Perception-and-Cognition-Inspired Quality Assessment for Sonar Image Super-Resolution

Due to the light-independent imaging characteristics, sonar images play a crucial role in fields such as underwater detection and rescue. However, the resolution of sonar images is negatively correlated with the imaging distance. To overcome this limitation, Super-Resolution (SR) techniques have been introduced into sonar image processing. Nevertheless, it is not always guaranteed that SR maintains the utility of the image. Therefore, quantifying the utility of SR reconstructed Sonar Images (SRSIs) can facilitate their optimization and usage. Existing Image Quality Assessment (IQA) methods are inadequate for evaluating SRSIs as they fail to consider both the unique characteristics of sonar images and reconstruction artifacts while meeting task requirements. In this paper, we propose a Perception-and-Cognition-inspired quality Assessment method for Sonar image Super-resolution (PCASS). Our approach incorporates a hierarchical feature fusion-based framework inspired by the cognitive process in the human brain to comprehensively evaluate SRSIs' quality under object recognition tasks. Additionally, we select features at each level considering visual perception characteristics introduced by SR reconstruction artifacts such as texture abundance, contour details, and semantic information to measure image quality accurately. Importantly, our method does not require training data and is suitable for scenarios with limited available images. Experimental results validate its superior performance.