Fish length estimation of free-swimming grouper in the cage culture using Underwater Televisual System (UTS), De-haze water correction, and deep learning methods

Abstract

This study aimed to obtain growth parameters for free-swimming grouper in cage culture by using a stereo camera Underwater Televisual System (UTS) for video recording. The UTS technology, utilizing two cameras, enables 3D perception and triangulation of rays for accurate depth estimation. The collected data underwent de-hazing water correction, preprocessing, and labeling. The length of the grouper was detected using the SSD Mobilenet v3 algorithm, with localization loss of 0.06%, accuracy of 92.00%, precision of 92.00%, recall of 100%, and F1-score of 95.83%. The measured length results indicated averages of 12.65 ± 3.81 cm and 26.00 ± 19.79 cm for two different sizes of free-swimming grouper. The study demonstrated that combining de-hazing water correction with the SSD Mobilenet v3 algorithm allows direct and accurate measurement of free-swimming grouper length. The integration of UTS technology and advanced algorithms significantly enhances the accuracy and efficiency of fish growth measurement in cage culture. These findings have practical implications for the development of sustainable fish farming practices, enabling optimized feed and water management, reduced mortality rates, and maximized production yields. Accurate growth monitoring contributes to the growth of the aquaculture industry, meeting the increasing demand for seafood sustainably.