An image enhancement approach for coral reef fish detection in underwater videos |
| |
| Affiliation: | 1. Agricultural and Ecological Research Unit, Indian Statistical Institute, Kolkata, India;2. Kerala University of Digital Sciences, Innovation and Technology, Thiruvananthapuram, Kerala, India;3. Department of Statistics, Visva-Bharati, Santiniketan, Birbhum, India;1. Unidade Acadêmica de Ciências Biológicas, Universidade Federal de Jataí – UFJ, Jataí, GO, Brazil;2. Departamento de Botânica, Universidade Estadual de Campinas – UNICAMP, Campinas, SP, Brazil;1. Biodiversity Centre, Finnish Environment Institute, Latokartanonkaari 11, FI-00790 Helsinki, Finland;2. Finnish Meteorological Institute, Weather and climate change impact research, P.O. Box 503, FI-00101 Helsinki, Finland;3. Department of Geosciences and Geography, University of Helsinki, P.O. Box 64, Gustaf Hällströminkatu 2a, 00014 Helsinki, Finland;1. Teagasc, Environment, Soils and Land Use Department, Johnstown Castle, Co. Wexford Y35 Y521, Ireland;2. Bangor College China, a Joint Unit of Bangor University, Wales, UK and Central South University of Forestry and Technology, Changsha 410004, Hunan, China;3. Department of Environmental Sciences, Government College University Faisalabad, Faisalabad 38000, Pakistan;4. Department of Soil and Environmental Sciences, College of Agriculture, University of Sargodha, Sargodha 40100, Punjab, Pakistan;1. Department of Health Science and Biostatistics, School of Health Sciences, Swinburne University of Technology, Hawthorn, Victoria, Australia;2. Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia;3. Sir Peter MacCallum Department of Oncology, The University of Melbourne, Victoria, Australia |
| |
| Abstract: | Coral reefs are rich in fisheries and aquatic resources, and the study and monitoring of coral reef ecosystems are of great economic value and practical significance. Due to complex backgrounds and low-quality videos, it is challenging to identify coral reef fish. This study proposed an image enhancement approach for fish detection in complex underwater environments. The method first uses a Siamese network to obtain a saliency map and then multiplies this saliency map by the input image to construct an image enhancement module. Applying this module to the existing mainstream one-stage and two-stage target detection frameworks can significantly improve their detection accuracy. Good detection performance was achieved in a variety of scenarios, such as those with luminosity variations, aquatic plant movements, blurred images, large targets and multiple targets, demonstrating the robustness of the algorithm. The best performance was achieved on the LCF-15 dataset when combining the proposed method with the cascade region-based convolutional neural network (Cascade-RCNN). The average precision at an intersection-over-union (IoU) threshold of 0.5 (AP50) was 0.843, and the F1 score was 0.817, exceeding the best reported results on this dataset. This study provides an automated video analysis tool for marine-related researchers and technical support for downstream applications. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
