Affiliation:
1. College of Control Science and Engineering, Zhejiang University, Hangzhou 310058, China
2. Signal Intelligence Detection and Life Behavior Perception Institute, NingboTech University, Ningbo 315100, China
3. Zhejiang Engineering Research Center for Intelligent Marine Ranch Equipment, Ningbo 315100, China
Abstract
The species and population size of marine fish are important for maintaining the ecological environment and reflecting climate change. Traditional fish detection methods mainly rely on manual or traditional computer vision, which has disadvantages such as complex design, low detection accuracy, and poor generalization. The widespread use of ocean observation systems has accumulated a large number of images and videos, which makes the application of deep learning on marine fish detection possible. In this paper, a real-time high-precision fish detection algorithm based on YOLOv5s is constructed. Considering the enhancement of the channel representation and spatial interaction ability of the model, the attention mechanism and gated convolution are introduced, respectively, and GhostNet is introduced to lighten the model. Through a series of model comparisons, two improved models, S-Head-Ghost-Fish9 and S-SE-HorBlock-Head-Ghost-Fish9, are finally obtained. Compared with the original model, in terms of model size, the former reduces by 19% and the latter increases by 9.5%; in terms of computation, the former reduces by 15.7% and the latter reduces by 3.1%; in terms of detection speed, both take about 17 ms to detect a single image, and both can meet the real-time detection requirements; in terms of detection accuracy, the former improves by 3% and the latter by 3.6%. Compared with the latest detection algorithms of YOLOv6 and YOLOv8, the detection accuracy is slightly lower than 1%, but the model size and computation amount are only 1/3 to 1/2 of them. The improved models can help assess the population size and growth of the fish, which is of great significance in maintaining the stability of the fish population.
Funder
National Natural Science Foundation of China
Ningbo Youth Science and Technology Innovation Leading Talent Project
Ningbo Public Welfare Research Program
Subject
Ocean Engineering,Water Science and Technology,Civil and Structural Engineering
Reference26 articles.
1. Deep Learning on Underwater Marine Object Detection: A Survey;BlancTalon;Advanced Concepts for Intelligent Vision Systems, Proceedings of the 18th International Conference (ACIVS 2017), Antwerp, Belgium, September 18-21, 2017,2017
2. Trade-off between number and length of remote videos for rapid assessments of reef fish assemblages;Garcia;J. Fish Biol.,2021
3. Real-world underwater fish recognition and identification, using sparse representation;Hsiao;Ecol. Informatics,2014
4. Cutter, G., Stierhoff, K., and Zeng, J. (2015, January 6–9). Automated Detection of Rockfish in Unconstrained Underwater Videos Using Haar Cascades and a New Image Dataset: Labeled Fishes in the Wild. Proceedings of the 2015 IEEE Winter Applications and Computer Vision Workshops, Waikoloa, HI, USA.
5. Automated fish detection in underwater images using shape-based level sets;Ravanbakhsh;Photogramm. Rec.,2015