Giant panda behaviour recognition using images
Monitoring giant panda (Ailuropoda melanoleuca) behaviour is critical for their conservation and understanding their health conditions. Currently, captive giant panda behaviour is usually monitored by their caregivers. In previous studies, researchers observed panda behaviours for short time spans o...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/152948 |
| _version_ | 1811691115576819712 |
|---|---|
| author | Swarup, Pranjal Chen, Peng Hou, Rong Que, Pinjia Liu, Peng Kong, Adams Wai Kin |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Swarup, Pranjal Chen, Peng Hou, Rong Que, Pinjia Liu, Peng Kong, Adams Wai Kin |
| author_sort | Swarup, Pranjal |
| collection | NTU |
| description | Monitoring giant panda (Ailuropoda melanoleuca) behaviour is critical for their conservation and understanding their health conditions. Currently, captive giant panda behaviour is usually monitored by their caregivers. In previous studies, researchers observed panda behaviours for short time spans over a period. However, both caregivers and researchers cannot monitor them 24-h using traditional methods of observation. In other words, animal behaviour data are difficult to collect over long periods and are prone to errors when recorded manually. Some researchers have used wearable devices such as accelerometer ear tags and collar-mounted units with a global position system (GPS) receiver and contactless devices such as depth cameras and video cameras for understanding behaviour of other animals such as primates and American white pelicans. However, the giant panda, an icon of endangered species conservation, is almost completely neglected in these studies. To monitor giant panda behaviour effectively, a fully automated giant panda behaviour recognition method based on Faster R–CNN and two modified ResNet was created. The Faster R–CNN network was able to detect panda bodies and panda faces in images. One of the modified ResNet was trained to classify their behaviour into five classes, walking, sitting, resting, climbing, and eating and the other to recognise whether the panda's eyes and mouth were opened or closed. Experiments were conducted on 10,804 images collected from over 218 pandas in various environments and illumination conditions. The experimental results were very encouraging and achieved an overall accuracy of 90% for the five panda behaviours and an overall accuracy of 84% for the subtle panda facial motions. The proposed method provides an effective way to monitor giant panda behaviour in captivity. |
| first_indexed | 2024-10-01T06:14:46Z |
| format | Journal Article |
| id | ntu-10356/152948 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:14:46Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1529482021-10-22T05:16:11Z Giant panda behaviour recognition using images Swarup, Pranjal Chen, Peng Hou, Rong Que, Pinjia Liu, Peng Kong, Adams Wai Kin School of Computer Science and Engineering Engineering::Computer science and engineering Giant Panda Animal Behaviour Recognition Monitoring giant panda (Ailuropoda melanoleuca) behaviour is critical for their conservation and understanding their health conditions. Currently, captive giant panda behaviour is usually monitored by their caregivers. In previous studies, researchers observed panda behaviours for short time spans over a period. However, both caregivers and researchers cannot monitor them 24-h using traditional methods of observation. In other words, animal behaviour data are difficult to collect over long periods and are prone to errors when recorded manually. Some researchers have used wearable devices such as accelerometer ear tags and collar-mounted units with a global position system (GPS) receiver and contactless devices such as depth cameras and video cameras for understanding behaviour of other animals such as primates and American white pelicans. However, the giant panda, an icon of endangered species conservation, is almost completely neglected in these studies. To monitor giant panda behaviour effectively, a fully automated giant panda behaviour recognition method based on Faster R–CNN and two modified ResNet was created. The Faster R–CNN network was able to detect panda bodies and panda faces in images. One of the modified ResNet was trained to classify their behaviour into five classes, walking, sitting, resting, climbing, and eating and the other to recognise whether the panda's eyes and mouth were opened or closed. Experiments were conducted on 10,804 images collected from over 218 pandas in various environments and illumination conditions. The experimental results were very encouraging and achieved an overall accuracy of 90% for the five panda behaviours and an overall accuracy of 84% for the subtle panda facial motions. The proposed method provides an effective way to monitor giant panda behaviour in captivity. Published version This work was supported by the Chengdu Research Base of Giant Panda Breeding [NO. CPB2018-02; NO. 2020CPB-C09; NO.2021CPB-C01; NO.2021CPB-B06]. The research done in the Nanyang Technological University, Singapore is under the project Development of a Computational Method for Giant Panda Identification from Images NO. CPB2018e02. 2021-10-22T05:16:11Z 2021-10-22T05:16:11Z 2021 Journal Article Swarup, P., Chen, P., Hou, R., Que, P., Liu, P. & Kong, A. W. K. (2021). Giant panda behaviour recognition using images. Global Ecology and Conservation, 26, e01510-. https://dx.doi.org/10.1016/j.gecco.2021.e01510 2351-9894 https://hdl.handle.net/10356/152948 10.1016/j.gecco.2021.e01510 2-s2.0-85101871688 26 e01510 en Global Ecology and Conservation © 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). application/pdf |
| spellingShingle | Engineering::Computer science and engineering Giant Panda Animal Behaviour Recognition Swarup, Pranjal Chen, Peng Hou, Rong Que, Pinjia Liu, Peng Kong, Adams Wai Kin Giant panda behaviour recognition using images |
| title | Giant panda behaviour recognition using images |
| title_full | Giant panda behaviour recognition using images |
| title_fullStr | Giant panda behaviour recognition using images |
| title_full_unstemmed | Giant panda behaviour recognition using images |
| title_short | Giant panda behaviour recognition using images |
| title_sort | giant panda behaviour recognition using images |
| topic | Engineering::Computer science and engineering Giant Panda Animal Behaviour Recognition |
| url | https://hdl.handle.net/10356/152948 |
| work_keys_str_mv | AT swaruppranjal giantpandabehaviourrecognitionusingimages AT chenpeng giantpandabehaviourrecognitionusingimages AT hourong giantpandabehaviourrecognitionusingimages AT quepinjia giantpandabehaviourrecognitionusingimages AT liupeng giantpandabehaviourrecognitionusingimages AT kongadamswaikin giantpandabehaviourrecognitionusingimages |