WAV-DUC: a dynamic image enhancement algorithm for underwater environment

Abstract

Object detection underwater is particularly difficult because of issues such as low illumination, illumination changes, and the scarcity of labeled underwater images. To overcome these issues, this paper introduces a new type of hybrid image enhancement method (Wav-DUC). The method incorporates the strengths of CLAHE, DCP, DWT, Unsharp Masking, and Bilateral filtering. While adopting the advantages of these techniques, the proposed method improves image quality under the various conditions of marine environments. The enhancement is done in such a way that the enhancement methods are selectively used above a predetermined threshold so as to enhance the image, resulting in an optimum result. testing the model with benchmark dataset [2], we achieved a PSNR score of 21.78 and an SSIM score of 0.8535. Also, the method has an average execution time of 64.78ms on Raspberry Pi 3. This proves the robustness and faster response time of the algorithm, making it suitable for edge devices.