Recognition Method of Abnormal Behavior of Marine Fish Swarm Based on In-Depth Learning Network Model


  • Liyong Chen School of Network Engineering, Zhoukou Normal University, Zhoukou 466001, China
  • Xiuye Yin School of Computer Science and Technology, Zhoukou Normal University, Zhoukou 466001, China



In-depth learning network model, marine fish swarm, recognition, abnormal behavior


In order to solve the problem that individual coordinates are easily ignored in the localization of abnormal behavior of marine fish, resulting in low recognition accuracy, execution efficiency and high false alarm rate, this paper proposes a method of fish abnormal behavior recognition based on deep learning network model. Firstly, the shadow of the fish behavior data is removed, and the background image is subtracted from each frame image to get the gray image of the fish school. Then, the label watershed algorithm is used to identify the fish, and the coordinates of different individuals in the fish swarm are obtained. Combined with the experimental size constraints and the number of fish, and combined with the deep learning network model, the weak link of video tag monitoring of abnormal behavior of marine fish is analyzed. Finally, the multi instance learning method and dual flow network model are used to identify the anomaly of marine fish school. The experimental results show that the method has high recognition accuracy, low false alarm rate and high execution efficiency. This method can provide a practical reference for the related research in this field.


Download data is not yet available.

Author Biographies

Liyong Chen, School of Network Engineering, Zhoukou Normal University, Zhoukou 466001, China

Liyong Chen was born in 1982, male, Chinese, He received master’s degree in School of Computer Science and Technology, Faculty of Electronic Information, Liaoning University of Science and Technology, China, in 2010. He has been teaching at Zhoukou Normal University since 2010. His research interests include artificial intelligence and data mining.

Xiuye Yin, School of Computer Science and Technology, Zhoukou Normal University, Zhoukou 466001, China

Xiuye Yin was born in Xinyang, Henan. P.R. China, in 1984. He received the Master degree from university of science and technology Liaoning, P.R. China. His research interest include computational intelligence, Cloud computing and big data.


Z.M. Wang, X. Wang, H. Song, ‘Mobile user behavior recognition method based on random dropout deep belief network’, Computer Application Research, 34(12), 3797–3800, 2017.

P, J. Wu, X. Mei, Y. He, S.Q. Yuan, ‘Detection method of abnormal behavior in video sequence based on deep network model’, Progress in Laser and Optoelectronics, 56(13), 2019.

H.D. Lu, X. Yu, G.Q. Liu, ‘A method for detecting abnormal behaviors of fish under low dissolved oxygen stress based on image processing and compressed sensing’, Journal of Zhejiang University (Agriculture and Life Sciences), 44(04), 499–506, 2018.

C.W. Chen, Y.G. Du, C. Zhou, C.H. Sun, ‘Fish school feeding behavior recognition technology based on support vector machine’, Jiangsu Agricultural Sciences, 46(07), 226–229, 2018.

Y. Gao, B. Chen, H.M. Liao, M.G. Lei, X. Li, J. Li, et al, ‘Deep learning recognition method for aggressive behaviors of group-raising pigs’, Journal of Agricultural Engineering, 35(23), 192–200, 2019.

F.B. Luo, P. Wang, S.Y. Liang, G.F. Xu, W. Wang, ‘Recognition of abnormal crowd behavior based on deep learning and sparse optical flow’, Computer Engineering, 46(04), 287–293, 300, 2020.

B. Chen, Q.T. Yu, T.M. Chen, ‘Research on the deep learning model of human body behavior recognition based on sensors’, Journal of Zhejiang University of Technology, 46(04), 25–31, 2018.

Z.W. Ni, X.H. Zhu, M.Y. Cheng, ‘Air quality prediction method based on artificial fish school and fractal dimension fusion svm’, Pattern recognition and artificial intelligence, 29(12), 1122–1131, 2016.

X.J. Bi, X.Y. Feng, Human behavior recognition based on improved deep learning model c-grbm, Journal of Harbin Engineering University, 39(01), 156–162, 2018.

Z.H. Miao, Y.C. Shen, X.H. Wang, X.F. Zhou, C.L. Liu, ‘Overlapping fruit image recognition algorithm and experiment in natural environment’, Journal of Agricultural Machinery, 47(06), 21–26, 2016.

Y.L. Huang, C.L. Wan, Human behavior recognition algorithm based on deep learning, Application of Electronic Technology, 44(10), 7–11+16, 2018.

J.Y. Li, B. Zhao, X. Li, H. Liu, Y.F. Liu, J.W. Zou, ‘Network traffic abnormal prediction method based on deep learning’, Computer Engineering and Applications, 056(006), 39–50, 2020.

Chen, L., Zhang, F., & Jiang, S., (2019), Typical military target recognition method based on deep forest learning model under small sample conditions, Journal of China Academy of Electronics, 14(03), 232–237.

M. Zhang, B. Xu, X.Y. Li, M.H. Yin, B.J. Wu, K. Qiu, ‘Deep neural network-based soft-failure detection and failure aware routing and spectrum allocation for elastic optic networks’, Optical Engineering, 58(6): 66107, 1-66107, 9, 2019.

W.Z. Chen, Y. Tang, J. Zhang, ‘Improved fish school algorithm optimization method for industrial control network communication anomaly detection’, Computer Application Research, 36(07), 2164–2168, 2019.

R.P. Zhang, Y.X. Yu, K. Zhang, M. Liu, Z.Q. Shang, ‘Research on human action recognition model based on oi-lstm neural network structure’, Computer Science and Exploration, 12(12), 1926–1939, 2018.

J.Q. Ding, B. Ma, X. Li, ‘Multi-view deep anomaly detection framework for vehicle refueling behavior based on fusion of spatiotemporal data’, Computer Applications, 39(11), 3370–3375, 2019.

X.Y. Feng, Q.R. Zhang, Q.Y. Li, ‘Rolling bearing fault identification based on improved deep network data fusion’, Journal of Chongqing University: Natural Science Edition, 42(02), 52–62, 2019.

X.J. Zhang, C.Z. Li, L.Y. Sun, M.L. Zhang, Behavior recognition based on improved 3d convolutional neural network, Computer Integrated Manufacturing System, 25(08), 2000–2006, 2019.

P. Jin, X.F. Xia, Y. Qiao, X.H. Cui, ‘High-dimensional sensor data anomaly detection algorithm based on deep belief network’, Journal of Sensor Technology, 032(06), 892–901, 2019.

Y.J. Jing, X.Y. Hu, Z.K. Song, Y.Q. Hou, ‘Research on deep convolutional neural network bearing fault recognition based on cnn-svm’, Vibration and Shock, 38(18), 173–178, 2019.

Q.P. Lai, J. Yang, B.D. Tan, L. Wang, S.Y. Fu, L.W. Han, ‘Insulator automatic identification and defect diagnosis model based on yolov2 network’, China Electric Power, 52(07), 31–39, 2019.

J.C. Wang, X.C. Tan, Z.H. Wang, Y.F. Zhong, H.P. Dong, S.T. Zhou, et al, ‘Research on remote sensing image target recognition method based on faster r-cnn deep network’, Journal of Geo-Information Science, 20(10), 132–140, 2018.

Z.M. Guo, H.H. Peng, S.X. Niu, K. Shao, Z. Lv, W. Wang, ‘Host anomaly detection method based on user and network behavior analysis’, Journal of Beijing Jiaotong University, 42(05), 44–50, 2018.

B.C. Jiang, J. Guan, W. Zhou, Y. He, ‘Mining and recognition and analysis of ship abnormal behavior in maritime traffic’, Computer Simulation, 34(06), 329–334, 2017.