Fish Shoals Behavior Detection Based on Convolutional Neural Network and Spatiotemporal Information

Fangfang Han,Baofeng Zhang,Bin Liu,Fuhua Xie,Junchao Zhu

doi:10.1109/access.2020.3008698

Fangfang Han, Baofeng Zhang + Show 3 more

Open Access

https://doi.org/10.1109/access.2020.3008698

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 48	License type: CC BY 4.0

Affiliation: Tianjin University of Technology

Abstract

Behavior is the first visible change in an animal species after exposure to its own or environmental stressors and is a sensitive indicator. Fish are social animals, and the abnormality of group behavior is more indicative about a particular event than individual behavior, providing more effective informeqation about environmental or group social changes. The group behavior is not only reflected in the spatial distribution, but also reflected in the temporal behavior of the group and individual movement changes under the influence of pressure factors. This paper proposes a group behavior discrimination method based on convolutional neural network and spatiotemporal information fusion, which intends to make use of the prominent performance of convolutional neural network in image recognition and state classification, and imitating the attentional mechanism of ventral channel and dorsal channel when the human brain processes visual signals. Some pressure environments are made in laboratory, the behavior states of fish shoals are recorded, and the sample database of shoals’ behavior state is established by combining the spatial information of shoals’ spatial distribution with the time information reflected in the movement behavior. A simple convolutional neural network is constructed to quickly identify the behavior state of fish shoals. The effects of bath size and training epoch on network training speed and recognition accuracy are discussed, and the visualization of the intermediate data of the convolutional neural network is studied. Shown from the results of experiments of this paper, different behavior states of fish shoals can be recognized and classified effectively by using the simple convolutional neural network and spatiotemporal fusion images. What’s more, from the visualization of network intermediate data, it is found that the convolutional neural network has a higher discrimination power to the image edge feature than the image gray-value feature.

Highlights

Fish belong to the group like, underwater activities, breathing with gills hypothermic animals, and individual of fish is sensitive to changes and disturbances in water quality and surrounding environmental factors, so all these factors determine the particularity of fish breeding [1]
The output layer of the CNN is set as six output nodes, corresponding to the six behavior states of the fish shoals to be distinguished in this paper
The size parameters of individual fish do not need to bet concerned about, because this paper puts emphasis on the group behavior of fish shoals. This model has no limitation on the size of individual fish, it is required to adjust the construction structure of the visual imaging system according to the size of the monitored fish shoals, in order to make the system be able to image the whole group of fish, to observe the features of spatial distribution and group motion energy

Summary

Introduction

Fish belong to the group like, underwater activities, breathing with gills hypothermic animals, and individual of fish is sensitive to changes and disturbances in water quality and surrounding environmental factors, so all these factors determine the particularity of fish breeding [1]. Is the first visible change after exposure to one’s own or environmental stressors, which has been shown to be a sensitive indicator with the most direct mapping of health, water quality, inventory density, physical disturbance and other factors. By observing and studying the group behavior state, its correlation with surrounding environment as well as the health of fish body can be found, providing reference value for fish breeding [2], [3]

Objectives

Methods

Findings

Conclusion