DeepPanda: A Video-Based Framework for Automatic Behavior Recognition of Giant Pandas
Source abstract
Abstract
Ex situ conservation in breading centers is one of the key strategies for saving giant pandas (Ailuropoda melanoleuca). Abnormal behaviors (e.g., inappetence) are key symptoms of potential health issues (e.g., Klebsiella pneumoniae) for the captives. Therefore, monitoring their normal activity patterns could set a baseline to detect these abnormalities for implementing timely interventions. However, traditional monitoring methods are labor-intensive, which often rely on manual observations. Here, we proposed a deep learning framework, termed as DeepPanda, for automatically recognizing four essential behaviors (i.e., eating, walking, resting and drinking) of giant pandas based on videos from common surveillance cameras. Experimental results demonstrated that the DeepPanda model achieved high performance on the self-established APanda dataset, with the testing mean average precision at an IoU threshold of 0.5 (mAP@0.5) of 98.8%. This methodology provides a powerful tool for monitoring the captive giant panda’s behaviors.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Context-Aware Activity Recognition Systems · Water Quality Monitoring Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
Key Laboratory of SFGA on the Giant Panda, China Conservation and Research Center for Giant Panda, Chengdu 610081, China
References (23)
Show source-provided references
1. Qin, W., Liu, J., Pan, H., Cheng, Y., Song, X., Fu, M., Zhang, Y., Luan, X., and Yang, B. (2024). Effects of ecological restoration measures on growth renewal and nutritional quality of Arundinaria faberi in degraded habitat of giant panda. Forests, 15.10.3390/f15122241 ↗
2. Tian, H., Zeng, Y., Zhang, Z., Lu, M., and Wei, W. (2025). Grazing-Induced Habitat Degradation: Challenges to Giant Panda Survival Resulting from Declining Bamboo and Soil Quality. Animals, 15.10.3390/ani15020202 ↗
3. Habitat status and feasibility of constructing corridors for a vulnerable population of giant pandas
4. Panda downlisted but not out of the woods10.1111/conl.12355 ↗
5. Comprehensive breeding techniques for the giant panda10.1007/978-3-030-23633-5_10 ↗
6. Feng, Y., Chen, Y., Liu, S., Hou, R., Yan, X., Geng, Y., Zhong, Z., Guo, H., Ouyang, P., and Zhang, D. (2022). Surveillance Study of Klebsiella pneumoniae in the Giant Panda Revealed High Genetic Diversity and Antibiotic Therapy Challenge. Antibiotics, 11.10.3390/antibiotics11040473 ↗
7. Parasites of the giant panda: A risk factor in the conservation of a species10.1016/bs.apar.2017.12.003 ↗
8. Feichtenhofer, C., Fan, H., Malik, J., and He, K. (2019, January 27). Slowfast networks for video recognition. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00630 ↗
9. Daily activity of captive giant pandas (Ailuropoda melanoleuca) at the Wolong Reserve10.1002/zoo.1430130104 ↗
10. Behavior of giant pandas (Ailuropoda melanoleuca) in captive conditions: Gender differences and enclosure effects10.1002/zoo.10076 ↗
11. The Hawthorne effect: A reconsideration of the methodological artifact10.1037/0021-9010.69.2.334 ↗
12. Chen, J., Wen, Q., Zhuo, C., and Mete, M. (2012, January 19–21). Pose recognition of giant pandas based on gradient shapes. Proceedings of the 2012 International Conference on Computational Problem-Solving, Leshan, China.
13. Identification of animal individuals using deep learning: A case study of giant panda10.1016/j.biocon.2020.108414 ↗
14. Giant panda face recognition based on PandaFaceNet10.1016/j.ecoinf.2023.102225 ↗
15. A joint time and spatial attention-based transformer approach for recognizing the behaviors of wild giant pandas10.1016/j.ecoinf.2024.102797 ↗
16. (2024, May 28). YOLOv8. Available online: https://github.com/ultralytics/ultralytics.
17. Martin, P., and Bateson, P. (2007). Measuring Behaviour: An Introductory Guide, Cambridge University Press. [3rd ed.].10.1017/CBO9780511810893 ↗
18. Carreira, J., and Zisserman, A. (2017, January 21–26). Quo vadis, action recognition? a new model and the kinetics dataset. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.502 ↗
19. Feichtenhofer, C. (2020, January 5). X3d: Expanding architectures for efficient video recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00028 ↗
20. Hara, K., Kataoka, H., and Satoh, Y. (2017, January 22–29). Learning spatio-temporal features with 3d residual networks for action recognition. Proceedings of the IEEE International Conference on Computer Vision Workshops, Venice, Italy.10.1109/ICCVW.2017.373 ↗
21. Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18–24). Simam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Virtual.
22. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
23. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗