Detection and Analysis of Behavior Trajectory for Sea Cucumbers Based on Deep Learning

Chen Xu,Ying Xiao,Juan Li,Lingxu Jiang,Limiao Deng,Zhongzhi Han

doi:10.1109/access.2019.2962823

Abstract

The motion trajectory of sea cucumbers reflects the behavior of sea cucumbers, and the behavior of sea cucumbers reflects the status of the feeding and individual health, which provides the important information for the culture, status detection and early disease warning. Different from the traditional manual observation and sensor-based automatic detection methods, this paper proposes a detection, location and analysis approach of behavior trajectory based on Faster R-CNN for sea cucumbers under the deep learning framework. The designed detection system consists of a RGB camera to collect the sea cucumbers' images and a corresponding sea cucumber identification software. The experimental results show that the proposed approach can accurately detect and locate sea cucumbers. According to the experimental results, the following conclusions are drawn: (1) Sea cucumbers have an adaptation time for the new environment. When sea cucumbers enter a new environment, the adaptation time is about 30 minutes. Sea cucumbers hardly move within 30 minutes and begin to move after about 30 minutes. (2) Sea cucumbers have the negative phototaxis and prefers to move in the shadows. (3) Sea cucumbers have a tendency to the edge. They like to move along the edge of the aquarium. When the sea cucumber is in the middle of the aquarium, the sea cucumber will look for the edge of the aquarium. (4) Sea cucumbers have unidirectional topotaxis. They move along the same direction with the initial motion direction. The proposed approach will be extended to the detection and behavioral analysis of the other marine organisms in the marine ranching.

Highlights

The motion behavior of sea cucumbers is one of the most basic behavioral ecology characteristics, and it is the basis of feeding, migration, defense, reproduction and other behaviors of sea cucumbers, which reflects the living habit and distribution characteristics of sea cucumbers [1]
The cut photos are synthesized into two videos and the Faster R-CNN is used to detect sea cucumbers
In this paper, an approach to detecting and locating sea cucumbers is researched based on deep learning and the motion trajectories of sea cucumbers are plotted

Summary

Introduction

The motion behavior of sea cucumbers is one of the most basic behavioral ecology characteristics, and it is the basis of feeding, migration, defense, reproduction and other behaviors of sea cucumbers, which reflects the living habit and distribution characteristics of sea cucumbers [1]. The behavioral research of sea cucumbers can reveal the response of sea cucumber to environmental factors, and can be used to improve the seedling technology of sea cucumbers and the. The behavioral research of sea cucumbers can provide a theoretical basis for the development of breeding and fishing facilities [2], [3], so that the economic benefits can be improved [4]. There are some reports about the behavior research of sea cucumber. Kashenko et al researched the vertical motion of the larvae of sea cucumber under different salinities by observing and recording the behavior of the larvaes of sea cucumbers (such as the columnar larvae, large ear larvae, middle ear larvae, small ear larvae, gastrula and blastocysts) [5]. By use of the experiments and field observations, Hamel and Young et al found that the main factors

Methods

Results

Discussion

Conclusion