Semantically-Based Animal Pose Estimation in the Wild
Accurate animal pose estimation in the wild is potentially useful for many downstream applications such as wildlife conservation. Currently, the main approach to assessing animal poses is based on identifying keypoints of the body and constructing the skeleton. However, a direct application of frame...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-12-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-2-W5-2024/33/2024/isprs-archives-XLVIII-2-W5-2024-33-2024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850064130792226816 |
|---|---|
| author | M. N. Favorskaya D. N. Natalenko |
| author_facet | M. N. Favorskaya D. N. Natalenko |
| author_sort | M. N. Favorskaya |
| collection | DOAJ |
| description | Accurate animal pose estimation in the wild is potentially useful for many downstream applications such as wildlife conservation. Currently, the main approach to assessing animal poses is based on identifying keypoints of the body and constructing the skeleton. However, a direct application of frameworks to human pose estimation is not successful due to the features of the skeletal structure of humans and mammals. In this study, we propose a two-stage method: coarse-tuning with animal detection using a bounding box, as is done in most similar methods, and fine-tuning with semantic segmentation of animal. The YOLOv8 Pose Estimation and Pose Keypoint Classification model was chosen as the base model for keypoint extraction. Extensive training experiments were conducted using the AwA2 dataset (with a small number of samples from own dataset), the AP-10K dataset, and the Tiger-Pose dataset. The trained model was tested on own dataset collected from camera traps in the Ergaki National Park, Russia. Experimental results show that the proposed algorithm using additional semantic segmentation increases the accuracy of animal pose estimation by 3.6–4.8% on samples of the Ergaki dataset. |
| format | Article |
| id | doaj-art-caca2fb2a185457997f5b2148ea6dca8 |
| institution | DOAJ |
| issn | 1682-1750 2194-9034 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-caca2fb2a185457997f5b2148ea6dca82025-08-20T02:49:23ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-12-01XLVIII-2-W5-2024334010.5194/isprs-archives-XLVIII-2-W5-2024-33-2024Semantically-Based Animal Pose Estimation in the WildM. N. Favorskaya0D. N. Natalenko1Reshetnev Siberian State University of Science and Technology, Institute of Informatics and Telecommunications, 31, Krasnoyarsky Rabochy ave., Krasnoyarsk, 660037, Russian FederationReshetnev Siberian State University of Science and Technology, Institute of Informatics and Telecommunications, 31, Krasnoyarsky Rabochy ave., Krasnoyarsk, 660037, Russian FederationAccurate animal pose estimation in the wild is potentially useful for many downstream applications such as wildlife conservation. Currently, the main approach to assessing animal poses is based on identifying keypoints of the body and constructing the skeleton. However, a direct application of frameworks to human pose estimation is not successful due to the features of the skeletal structure of humans and mammals. In this study, we propose a two-stage method: coarse-tuning with animal detection using a bounding box, as is done in most similar methods, and fine-tuning with semantic segmentation of animal. The YOLOv8 Pose Estimation and Pose Keypoint Classification model was chosen as the base model for keypoint extraction. Extensive training experiments were conducted using the AwA2 dataset (with a small number of samples from own dataset), the AP-10K dataset, and the Tiger-Pose dataset. The trained model was tested on own dataset collected from camera traps in the Ergaki National Park, Russia. Experimental results show that the proposed algorithm using additional semantic segmentation increases the accuracy of animal pose estimation by 3.6–4.8% on samples of the Ergaki dataset.https://isprs-archives.copernicus.org/articles/XLVIII-2-W5-2024/33/2024/isprs-archives-XLVIII-2-W5-2024-33-2024.pdf |
| spellingShingle | M. N. Favorskaya D. N. Natalenko Semantically-Based Animal Pose Estimation in the Wild The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Semantically-Based Animal Pose Estimation in the Wild |
| title_full | Semantically-Based Animal Pose Estimation in the Wild |
| title_fullStr | Semantically-Based Animal Pose Estimation in the Wild |
| title_full_unstemmed | Semantically-Based Animal Pose Estimation in the Wild |
| title_short | Semantically-Based Animal Pose Estimation in the Wild |
| title_sort | semantically based animal pose estimation in the wild |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-2-W5-2024/33/2024/isprs-archives-XLVIII-2-W5-2024-33-2024.pdf |
| work_keys_str_mv | AT mnfavorskaya semanticallybasedanimalposeestimationinthewild AT dnnatalenko semanticallybasedanimalposeestimationinthewild |