Aquatic Toxic Analysis by Monitoring Fish Behavior Using Computer Vision: A Recent Progress.

Lingxin Chen,Longwen Fu,Chunlei Xia,Yuedan Liu,Hui Liu,Zuoyi Liu

doi:10.1155/2018/2591924

Abstract

Video tracking based biological early warning system achieved a great progress with advanced computer vision and machine learning methods. Ability of video tracking of multiple biological organisms has been largely improved in recent years. Video based behavioral monitoring has become a common tool for acquiring quantified behavioral data for aquatic risk assessment. Investigation of behavioral responses under chemical and environmental stress has been boosted by rapidly developed machine learning and artificial intelligence. In this paper, we introduce the fundamental of video tracking and present the pioneer works in precise tracking of a group of individuals in 2D and 3D space. Technical and practical issues suffered in video tracking are explained. Subsequently, the toxic analysis based on fish behavioral data is summarized. Frequently used computational methods and machine learning are explained with their applications in aquatic toxicity detection and abnormal pattern analysis. Finally, advantages of recent developed deep learning approach in toxic prediction are presented.

Highlights

Monitoring aquatic toxicology is a fundamental and essential task for risk assessment in aquatic ecosystems and water resource management
We summarize the fundamental of video tracking and the development of behavioral monitoring
Behavioral sensing plays an important role in risk assessment in aquatic ecosystems

Summary

Introduction

Monitoring aquatic toxicology is a fundamental and essential task for risk assessment in aquatic ecosystems and water resource management. Sensing disturbance (e.g., pollutants or toxicants) in aquatic system is a crucial issue for early warning of water quality. In the early stage of behavioral monitoring of aquatic organisms, behavioral signal was represented by the strength of electrical fields in the surrounding water of the testing organisms. Video tracking based biological early warning system achieved a great progress in the last decade since advanced computer vision algorithms are developed and integrated to the behavioral monitoring system [13, 14]. Computational models are widely studied for prediction of disturbance (e.g., toxicant) in aquatic ecosystem in the last decades. Developed machine learning techniques provide sophisticated approaches of detecting abnormal behaviors of aquatic organisms exposed chemical stress. An overview of computational models and machine learning algorithm for investigating behavioral changes to toxic chemicals is presented and the recent research of toxicity prediction using deep learning is presented

Video Tracking Based Behavioral Monitoring

Toxic Analysis

Conclusions