Random Walk Detection of Small Targets Based on Information Entropy and Intensity Local Contrast Method

Underwater sonar target detection and tracking face persistent challenges due to the complex and variable aquatic environment, resulting in low signal-to-noise ratios and fluctuating intensity levels. These challenges are further exacerbated when detecting small, weakly scattering targets, making effective and stable detection crucial. This paper introduces a nested multi-scale sonar target detection method leveraging random walk principles, based on the local contrast of information entropy and target intensity. The method unfolds in four stages: Initially, target intensity and information entropy are calculated to estimate the potential target range. Subsequently, a multi-scale local contrast descriptor suppresses background noise. The random walk fine local contrast descriptor then distinguishes the target from the background, precisely locating and enhancing the target. Finally, these descriptors are integrated using the nesting principle to enhance targets while suppressing the background. This method has been validated through real lake experiments. Both qualitative and quantitative analyses, along with sequence data analysis, demonstrate superior target detection accuracy compared to traditional baseline methods.