A Novel Framework for Giraffe Re-identification Based on Deep Learning

Bokai Wen

doi:10.47297/taposatWSP2633-456907.20250604

PDF
Export
Share
Collection
Album

A Novel Framework for Giraffe Re-identification Based on Deep Learning

Volume 6, Issue 4

Views: 0 Downloads: 0

A Novel Framework for Giraffe Re-identification Based on Deep Learning
A Novel Framework for Giraffe Re-identification Based on Deep Learning
Department of Computer Science University of Nottingham, Ningbo, China
Vol. 6, Issue 4, Pages: 44-51(2025)
Published：22 April 2025
DOI：10.47297/taposatWSP2633-456907.20250604
Accepted：

Scan QR Code

Wen Bokai.A Novel Framework for Giraffe Re-identification Based on Deep Learning[J].Theory and Practice of Science and Technology,2025,06(04):44-51.
DOI：

Wen Bokai.A Novel Framework for Giraffe Re-identification Based on Deep Learning[J].Theory and Practice of Science and Technology,2025,06(04):44-51. DOI： 10.47297/taposatWSP2633-456907.20250604.

摘要

Abstract

Giraffes are crucial to the African ecosystem. They are "botanical gardens" on the grasslands

helping to control plant growth and maintain ecological balance by gnawing on leaves. Besides

giraffes are also an important food source for many animals and their feces help spread seeds and promote plant growth. To understand the giraffe demographic processes

researchers use giraffe photo to identify the individual and monitor the giraffe behaviour. As the number of giraffes to identify increases

expertise-based visual comparisons of images can rapidly become overwhelming. The problem would be even more acute as the number of photos can be easily reached over ten of thousands in digital era. In this paper

we proposed a novel framework which combined YOLOv5 and Swin Transformer for giraffe re-identification. After comparison test

we proof our proposed framework has better performance.

关键词

Keywords

references

Schradin C, Hayes L D. A synopsis of long-term field studies of mammals: achievements, future directions, and some advice[J]. Journal of Mammalogy, 2017, 98(3): 670-677.

Schneider S, Taylor G W, Kremer S C. Similarity learning networks for animal individual re-identification: an ecological perspective[J]. Mammalian Biology, 2022, 102(3): 899-914.

Schneider S, Taylor G W, Kremer S C. Similarity learning networks for animal individual re-identification-beyond the capabilities of a human observer[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision workshops. 2020: 44-52.

Medathati N V K, Neumann H, Masson G S, et al. Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision[J]. computer vision and image understanding, 2016, 150: 1-30.

Bolger D T, Morrison T A, Vance B, et al. A computer‐assisted system for photographic mark–recapture analysis[J]. Methods in Ecology and Evolution, 2012, 3(5): 813-822.

Halloran K M, Murdoch J D, Becker M S. Applying computer‐aided photo‐identification to messy datasets: a case study of T hornicroft's giraffe (G iraffa camelopardalis thornicrofti)[J]. African Journal of Ecology, 2015, 53(2): 147-155.

Muneza A B, Ortiz-Calo W, Packer C, et al. Quantifying the severity of giraffe skin disease via photogrammetry analysis of camera trap data[J]. Journal of wildlife diseases, 2019, 55(4): 770-781.

Lindeberg T. Scale invariant feature transform[J]. 2012.

Buehler P, Carroll B, Bhatia A, et al. An automated program to find animals and crop photographs for individual recognition[J]. Ecological informatics, 2019, 50: 191-196.

Ravoor P C, Sudarshan T S B. Deep learning methods for multi-species animal re-identification and tracking–a survey[J]. Computer Science Review, 2020, 38: 100289.

Schneider S, Taylor G W, Linquist S, et al. Past, present and future approaches using computer vision for animal re‐identification from camera trap data[J]. Methods in Ecology and Evolution, 2019, 10(4): 461-470.

Miele V, Dussert G, Spataro B, et al. Revisiting animal photo‐identification using deep metric learning and network analysis[J]. Methods in Ecology and Evolution, 2021, 12(5): 863-873.

Aburasain R. Application of convolutional neural networks in object detection, re-identification and recognition[D]. Loughborough University, 2020.

Chen R, Little R, Mihaylova L, et al. Wildlife surveillance using deep learning methods[J]. Ecology and evolution, 2019, 9(17): 9453-9466.

Zhang H, Zhang Q, Nguyen P A, et al. Chinese White Dolphin Detection in the Wild[C]//Proceedings of the 3rd ACM International Conference on Multimedia in Asia. 2021: 1-5

Zhao T, Yi X, Zeng Z, et al. MobileNet-Yolo based wildlife detection model: A case study in Yunnan Tongbiguan Nature Reserve, China[J]. Journal of Intelligent & Fuzzy Systems, 2021, 41(1): 2171-2181.

Ribani R, Marengoni M. A survey of transfer learning for convolutional neural networks[C]//2019 32nd SIBGRAPI conference on graphics, patterns and images tutorials (SIBGRAPI-T). IEEE, 2019: 47-57.

Kuncheva L I, Garrido-Labrador J L, Ramos-Pérez I, et al. An experiment on animal re-identification from video[J]. Ecological Informatics, 2023, 74: 101994

Wu Y, Zhao D, Zhang J, et al. An Individual Identity-Driven Framework for Animal Re-Identification[J ] . arXiv preprint arXiv: 2410.22927 , 2024.

Wahltinez O, Wahltinez S J. An open‐source general purpose machine learning framework for individual animal re‐identification using few‐shot learning[J]. Methods in Ecology and Evolution, 2024, 15(2): 373-387.

Čermák V, Picek L, Adam L, et al. WildlifeDatasets: An open-source toolkit for animal re-identification[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2024: 5953-5963.

Hou S, Huang P, Wang Z, et al. OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization[J ] . arXiv preprint arXiv: 2410.00204 , 2024.

Kuncheva L I, Williams F, Hennessey S L, et al. A benchmark database for animal re-identification and tracking[C]//2022 IEEE 5th International Conference on Image Processing Applications and Systems (IPAS). IEEE, 2022: 1-6.

Nepovinnykh E, Eerola T, Biard V, et al. SealID: Saimaa ringed seal re-identification dataset[J]. Sensors, 2022, 22(19): 7602.

Adam L, Čermák V, Papafitsoros K, et al. WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals[J ] . arXiv preprint arXiv: 2406.09211 , 2024.

Shinoda R, Shiohara K. PetFace: A large-scale dataset and benchmark for animal identification[C]//European Conference on Computer Vision. Springer, Cham, 2025: 19-36.

Otarashvili L, Subramanian T, Holmberg J, et al. Multispecies Animal Re-ID Using a Large Community-Curated Dataset[J ] . arXiv preprint arXiv: 2412.05602 , 2024.

Koonce B, Koonce B. ResNet 50[J]. Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization, 2021: 63-72.

Zhang C, Benz P, Argaw D M, et al. Resnet or densenet? introducing dense shortcuts to resnet[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2021: 3550-3559.

Gong M, Fei Q. An Improved Light-weight Deep Transfer Learning for Fetal Lung Ultrasound Image Segmentation[C]//2024 3rd International Conference on Image Processing and Media Computing (ICIPMC). IEEE, 2024: 151-156.

Liu Z, Ning J, Cao Y, et al. Video swin transformer[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022: 3202-3211.

Bagaskara A, Suryanegara M. Evaluation of VGG-16 and VGG-19 deep learning architecture for classifying dementia people[C]//2021 4th International Conference of Computer and Informatics Engineering (IC2IE). IEEE, 2021: 1-4.

Xu B, Wang W, Guo L, et al. CattleFaceNet: A cattle face identification approach based on RetinaFace and ArcFace loss[J]. Computers and Electronics in Agriculture, 2022, 193: 106675.

Alert me when the article has been cited

Submit

Research on Network Security Based on Artificial Intelligence—On How Artificial Intelligence is Reshaping the Landscape of the Network Security Industry

Evaluating Neural Network Models for Stress-Strain Prediction in Coarse-Grained Soils

Artificial Intelligence for Facial Emotion Recognition: A Review

Deep Learning Driven by Digital Twins Helps the Development and Breakthrough of Adaptive Automated Production Lines

Application of deep learning in visual detection in intelligent manufacturing environment

Related Author

Jian Yu College of Computer Science and Electronic Engineering, Hunan University

Zeli Wang State grid Beijing electric power company Chaoyang power supply company, 41 Qianmen West Street

Jiyuan He North China Electric Power University, School of Control and Computer Engineering,Beinong Road

Waikan Chong Intelligent Science and Engineering, Jinan University