深度学习在野生动物图像识别分析中的应用进展

doi:10.16829/j.slxb.150954

兽类学报 ›› 2026, Vol. 46 ›› Issue (1): 20-38.DOI: 10.16829/j.slxb.150954

• 综述 • 上一篇

深度学习在野生动物图像识别分析中的应用进展

陈诗雨¹, 侯金^1,2, 刘丹³, 刘晶³, 罗鹏⁴, 郑伯川⁴, 张晋东¹

1 西南野生动植物资源保护教育部重点实验室, 西华师范大学生命科学学院, 南充 637002;
2 东北虎豹国家公园保护生态学国家林业和草原局重点实验室, 北京师范大学生命科学学院, 北京 100875;
3 西北农林科技大学信息工程学院, 杨凌 712100;
4 西华师范大学计算机学院, 南充 637001

收稿日期:2024-05-13 修回日期:2025-03-17 发布日期:2026-02-03
通讯作者: 张晋东，E-mail:zhangjd224@cwnu.edu.cn
作者简介:陈诗雨（2001-），女，硕士研究生，主要从事野生动物保护与自然保护区建设等研究；侯金（1995-），男，博士研究生，主要从事动物生态学研究.
基金资助:
国家林业和草原局重点项目（CGF2024001）；国家自然科学基金面上项目（U2571211，32470541，32270551，U21A20193）；北京师范大学博士生学科交叉基金项目（BNUXKJC2221）；教育部春晖计划项目（2018）；西华师范大学省级大学生创新创业项目（S202110638062）

Progress in the application of deep learning in wildlife image recognition and analysis

CHEN Shiyu¹, HOU Jin^1,2, LIU Dan³, LIU Jing³, LUO Peng⁴, ZHENG Bochuan⁴, ZHANG Jindong¹

1 Key Laboratory of Southwest Wildlife Resources Protection, Ministry of Education, College of Life Sciences, West China Normal University, Nanchong 637002, China;
2 National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard National Park, College of Life Sciences, Beijing Normal University, Beijing 100875, China;
3 College of Information Engineering, Northwest A & F University, Yangling 712100, China;
4 School of Computer Science, West China Normal University, Nanchong 637001, China

Received:2024-05-13 Revised:2025-03-17 Published:2026-02-03

摘要/Abstract

摘要： 建立完善的野生动物监测体系是开展保护研究的基础。传统人为监测手段由于存在多种局限，部分监测工作逐渐被红外相机陷阱技术所替代，而红外相机监测技术的广泛使用也随之带来海量数据处理与分析的难题。因此，亟需寻找高效处理分析大量红外相机数据的方法。近年来，深度学习在野生动物的图像研究上开展了诸多实践应用。为全面了解深度学习理论与技术在野生动物图像识别上的应用进展，本文梳理了2000—2024年的相关研究，从无效图像筛除、物种识别、个体识别和行为识别等4个方面阐述了常用网络模型应用及其研究进展。总结了深度学习在野生动物图像中的研究现状，并着重讨论了深度学习在红外相机图像中的现存问题及解决方案。针对人工智能图像处理技术在红外相机监测工作中的应用前景进行分析，并对其未来发展做出建议与展望，以期为野生动物的个体识别和种群监测的研究与工作提供思路与方向。

关键词: 图像识别, 人工智能, 深度学习, 红外相机监测

Abstract: Establishing a comprehensive wildlife monitoring system is the foundation for conducting conservation research. Traditional manual monitoring methods have various limitations, and some monitoring efforts have gradually been replaced by infrared camera trap technology. Nevertheless, the widespread use of infrared camera monitoring technology has introduced challenges in handling and analyzing massive amounts of data. Therefore, it is urgent to find an efficient method to process and analyze a large number of infrared camera data. In recent years, deep learning has been widely applied in the study of wild animal images. In order to comprehensively understand the application progress of deep learning theory and technology in wildlife image recognition, we provide an overview of the relevant research from 2000 to 2024. It elaborates on commonly used network models applications and their research progress in terms of eliminating invalid data, species identification, individual recognition, and behavior recognition. We summarize the status of deep learning in two types of images of wild animals, and emphatically discuss the existing problems and solutions of deep learning in infrared camera images. This paper analyzes the potential of applying artificial intelligence image processing techniques in infrared camera monitoring work and provides recommendations and insights for future development in order to provide ideas and directions for research on individual identification and population monitoring of wild animals.

Key words: Image recognition, Artificial intelligence, Deep learning, Infrared camera monitoring

中图分类号:

Q95-33
TP18

陈诗雨, 侯金, 刘丹, 刘晶, 罗鹏, 郑伯川, 张晋东. 深度学习在野生动物图像识别分析中的应用进展[J]. 兽类学报, 2026, 46(1): 20-38.

CHEN Shiyu, HOU Jin, LIU Dan, LIU Jing, LUO Peng, ZHENG Bochuan, ZHANG Jindong. Progress in the application of deep learning in wildlife image recognition and analysis[J]. ACTA THERIOLOGICA SINICA, 2026, 46(1): 20-38.

参考文献

Akcay H G,Kabasakal B,Aksu D,Demir N,ÖZ M,Erdoğan A, 2020. Automated bird counting with deep learning for regional bird distribution mapping[J]. Animals, 10 (7):1027. DOI:10. 3390/ani10071207.
Annesa O D,Kartiko C,Prasetiadi A,2020. Identification of reptile species using convolutional neural networks (CNN)[J]. Rekayasa Sistem Dan Teknologi Informasi,4 (5):899-906.
Antoine M D,Marion V,Georgina B,Frederic T,Beata U,2021.Machine learning is a powerful tool to study the effect of cancer on species and ecosystems[J]. Methods in Ecology and Evolution,12 (12):2310-2323. DOI:10. 29207/resti. v4i5. 2282.
Bala P C,Eisenreich B R,Yoo S B,Hayden B Y,Park H S,Zimmermann J,2020. Automated markerless pose estimation in freely moving macaques with OpenMonkeyStudio[J]. Nature Communications,11 (1). DOI:10. 1038/s41467-020-18441-5.
Bengio Y, Lamblin P, Popovici D, Larochelle H, 2006. Greedy layer-wise training of deep networks[C]. Neural Information Processing Systems 19. DOI:10. 7551/mitpress/7503. 003. 0024.
Bertasius G, Wang H, Torresani L, 2021. Is space-time attention all you need for video understanding?[C]. International Conference on Machine Learning. DOI:10. 48550/arXiv. 2102. 05095.
Bi D X, Chen D L, Chen G T, et al., 2024. DeepSeek LLM:scaling open-source language models with longtermism[J/OL]. arXiv preprint arXiv:2401. 02954.
Biggs B, Boyne O, Charles J, Fitzgibbon A, Cipolla R, 2020.Who left the dogs out? 3D animal reconstruction with expectation maximization in the loop[C]. Computer Vision-ECCV 2020.DOI:10. 1007/978-3-030-58621-8_12.
Biggs B, Roddick T, Fitzgibbon A, Cipolla R, 2019. Creatures great and SMAL:recovering the shape and motion of animals from video[C]. Computer Vision-ACCV 2018. DOI:10. 1007/978-3-030-20873-8_1.
Bochkovskiy A, Wang C Y, Liao H Y M, 2020. YOLOv4:optimal speed and accuracy of object detection[J/OL]. arXiv preprint arXiv:2004. 10934.
Bogucki R,Cygan M,Khan C B,Klimek M,Milczek J K,Mucha M,2018. Applying deep learning to right whale photo identification[J]. Conservation Biology,33 (3):676-684.
Boudaoud L B,Maussang F,Garello R,Chevallier A,2019. Marine bird detection based on deep learning using high-resolution aerial images[C]. Oceans2019-Marseille. DOI:10. 1109/OCEANSE. 2019. 8867242.
Brust C A, Burghardt T, Groenenberg M, KäDing C, KüHl H S, Manguette M L, Denzler J, 2017. Towards automated visual monitoring of individual gorillas in the wild[C]. 2017
IEEE International Conference on Computer Vision Workshops(ICCVW). DOI:10. 1109/ICCVW. 2017. 333,2820-2830.
Cao J K, Tang H Y, Fang H S, Shen X Y, Lu C, Tai Y W, 2019. Cross-domain adaptation for animal pose estimation[C]. 2019 IEEE/CVF International Conference on Computer Vision(ICCV). DOI:10. 1109/ICCV. 2019. 00959.
Cao Y, Xie Z D, Liu B, Lin Y T, Zhang Z, Hu H, 2020.Parametric instance classification for unsupervised visual feature learning[J]. Advances in Neural Information Processing Systems, 33:15614-15624.
Cao Z, Hidalgo G, Simon T, Wei S E, Sheikh Y, 2021. OpenPose:realtime multi-person 2D pose estimation using part affinity fields[J]. Transactions on Pattern Analysis and Machine Intelligence, 43 (1):172-186. DOI:10. 1109/TPAMI. 2019. 2929257.
Carl C,SchöNfeld F,Profft I,Klamm A,Landgraf D,2020. Automated detection of European wild mammal species in camera trap images with an existing and pre-trained computer vision model[J]. European Journal of Wildlife Research,66 (4):62.DOI:10. 1007/s10344-020-01404-y.
Chen C H,Ramanan D,2017. 3D human pose estimation=2D pose estimation + matching[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10. 1109/CVPR. 2017. 610.
Chen C H, Tyagi A, Agrawal A, Drover D, Mv R, Stojanov S, Rehg J M,2019. Unsupervised 3D pose estimation with geometric self-supervision[C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10. 1109/CVPR. 2019. 00586.
Chen P,Swarup P,Matkowski W M,Kong A W,Han S,Zhang Z,Rong H,2020. A study on giant panda recognition based on images of a large proportion of captive pandas[J]. Ecology and Evolution,10 (7):3561-3573. DOI:10. 1002/ece3. 6152.
Cui Y, Jia M L, Lin T Y, Song Y, Belongie S J, 2019.Class-balanced loss based on effective number of samples[C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10. 1109/CVPR. 2019. 00949.
Dai D M,Deng C Q,Zhao C G,Xu R X,Gao H Z,Chen D L, Li J S, Zeng W D, Yu X K, Wu Y, Xie Z D, Li Y K, Huang P P, Luo F L, Ruan C, Sui Z F, Liang W F, 2024.
DeepSeekMoE:towards ultimate expert specialization in mixture-of-experts language models[C]. 62nd Annual Meeting of the Association for Computational Linguistics. DOI:10. 18653/v1/2024. acl-long. 70.
Deepseek-Ai,Liu A X,Feng B,et al., 2024. DeepSeek-V3 technical report[J/OL]. arXiv preprint arXiv:2412. 19437.
Deepseek-Ai, Guo D Y, Yang D J, et al., 2025. DeepSeek-R1:incentivizing reasoning capability in LLMs via reinforcement learning[J/OL]. arXiv preprint arXiv:2501. 12948.
Desai B, Patel A J, Patel V, Shah S, Raval M S, Ghosal R, 2022. Identification of free-ranging mugger crocodiles by applying deep learning methods on UAV imagery[J]. Ecological Informatics,72:101874. DOI:10. 1016/j. ecoinf. 2022. 101874.
Dhariwal P,Nichol A,2021. Diffusion models beat GANs on image synthesis[C]. Neural Information Processing Systems 34 (NeurIPS 2021). DOI:10. 48550/arXiv. 2105. 05233.
Ditria E M,Lopez-Marcano S,Sievers M,Jinks E L,Brown C J, Connolly R M,2020. Automating the analysis of fish abundance using object detection:optimizing animal ecology with deep learning[J]. Frontiers in Marine Science, 7:429. DOI:10. 3389/fmars. 2020. 00429.
Donahue J,Hendricks L A,Rohrbach M,Venugopalan S,Guadarrama S,Saenko K,Darrell T,2017. Long-term recurrent convolutional networks for visual recognition and description[J]. Transactions on Pattern Analysis and Machine Intelligence, 39(4):677-691. DOI:10. 1109/TPAMI. 2016. 2599174.
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X H, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N, 2021. An image is worth 16x16 words:transformers for image recognition at scale[J/OL]. Computing Research Repository, arXiv preprint arXiv:2010. 11929.
Duporge I, Isupova O, Reece S, Macdonald D W, Wang T J, 2021. Using very high-resolution satellite imagery and deep learning to detect and count African elephants in heterogeneous landscapes[J]. Remote Sensing in Ecology and Conservation, 7(3):369-381. DOI:10. 1002/rse2. 195.
Egmont P M, Ridder D D, Handels H, 2002. Image processing with neural networks-a review[J]. Pattern Recognition, 35(10):2279-2301. DOI:10. 1016/s0031-3203(01) 00178-9.
Fabrizio S, Alessandro T, Julio B, Guillermo B, Fernando H, 2019. Reliable methods for identifying animal deaths in GPS- and satellite-tracking data:review, testing and calibration[J]. Journal of Applied Ecology,56 (3):562-572. DOI:10. 1111/1365-2664. 13294.
Fan Z,Liu Y,Xovee X,Goce T,2021. Decoupling representation and regressor for long-tailed information cascade prediction[C]. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)(2021). DOI:10. 1145/3404835. 3463104.
Faurina R, Wijanarko A, Heryuanti A F, Ishak S I, Agustian I. 2023. Comparative study of ensemble deep learning models to determine the classification of turtle species[J]. Computer Science and Information Technologies,4 (1):24-32.
Feng L Q, Zhao Y Q, Sun Y C, Zhao W X, Tang J X, 2021.Action recognition using a spatial-temporal network for wild felines[J]. Animals,11 (2):485. DOI:10. 3390/ani11020485.
Ferreira A C,Silva L R,Renna F,Brandl H B,Renoult J P,Farine D R,Covas R,Doutrelant C,2020. Deep learning-based methods for individual recognition in small birds[J]. Methods in Ecology and Evolution, 11 (9):1072-1085. DOI:10. 1111/2041-210X. 13436.
Freytag A,Rodner E,Simon M,Loos A,KüHl H S,Denzler J, 2016. Chimpanzee faces in the wild:log-euclidean CNNs for predicting identities and attributes of primates[J]. German Conference on Pattern Recognition, 9796:51-63. DOI:10. 1007/978-3-319-45886-1_5.
Gao C Q, Wu J F, Yu H, Yin J H, Guo S H, 2022. FIRN:a novel fish individual recognition method with accurate detection and attention mechanism[J]. Electronics,11 (21):3459. DOI:10. 3390/electronics11213459.
Gavali P R,Banu J S,2020. Bird species identification using deep learning on GPU platform[C]. 2020 International Conference on Emerging Trends in Information Technology and Engineering(ic-ETITE). DOI:10. 1109/ic-ETITE47903. 2020. 85.
Glorot X,Bengio Y,2010. Understanding the difficulty of training deep feedforward neural networks[C]. Journal of Machine Learning Research Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS). DOI:10. 5555/3104322. 3104425.
Goodfellow I,Pouget-Abadie J,Mirza M,Xu B,Warde-Farley D, Ozair S,Courville A,Bengio Y,2020. Generative adversarial networks[J]. Communications of the ACM,63 (11):139-144.
Graving J M, Chae D, Naik H, Li L, Koger B, Costelloe B R, Couzin I D,2019. DeepPoseKit,a software toolkit for fast and robust animal pose estimation using deep learning[J]. eLife, 8.DOI:10. 7554/eLife. 47994. DOI:10. 7554/eLife. 47994.
Gray P C,Bierlich K C,Mantell S A,Friedlaender A S,Goldbogen J A,Johnston D W,2019. Drones and convolutional neural networks facilitate automated and accurate cetacean species identification and photogrammetry[J]. Methods in Ecology and Evolution,10 (9):1490-1500. DOI:10. 1111/2041-210X. 13246.
Guo Q W,Wang C T,Xiao D Q,Huang Q,2024. A lightweight open-world pest image classifier using ResNet8-based matching network and NT-Xent loss function[J]. Expert Systems with Applications,237:121395. DOI:10. 1016/j. eswa. 2023. 121395.
Guo S T,Xu P F,Miao Q G,Shao G F,Chapman C A,Chen X J,He G,Fang D Y,Zhang H,Sun Y W,Shi Z H,Li B G, 2020. Automatic identification of individual primates with deep learning techniques[J]. iScience,23 (8):DOI:org/10. 1016/j. isci. 2020. 101412.
Guo Y M, Liu Y, Oerlemans A, Lao S Y, Wu S, Lew M S, 2016. Deep learning for visual understanding:a review[J]. Neurocomputing, 187:27-48. DOI:10. 1016/j. neucom. 2015. 09. 116.
Harrison D J,Chapin T G,1998. Extent and connectivity of habitat for wolves in eastern north America[J]. Wildlife Society Bulletin, 26 (4):767-775.
He K M,Zhang X Y,Ren S Q,Sun J,2016. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10. 1109/CVPR. 2016. 90.
Hebert P D N,Gregory T R,2005. The promise of DNA barcoding for taxonomy[J]. Systematic Biology,54 (5):852-859. DOI:10. 1080/10635150500354886.
Hinton G E,Salakhutdinov R R,2006. Reducing the dimensionality of data with neural networks[J]. Science, 313 (5786):504-507. DOI:10. 1126/science. 1127647.
Hinton G E,Srivastava N,Krizhevsky A,Sutskever I,Salakhutdinov R R, 2012. Improving neural networks by preventing co-adaptation of feature detectors[J/OL]. Neural and Evolutionary Computing,arXiv preprint arXiv:1207. 0580.
Hou J,He Y X,Yang H B,Connor T,Gao J,Wang Y J,Zeng Y C, Zhang J D, Huang J Y, Zheng B C, Zhou S Q, 2020.
Identification of animal individuals using deep learning:a case study of giant panda[J]. Biological Conservation, 242:108414. DOI:10. 1016/j. biocon. 2020. 108414.
Howard A G, Zhu M L, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H, 2017. Mobilenets:efficient convolutional neural networks for mobile vision applications[J]. Computer Vision and Pattern Recognition, arXiv preprint arXiv:1704. 04861.
Huang Y P,Basanta H,2021. Recognition of endemic bird species using deep learning models[J]. IEEE Access, 9:102975-102984. DOI:10. 1109/ACCESS. 2021. 3098532.
Iskakov K,Burkov E,Lempitsky V,Malkov Y,2019. Learnable triangulation of human pose[C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). DOI:10. 1109/ICCV. 2019. 00781.
Jiang L,Lee C,Teotia D,Ostadabbas S,2022. Animal pose estimation:a closer look at the state-of-the-art, existing gaps and opportunities[J]. Computer Vision and Image Understanding, 222:103483. DOI:10. 1016/j. cviu. 2022. 103483.
Jin L L,Liang H,2017. Deep learning for underwater image recognition in small sample size situations[C]. Oceans2017- Aberdeen. DOI:10. 1109/OCEANSE. 2017. 8084645.
Joe Y N,Matthew J H,Sudheendra V,Oriol V,Rajat M,George T,2015. Beyond short snippets:deep networks for video classification[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI:10. 1109/CVPR. 2015. 7299101.
Joska D,Clark L,Muramatsu N,Jericevich R,Nicolls F,Mathis A,Mathis M W,Patel A,2021. AcinoSet:a 3D pose estimation dataset and baseline models for cheetahs in the wild[C]. 2021 IEEE International Conference on Robotics and Automation(ICRA). DOI:10. 1109/ICRA48506. 2021. 9561338.
Kanopoulos N,Vasanthavada N,Baker R,1988. Design of an image edge detection filter using the sobel operator[J]. IEEE Journal of Solid-State Circuits, 23 (2):358-367. DOI:10. 1109/4. 996.
Kassim Y M, Byrne M E, Burch C G, Mote K, Hardin J B, Larsen D R,Palaniappan K,2020. Small object bird detection in infrared drone videos using Mask R-CNN deep learning[J]. Electronic Imaging,32 (8):85-1-85-8.
Kekre H B, Thepade S D, Banura V K, 2011. Amelioration of walsh-hadamard texture patterns based image retrieval using HSV color space[J]. International Journal of Computer Science and Information Security,9 (3):64-69.
Kocon J,Cichecki I,Kaszyca O,Kochanek M,Szydlo D,Baran J,Bielaniewicz J,Gruza M,Janz A,Kanclerz K,Kocon A, Koptyra B,Kowszewicz W M,Milkowski P,Oleksy M,Piasecki M, Radlinski L, Wojtasik K, Wozniak S, Kazienko P, 2023. ChatGPT:jack of all trades,master of none[J]. Information Fusion,99:101861. DOI:10. 1016/j. inffus. 2023. 101861.
Krizhevsky A,Sutskever I,Hinton G E,2017. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,60 (6):84-90. DOI:10. 1145/3065386.

[1]	黄泳桥, 张承云, 张梓欣, 郝泽周. 陆生哺乳动物声音数据处理分析软件进展与展望[J]. 兽类学报, 2025, 45(6): 784-796.
[2]	李明慧, 黄莘钧, 常劲, 莫志民, 万冬梅, 蒋一婷. 辽西地区狍的相对多度、集群模式及日活动节律[J]. 兽类学报, 2025, 45(3): 356-367.
[3]	尹光华, 覃忠义, 罗文富, 卢立雄, 李函, 高文俊, 徐萍, 李乾恩, 尹存全, 李根会, 张志强, 李育武, 刘东, 蒋学龙, 李学友. 云南哀牢山国家级自然保护区楚雄州片区大中型兽类和雉类多样性初探[J]. 兽类学报, 2024, 44(2): 237-246.
[4]	钟俊杰, 钮冰, 陈沁, 陈翔, 王艳. 深度学习在野生动物保护中的应用[J]. 兽类学报, 2023, 43(6): 734-744.
[5]	漆愚, 苏菡, 侯蓉, 刘鹏, 陈鹏, 臧航行, 张志和. 基于高分辨率网络的大熊猫姿态估计方法[J]. 兽类学报, 2022, 42(4): 451-460.
[6]	宫一男谭孟雨王震赵国静蒋沛林蒋仕铭张鼎基葛剑平冯利民. 基于深度学习的红外相机动物影像人工智能识别：以东北虎豹国家公园为例[J]. 兽类学报, 2019, 39(4): 458-465.
[7]	粟海军李光容陈光平姚小刚张明明胡灿实. 贵州宽阔水自然保护区野生动物红外相机调查初报[J]. 兽类学报, 2018, 38(2): 221-229.

深度学习在野生动物图像识别分析中的应用进展

Progress in the application of deep learning in wildlife image recognition and analysis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics