Enhancing Underwater Images of a Bionic Horseshoe Crab Robot Using an Artificial Lateral Inhibition Network

TL;DR

This paper introduces an underwater image enhancement method inspired by the compound eye of a bionic horseshoe crab robot, improving contrast and target recognition in low-resource environments.

Contribution

A novel artificial lateral inhibition network (ALIN) is proposed for underwater image enhancement, inspired by biological systems and optimized for low energy and high efficiency.

Findings

ALIN effectively enhances contrast between highlight and shadow areas in underwater images.

The ALIN outperforms traditional algorithms in emphasizing key image features and suppressing non-informative pixels.

The BHCR successfully maneuvers and identifies targets underwater using ALIN-enhanced images.

Abstract

This paper proposes an underwater image enhancement technology based on an artificial lateral inhibition network (ALIN) generated in the compound eye of a bionic horseshoe crab robot (BHCR). The concept of a horizontal suppression network is applied to underwater image processing with the aim of achieving low energy consumption, high efficiency processing, and adaptability to limited computing resources. The lateral inhibition network has the effect of “enhancing the center and suppressing the surroundings”. In this paper, a pattern recognition algorithm is used to compare and analyze the images obtained by an artificial lateral inhibition network and eight main underwater enhancement algorithms (white balance, histogram equalization, multi-scale Retinex, and dark channel). Therefore, we can evaluate the application of the artificial lateral inhibition network in underwater image enhancement and the deficiency of the algorithm. The experimental results show that the ALIN plays an obvious role in enhancing the important information in underwater image processing technology. Compared with other algorithms, this algorithm can effectively improve the contrast between the highlight area and the shadow area in underwater image processing, solve the problem that the information of the characteristic points of the collected image is not prominent, and achieve the unique effect of suppressing the intensity of other pixel points without information. Finally, we conduct target recognition verification experiments to assess the ALIN’s performance in identifying targets underwater with the BHCR in static water environments. The experiments confirm that the BHCR can maneuver underwater using multiple degrees of freedom (MDOF) and successfully acquire underwater targets.

Figures