Underwater self-supervised monocular depth estimation and its application in image enhancement. (April 2023)

• Record Type: Journal Article
• Authors: Wang, Junting; Ye, Xiufen; Liu, Yusong; Mei, Xinkui; Hou, Jun
• Is Part Of: Engineering applications of artificial intelligence. Volume 120(2023)
• Publication Date: 2023-04
• Subjects: Deep learning -- Underwater image enhancement -- Underwater depth estimation -- Monocular depth estimation; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2023.105846
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Accurate depth estimation is necessary for imaging model-based underwater image enhancement. However, limited by the length of baseline, traditional binocular-based methods are not easy to deploy in underwater scenarios, while monocular methods are more appropriate due to their availability and cost. Therefore, we propose a self-supervised model (called UWdepth) to estimate the depth of underwater scenes with monocular sequences. Addressing the challenges posed by the scale of data and the complexity of motion in underwater scenes, we design an iterative pose network and further introduce a depth consistency loss to achieve more accurate inter-frame motion prediction and depth estimation. The predicted depth can be used to precisely enhance the image based on the underwater imaging model. Experiments show that UWdepth outperforms existing depth estimation models in terms of multiple evaluation indexes. Furthermore, by applying UWdepth, we can enhance underwater images with Akkaynak–Treibitz imaging model, achieving better indexes and visual perception quality than existing traditional and deep-learning based underwater image enhancement algorithms.