{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T11:28:41Z","timestamp":1787225321055,"version":"build-2736575974"},"reference-count":41,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32260131"],"award-info":[{"award-number":["32260131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31960119"],"award-info":[{"award-number":["31960119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62262001"],"award-info":[{"award-number":["62262001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["32260131"],"award-info":[{"award-number":["32260131"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["31960119"],"award-info":[{"award-number":["31960119"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["62262001"],"award-info":[{"award-number":["62262001"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Yunnan Provincial Science and Technology Department University Joint Project","award":["202301BA070001-035"],"award-info":[{"award-number":["202301BA070001-035"]}]},{"award":["202301BA070001-035"],"award-info":[{"award-number":["202301BA070001-035"]}],"id":[{"id":"https:\/\/ror.org\/03whqdf70","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Scientific Research Fund project of the Education Department of Yunnan Province of China","award":["2025Y1250"],"award-info":[{"award-number":["2025Y1250"]}]},{"name":"Cultivating Plan Program for the Leader in Science and Technology of Yunnan Province of China","award":["202405AC350023"],"award-info":[{"award-number":["202405AC350023"]}]},{"name":"Cultivating Plan Program for the Leader in Science and Technology of Yunnan Province of China","award":["202205AC160001"],"award-info":[{"award-number":["202205AC160001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Animals"],"abstract":"<jats:p>Camera traps are widely used in wildlife surveys but often generate numerous empty images due to false triggers, which are time-consuming to filter manually. Microsoft\u2019s MegaDetector (MD) is commonly applied for empty image filtering; however, setting its confidence threshold is challenging because a high threshold increases the false negative rate (FNR), whereas a low threshold raises the false positive rate (FPR), making it difficult to achieve a satisfactory trade-off between the two. To address this dilemma, we proposed three MD-based methods with different performance and computational requirements. For FNR-sensitive users, we proposed MD_CS, which integrated context image similarity to achieve a very low FNR while controlling the FPR. For FPR-sensitive users, we proposed MD_CL, which used MD to generate supervisory signals for training a classification model, thereby reducing the FPR while controlling the FNR. For users requiring both low FNR and low FPR, we proposed MD_CS_CL, an ensemble method that combined the strengths of MD_CS and MD_CL. Experimental results on multiple datasets showed that these three methods achieved a significantly better balance between FNR and FPR compared to the threshold adjustment method of the MD method. Specifically, MD_CS maintained an FNR of 1.8\u20135.9% while controlling the FPR at 4.9\u20138.5%; MD_CL kept the FPR at 0.4\u20132.6% while controlling the FNR at 3.8\u20138.4%; MD_CS_CL achieved an optimal balance with an FNR of 1.4\u20134.0% and an FPR of 0.3\u20130.9%. On a server equipped with an RTX 4090 GPU, the three methods processed 6.7, 5.4, and 4.0 images per second, respectively, and none required manual annotation. Consequently, the proposed methods reduce labor costs, improve work efficiency, and provide reliable technical support for large-scale wildlife monitoring by achieving a superior FNR\u2013FPR trade-off compared to MD\u2019s traditional threshold regulation.<\/jats:p>","DOI":"10.3390\/ani16162609","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T10:55:18Z","timestamp":1787223318000},"page":"2609","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reannotation-Free Automatic Recognition Methods for Empty Camera Trap Images Based on MegaDetector Optimization"],"prefix":"10.3390","volume":"16","author":[{"given":"Mei","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mathematics and Computer Science, Dali University, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing-Xu","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Dali University, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong-Hai","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Dali University, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Dali University, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo-Peng","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Agricultural and Biological Sciences, Dali University, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4951-7524","authenticated-orcid":false,"given":"Wen","family":"Xiao","sequence":"additional","affiliation":[{"name":"Institute of Eastern-Himalaya Biodiversity Research, Dali University, Dali 671003, China"},{"name":"Collaborative Innovation Center for the Biodiversity in the Three Parallel Rivers of China, Dali 671003, China"},{"name":"Yunling Black-and-White Snub-Nosed Monkey Observation and Research Station of Yunnan Province, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1437-3097","authenticated-orcid":false,"given":"Deng-Qi","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Dali University, Dali 671003, China"},{"name":"Institute of Eastern-Himalaya Biodiversity Research, Dali University, Dali 671003, China"},{"name":"Collaborative Innovation Center for the Biodiversity in the Three Parallel Rivers of China, Dali 671003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"8","DOI":"10.58837\/tnh.24.1.263152","article-title":"Wildlife Species Recorded by Camera Traps in Reforested Lowland Rainforest and Peat Swamp Forest of Gunung Palung National Park, Indonesia","volume":"24","author":"Leo","year":"2024","journal-title":"Trop. Nat. Hist."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1111\/2041-210x.70260","article-title":"Paying attention to other animal detections improves camera trap classification models","volume":"17","author":"Dussert","year":"2026","journal-title":"Methods Ecol. Evol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102453","DOI":"10.1016\/j.ecoinf.2023.102453","article-title":"Object classification and visualization with edge artificial intelligence for a customized camera trap platform","volume":"79","author":"Nazir","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"102095","DOI":"10.1016\/j.ecoinf.2023.102095","article-title":"DeepWILD: Wildlife Identification, Localisation and estimation on camera trap videos using Deep learning","volume":"75","author":"Bouveyron","year":"2023","journal-title":"Ecol. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102060","DOI":"10.1016\/j.ecoinf.2023.102060","article-title":"Bag of tricks for long-tail visual recognition of animal species in camera-trap images","volume":"76","author":"Cunha","year":"2023","journal-title":"Ecol. Inform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"150026","DOI":"10.1038\/sdata.2015.26","article-title":"Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna","volume":"2","author":"Swanson","year":"2015","journal-title":"Sci. Data"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.1111\/2041-210X.70132","article-title":"Essential tools but overlooked bias: Artificial intelligence and citizen science classification affect camera trap data","volume":"16","author":"Santoro","year":"2025","journal-title":"Methods Ecol. Evol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"101021","DOI":"10.1016\/j.ecoinf.2019.101021","article-title":"Zilong: A tool to identify empty images in camera-trap data","volume":"55","author":"Wei","year":"2020","journal-title":"Ecol. Inform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102527","DOI":"10.1016\/j.ecoinf.2024.102527","article-title":"A systematic study on transfer learning: Automatically identifying empty camera trap images using deep convolutional neural networks","volume":"80","author":"Yang","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1111\/2041-210X.13504","article-title":"A deep active learning system for species identification and counting in camera trap images","volume":"12","author":"Norouzzadeh","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/2041-210X.13099","article-title":"Identifying animal species in camera trap images using deep learning and citizen science","volume":"10","author":"Willi","year":"2019","journal-title":"Methods Ecol. Evol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"101350","DOI":"10.1016\/j.ecoinf.2021.101350","article-title":"A systematic study of the class imbalance problem: Automatically identifying empty camera trap images using convolutional neural networks","volume":"64","author":"Yang","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7591","DOI":"10.1002\/ece3.7591","article-title":"An automatic method for removing empty camera trap images using ensemble learning","volume":"11","author":"Yang","year":"2021","journal-title":"Ecol. Evol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1002\/wsb.1176","article-title":"An Adaptive Automatic Approach to Filtering Empty Images from Camera Traps Using a Deep Learning Model","volume":"45","author":"Yang","year":"2021","journal-title":"Wildl. Soc. Bull."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.1002\/ece3.4747","article-title":"Animal Scanner: Software for classifying humans, animals, and empty frames in camera trap images","volume":"9","author":"Yousif","year":"2019","journal-title":"Ecol. Evol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"E5716","DOI":"10.1073\/pnas.1719367115","article-title":"Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning","volume":"115","author":"Norouzzadeh","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"D\u2019acremont, A., Fablet, R., Baussard, A., and Quin, G. (2019). CNN-Based Target Recognition and Identification for Infrared Imaging in Defense Systems. Sensors, 19.","DOI":"10.3390\/s19092040"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1111\/2041-210X.14031","article-title":"Can CNN-based species classification generalise across variation in habitat within a camera trap survey?","volume":"14","author":"Norman","year":"2023","journal-title":"Methods Ecol. Evol."},{"key":"ref_19","unstructured":"Pei, Y., Huang, Y., Zou, Q., Zang, H., Zhang, X., and Wang, S. (2018). Effects of Image Degradations to CNN-based Image Classification. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"102541","DOI":"10.1016\/j.ecoinf.2024.102541","article-title":"WildARe-YOLO: A lightweight and efficient wild animal recognition model","volume":"80","author":"Bakana","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102856","DOI":"10.1016\/j.ecoinf.2024.102856","article-title":"Enhanced Yolov8 network with Extended Kalman Filter for wildlife detection and tracking in complex environments","volume":"84","author":"Jiang","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Loos, A., Weigel, C., and Koehler, M. (2018). Towards Automatic Detection of Animals in Camera-Trap Images. 2018 26th European Signal Processing Conference (EUSIPCO), IEEE.","DOI":"10.23919\/EUSIPCO.2018.8553439"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Beery, S., Wu, G., Rathod, V., Votel, R., and Huang, J. (2020). Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 16\u201318 June 2020, IEEE.","DOI":"10.1109\/CVPR42600.2020.01309"},{"key":"ref_24","unstructured":"Beery, S., Morris, D., and Yang, S. (2019). Efficient Pipeline for Camera Trap Image Review. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Falzon, G., Lawson, C., Cheung, K.-W., Vernes, K., Ballard, G.A., Fleming, P.J.S., Glen, A.S., Milne, H., Mather-Zardain, A., and Meek, P.D. (2019). ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images. Animals, 10.","DOI":"10.1101\/646737"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"552","DOI":"10.3390\/ai2040034","article-title":"A Performance Comparison and Enhancement of Animal Species Detection in Images with Various R-CNN Models","volume":"2","author":"Ibraheam","year":"2021","journal-title":"AI"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Schneider, S., Taylor, G.W., and Kremer, S. (2018). Deep Learning Object Detection Methods for Ecological Camera Trap Data. 2018 15th Conference on Computer and Robot Vision (CRV), IEEE.","DOI":"10.1109\/CRV.2018.00052"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Tan, M., Chao, W., Cheng, J.-K., Zhou, M., Ma, Y., Jiang, X., Ge, J., Yu, L., and Feng, L. (2022). Animal Detection and Classification from Camera Trap Images Using Different Mainstream Object Detection Architectures. Animals, 12.","DOI":"10.3390\/ani12151976"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., Sakaridis, C., Dai, D., and Van Gool, L. (2018, January 18\u201322). Domain Adaptive Faster R-CNN for Object Detection in the Wild. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, Q., and Zhao, Z. (2023). YOLO-G: Improved YOLO for cross-domain object detection. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0291241"},{"key":"ref_31","first-page":"e02104","article-title":"Use of object detection in camera trap image identification: Assessing a method to rapidly and accurately classify human and animal detections for research and application in recreation ecology","volume":"35","author":"Fennell","year":"2022","journal-title":"Glob. Ecol. Conserv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"101876","DOI":"10.1016\/j.ecoinf.2022.101876","article-title":"Human vs. machine: Detecting wildlife in camera trap images","volume":"72","author":"Leorna","year":"2022","journal-title":"Ecol. Inform."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.-Y. (2023). Segment Anything. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 26 June\u20131 July 2016, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_35","unstructured":"Villalva, P., and Jordano, P. (2023). AI-Based Workflow for Recording Plant-Animal Interactions Data with Camera Traps, Estaci\u00f3n Biol\u00f3gica de Do\u00f1ana, EBD-CSIC."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"102231","DOI":"10.1016\/j.ecoinf.2023.102231","article-title":"Automated wildlife image classification: An active learning tool for ecological applications","volume":"77","author":"Bothmann","year":"2023","journal-title":"Ecol. Inform."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1111\/2041-210X.14254","article-title":"Sherlock\u2014A flexible, low-resource tool for processing camera-trapping images","volume":"15","author":"Penn","year":"2024","journal-title":"Methods Ecol. Evol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2500","DOI":"10.1111\/2041-210X.70144","article-title":"An Active Ensemble Classifier for Detecting Animal Sequences from Global Camera Trap Data","volume":"16","author":"Mononen","year":"2025","journal-title":"Methods Ecol. Evol."},{"key":"ref_39","unstructured":"Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., Tsang, I.W., and Sugiyama, M. (2018). Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels. Advances in Neural Information Processing Systems (NeurIPS), NeurIPS."},{"key":"ref_40","unstructured":"Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2017, January 6\u201311). On Calibration of Modern Neural Networks. Proceedings of the 34th International Conference on Machine Learning: ICML 2017, Sydney, Australia."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 26 June\u20131 July 2016, IEEE.","DOI":"10.1109\/CVPR.2016.308"}],"container-title":["Animals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/16\/2609\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T11:04:45Z","timestamp":1787223885000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/16\/2609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":41,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["ani16162609"],"URL":"https:\/\/doi.org\/10.3390\/ani16162609","relation":{},"ISSN":["2076-2615"],"issn-type":[{"value":"2076-2615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}