Skip to Content
You are currently on the new version of our website. Access the old version .
AnimalsAnimals
  • Article
  • Open Access

17 May 2024

23 Pages

Deconvolution Enhancement Keypoint Network for Efficient Fish Fry Counting

,
,
,
,
,
and
1
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
2
College of Foreign Studies, South China Agricultural University, Guangzhou 510642, China
*
Authors to whom correspondence should be addressed.

Simple Summary

Fish fry counting finds applications in various scenarios, including fish fry trading and the management of breeding densities. However, current computer-based methods struggle to accurately and effectively count large numbers of fish fry and locate them. To address these challenges, this study proposes a fish fry counting method based on a single keypoint as a feature. Additionally, a large-scale fish fry dataset, FishFry-2023, has been constructed, which includes universal point annotations for use. The number of fry in a single image ranges from 204 to 1935, ensuring an effective evaluation of the proposed method. Our approach was trained and tested on FishFry-2023, with experimental results demonstrating an average counting accuracy of 98.59%, exhibiting higher counting precision compared to the density map algorithms now available.

Abstract

Fish fry counting has been vital in fish farming, but current computer-based methods are not feasible enough to accurately and efficiently calculate large number of fry in a single count due to severe occlusion, dense distribution and the small size of fish fry. To address this problem, we propose the deconvolution enhancement keypoint network (DEKNet), a method for fish fry counting that features a single-keypoint approach. This novel approach models the fish fry as a point located in the central part of the fish head, laying the foundation for our innovative counting strategy. To be specific, first, a fish fry feature extractor (FFE) characterized by parallel dual branches is designed for high-resolution representation. Next, two identical deconvolution modules (TDMs) are added to the generation head for a high-quality and high-resolution keypoint heatmap with the same resolution size as the input image, thus facilitating the precise counting of fish fry. Then, the local peak value of the heatmap is obtained as the keypoint of the fish fry, so the number of these keypoints with coordinate information equals the number of fry, and the coordinates of the keypoint can be used to locate the fry. Finally, FishFry-2023, a large-scale fish fry dataset, is constructed to evaluate the effectiveness of the method proposed by us. Experimental results show that an accuracy rate of 98.59% was accomplished in fish fry counting. Furthermore, DEKNet achieved a high degree of accuracy on the Penaeus dataset (98.51%) and an MAE of 13.32 on a public dataset known as Adipocyte Cells. The research outcomes reveal that DEKNet has superior comprehensive performance in counting accuracy, the number of parameters and computational effort.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.