Automatic Fish Population Counting by Machine Vision and a Hybrid Deep Neural Network Model

• Published in: Animals
• Main Authors: Zhang, Song, Yang, Xinting, Wang, Yizhong, Zhao, Zhenxi, Liu, Jintao, Liu, Yang, Sun, Chuanheng, Zhou, Chao
• Format: Text
• Language: English
• Published: MDPI 2020
• Subjects: Article; Atlantic salmon
• Online Access: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7070656/; http://www.ncbi.nlm.nih.gov/pubmed/32102380; https://doi.org/10.3390/ani10020364

SIMPLE SUMMARY: In aquaculture, the number of fish population can provide valuable input for the development of an intelligent production management system. Therefore, by using machine vision and a new hybrid deep neural network model, this paper proposes an automated fish population counting method to estimate the number of farmed Atlantic salmon. The experiment showed that the estimation accuracy can reach 95.06%, which can provide an essential reference for feeding and other breeding operations. ABSTRACT: In intensive aquaculture, the number of fish in a shoal can provide valuable input for the development of intelligent production management systems. However, the traditional artificial sampling method is not only time consuming and laborious, but also may put pressure on the fish. To solve the above problems, this paper proposes an automatic fish counting method based on a hybrid neural network model to realize the real-time, accurate, objective, and lossless counting of fish population in far offshore salmon mariculture. A multi-column convolution neural network (MCNN) is used as the front end to capture the feature information of different receptive fields. Convolution kernels of different sizes are used to adapt to the changes in angle, shape, and size caused by the motion of fish. Simultaneously, a wider and deeper dilated convolution neural network (DCNN) is used as the back end to reduce the loss of spatial structure information during network transmission. Finally, a hybrid neural network model is constructed. The experimental results show that the counting accuracy of the proposed hybrid neural network model is up to 95.06%, and the Pearson correlation coefficient between the estimation and the ground truth is 0.99. Compared with CNN- and MCNN-based methods, the accuracy and other evaluation indices are also improved. Therefore, the proposed method can provide an essential reference for feeding and other breeding operations.