元数据
计算机科学
摄像机陷阱
可扩展性
存水弯(水管)
过程(计算)
上下文图像分类
任务(项目管理)
野生动物
人工智能
图像(数学)
数据库
万维网
生态学
环境科学
工程类
生物
系统工程
环境工程
操作系统
作者
Aslak Tøn,Ali Shariq Imran,Mohib Ullah
标识
DOI:10.1109/euvip58404.2023.10323040
摘要
Camera trap imaging has emerged as a valuable tool for modern wildlife surveillance, enabling researchers to monitor and study wild animals and their behaviours. However, a significant challenge in camera trap data analysis is the labour-intensive task of species classification from the captured images. This study proposes a novel approach to species classification by leveraging metadata associated with camera trap images. By developing predictive models using metadata alone, we demonstrate that accurate species classification can be achieved without accessing the image data. Our approach reduces the computational burden and offers potential benefits in scenarios where image access is restricted or limited. Our findings highlight the valuable role of metadata in complementing the species classification process and present new opportunities for efficient and scalable wildlife monitoring using camera trap technology.
科研通智能强力驱动
Strongly Powered by AbleSci AI