.png){kind=icon}
返回
Automated multiple fish tracking in three-Dimension using a Structured Light Sensor
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compag.2015.12.014.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Image-based monitoring using video tracking has been showing potential in aquaculture behavioural studies during the past decade. It provides higher spatial and temporal resolution in comparison to most conventional methods such as hand scoring, tagging or telemetry. It also permits more quantitative environmental data to be collected than do other methods. Studies about trajectory are usually based on tracking in two-Dimensional (2D) environments; however, most aquatic organisms move in a three-Dimensional (3D) environment, which greatly influences ecological interactions. Furthermore, in most 2D image analysis, occlusion of fish is a frequent problem for analysis of tracking and ultimately evaluating their behaviour. Recently, sensors based on 3D single point imaging technology, which can provide geometric information of 3D environment with high-frame rate in real time have been developed. These sensors provide the opportunity to develop a practical and affordable tracking system to study movements of multiple fish in real-time. This study aims to develop a multiple fish tracking system in 3D space based on currently available structured-light sensor. Kinect I as low cost available structured light sensor was used to record a 10-min video from four Nile tilapia (Oreochromis niloticus) which were freely swimming in an aquarium. The video was processed to identify position of each fish in 3D space (x, y, and z) within each frame so as to create a trajectory. The system accurately (98%) tracked multiple tilapia in an aquarium. Another objective of this study was comparing trajectory of introduced system with stereo vision as a conventional method for monitoring in 3D space. This study is contributing to feasibility of new sensor for monitoring fish behaviours in 3D space. (C) 2015 Elsevier B.V. All rights reserved.
Keyword:
3D single point imaging
Structured Light Sensor
Trajectory
Fish tracking
Tilapia
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
1.0W
被引数:
4.8W
机构
引用论文
Preparation of Various Oxide Films by an Electrophoretic Deposition Method: A Study of the Mechanism
.png){kind=icon}
PREAI
分享收藏
A computer vision system to analyse the swimming behaviour of farmed fish in commercial aquaculture facilities: A case study using cage-held Atlantic salmon计算机视觉系统，用于分析商业水产养殖设施中养殖鱼类的游泳行为: 以笼养大西洋鲑鱼为例
PREAI
分享收藏分享收藏分享收藏
查看更多内容