteristics remain invariant across different domains.

Abstract

With consecutive bands in a wide range of wavelengths, hyperspectral images (HSI) have provided a unique tool for object detection task. However, existing HSI object detection methods have not been fully utilized in real applications, which is mainly resulted by the difference of spatial and spectral resolution between the unlabeled target domain and a labeled source domain, i.e. the domain shift of HSI. In this work, we aim to explore the unsupervised cross-domain object detection of HSI. Our key observation is that the local spatial-spectral characteristics remain invariant across different domains. For solving the problem of domain-shift, we propose a HSI cross-domain object detection method based on spectral-spatial feature alignment, which is the first attempt in the object detection community to the best of our knowledge. Firstly, we develop a spectral-spatial alignment module to extract domain-invariant local spatial-spectral features. Secondly, the spectral autocorrelation module has been designed to solve the domain shift in the spectral domain specifically, which can effectively align HSIs with different spectral resolutions. Besides, we have collected and annotated an HSI dataset for the cross-domain object detection. Our experimental results have proved the effectiveness of HSI cross-domain object detection, which has firstly demonstrated a significant and promising step towards HSI cross-domain object detection in the object detection community.

Figures (9)

• Figure 1: Illustration of the invariant local spatial-spectral characteristics and extracted corresponding features from SFA.
• Figure 1: Qualitative results on the LWP $\to$ M2SODAI.
• Figure 2: The overview of SFA.
• Figure 3: The overview of the SSAM.
• Figure 4: The overview of the SACM.