Most existing hyperspectral anomaly detection algorithms primarily rely on spatial information to identify anomalous targets. However, they often overlook the spatial–spectral gradient information inherent in hyperspectral images, which can lead to decreased detection accuracy. To address this limitation, we propose a novel hyperspectral anomaly detection algorithm that incorporates both local sub-block contrast and spatial–spectral gradient features. In this approach, a grid block window is utilized to capture local spatial information. To effectively detect low-contrast targets, we introduce a novel local sub-block ratio-multiply contrast method that enhances anomalous regions while suppressing the background. Additionally, to mitigate the challenges posed by complex backgrounds, a feature extraction technique based on spatial–spectral gradients is proposed. To account for the spectral reflectance differences between anomalous targets and the background, we further introduce a local sub-block ratio-difference contrast method to compute preliminary detection scores. The final anomaly detection results are obtained by merging these two detection scores. The key advantage of the proposed method lies in its ability to exploit local gradient characteristics within hyperspectral images, thereby resolving the issue of edge features being misidentified as anomalies. This method also effectively reduces the impact of noise on detection accuracy. Experimental validation based on four real-world datasets demonstrates that the proposed method outperforms seven state-of-the-art techniques, showing superior performance in both qualitative and quantitative evaluations.

Existing hyperspectral anomaly detection methods leverage the spectral and spatial information in the hyperspectral image (HSI) to detect the anomalies. However, the performance of these methods is limited due to the spectral variability of the materials. To address this issue, a hyperspectral anomaly detection method, based on empirical mode decomposition (EMD) and local weighted contrast (HELWC), is proposed. Firstly, a novel spectral decomposition method based on EMD is adopted to reduce the spectral noise, and estimate the spectral reference of the material. Secondly, spectral Jensen–Shannon(JS) divergence is utilized to describe the distances between different spectra. Subsequently, a local weighted contrast estimation method is proposed to calculate the contrast score. Finally, the contrast score is multiplied with the test pixel to obtain the final detection result. Experiments are conducted on four real-world datasets using multiple metrics for comparing the proposed and the benchmark approaches. The results demonstrate that the proposed method effectively reduces spectral noise and suppresses background. The average AUC _(D,F) of the proposed method on the four datasets is 0.9965, which is 0.0014 higher than the second ranked baseline method. Overall, the proposed algorithm outperforms the nine state-of-the-art methods in both subjective and objective evaluations.