深度学习在野生动物保护中的应用  

Application of deep learning in wildlife conservation

作　　者：钟俊杰 钮冰[1] 陈沁[1] 陈翔 王艳 ZHONG Junjie;NIU Bing;CHEN Qin;CHEN Xiang;WANG Yan(School of Life Sciences,Shanghai University,Shanghai 200444,China;Shanghai Customs,Shanghai 200135,China;Technical Center for Animal Plant and Food Inspection and Quarantine,Shanghai Customs,Shanghai 200135,China)

机构地区：[1]上海大学生命科学学院,上海200444 [2]上海海关,上海200135 [3]上海海关动植物与食品检验检疫技术中心,上海200135

出　　处：《兽类学报》2023年第6期734-744,共11页Acta Theriologica Sinica

基　　金：国家重点研发计划(2022YFC2601200)。

摘　　要：野生动物是重要的生物资源之一,但是人类活动的增加和自然环境的恶化严重威胁着野生动物的生存。而深度学习已经成为人工智能领域重点研究方向之一,被广泛应用于各个学科领域,其灵活性使得它在野生动物保护中的图像识别、监测和音频识别等方面展现出了巨大的潜力。本文介绍了几种常见的深度学习算法,综述了不同深度学习模型在野生动物保护中的应用,分析了目前存在的问题及挑战,包括有限的训练数据、环境条件的多变性以及野生动物行为的复杂性等。在未来利用深度学习保护野生动物,除了要解决数据获取和利用、图像的抗干扰等方面的挑战外,还需开发更加稳健和高效的深度学习模型,以满足野生动物保护的特殊需求。Wildlife is one of the vital biological resources,but the increasing human activities and environmental degradation pose a severe threat to the survival of wild animals.Deep learning has emerged as a prominent research direction in the field of artificial intelligence and has been widely applied across various disciplines.Its versatility has demonstrated enormous potential in wildlife conservation,particularly in image recognition,monitoring,and audio recognition.This article introduces several common deep learning algorithms,provides an overview of the applications of different deep learning models in wildlife conservation,and analyzes the current issues and challenges,including limited training data,variability of environmental conditions,and the complexity of wildlife behavior.In the future,to employ deep learning for wildlife protection,in addition to addressing challenges such as data acquisition and utilization,and robustness in image recognition against various interferences,it is crucial to develop more robust and efficient deep learning models that cater to the specific requirements of wildlife conservation.

关 键 词：深度学习 图像识别 音频识别 野生动物保护 

分 类 号：Q95[生物学—动物学]