DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images
The automated classification of wildlife species using camera trap images is of paramount importance for wildlife surveys and biodiversity conservation. Deep learning methods, which are particularly adept at handling large datasets, has demonstrated considerable promise in this field. While the came...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124004916 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595428252581888 |
|---|---|
| author | Lifeng Wang Shun Wang Chenxun Deng Haowei Zhu Ye Tian Junguo Zhang |
| author_facet | Lifeng Wang Shun Wang Chenxun Deng Haowei Zhu Ye Tian Junguo Zhang |
| author_sort | Lifeng Wang |
| collection | DOAJ |
| description | The automated classification of wildlife species using camera trap images is of paramount importance for wildlife surveys and biodiversity conservation. Deep learning methods, which are particularly adept at handling large datasets, has demonstrated considerable promise in this field. While the camera trap location context may offer supplementary information for species classification, existing methods frequently fail to adequately incorporate this contextual information. To increase classification accuracy and facilitate ecological information processing, we explore the correlation between location context and species classification tasks, proposing the Decoupled Location Context-guided framework (DeLoCo). DeLoCo incorporates wildlife image backgrounds from camera trap locations to assist in species classification by decoupling co-supervised species and location classification tasks. Moreover, the weighted loss strategy based on correlation strength is proposed to prioritize image samples from locations with fewer classes and minimize the impact of samples from locations with diverse classes. Experiments on two typical camera trap datasets (IWildCam and TerraInc) validates that our approach outperforms eight benchmark methods. This demonstrates the great advantages of utilizing our innovative DeLoCo method for the efficient ecological data processing in camera trap images with location information. The code is available here: https://github.com/rid1cul0us/wildlife. |
| format | Article |
| id | doaj-art-d867fa53251c4d96910e40cd04fe5e9f |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-d867fa53251c4d96910e40cd04fe5e9f2025-01-19T06:24:37ZengElsevierEcological Informatics1574-95412025-03-0185102949DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap imagesLifeng Wang0Shun Wang1Chenxun Deng2Haowei Zhu3Ye Tian4Junguo Zhang5School of Technology, Beijing Forestry University, Beijing, 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing, 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing, 100083, ChinaSchool of Software, Tsinghua University, Beijing, 100084, ChinaSchool of Technology, Beijing Forestry University, Beijing, 100083, China; Corresponding author.School of Technology, Beijing Forestry University, Beijing, 100083, China; Research Center for Biodiversity Intelligent Monitoring, Beijing Forestry University, Beijing, 100083, China; Key Lab of State Forestry and Grassland Administration on Forestry Equipment and Automation, Beijing Forestry University, Beijing, 100083, China; Correspondence to: School of Technology, Beijing Forestry University, 35 Qinghua East Road, Haidian District, Beijing, China.The automated classification of wildlife species using camera trap images is of paramount importance for wildlife surveys and biodiversity conservation. Deep learning methods, which are particularly adept at handling large datasets, has demonstrated considerable promise in this field. While the camera trap location context may offer supplementary information for species classification, existing methods frequently fail to adequately incorporate this contextual information. To increase classification accuracy and facilitate ecological information processing, we explore the correlation between location context and species classification tasks, proposing the Decoupled Location Context-guided framework (DeLoCo). DeLoCo incorporates wildlife image backgrounds from camera trap locations to assist in species classification by decoupling co-supervised species and location classification tasks. Moreover, the weighted loss strategy based on correlation strength is proposed to prioritize image samples from locations with fewer classes and minimize the impact of samples from locations with diverse classes. Experiments on two typical camera trap datasets (IWildCam and TerraInc) validates that our approach outperforms eight benchmark methods. This demonstrates the great advantages of utilizing our innovative DeLoCo method for the efficient ecological data processing in camera trap images with location information. The code is available here: https://github.com/rid1cul0us/wildlife.http://www.sciencedirect.com/science/article/pii/S1574954124004916WildlifeDeep learningSpecies classificationCamera trap imageLocation context |
| spellingShingle | Lifeng Wang Shun Wang Chenxun Deng Haowei Zhu Ye Tian Junguo Zhang DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images Ecological Informatics Wildlife Deep learning Species classification Camera trap image Location context |
| title | DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images |
| title_full | DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images |
| title_fullStr | DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images |
| title_full_unstemmed | DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images |
| title_short | DeLoCo: Decoupled location context-guided framework for wildlife species classification using camera trap images |
| title_sort | deloco decoupled location context guided framework for wildlife species classification using camera trap images |
| topic | Wildlife Deep learning Species classification Camera trap image Location context |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124004916 |
| work_keys_str_mv | AT lifengwang delocodecoupledlocationcontextguidedframeworkforwildlifespeciesclassificationusingcameratrapimages AT shunwang delocodecoupledlocationcontextguidedframeworkforwildlifespeciesclassificationusingcameratrapimages AT chenxundeng delocodecoupledlocationcontextguidedframeworkforwildlifespeciesclassificationusingcameratrapimages AT haoweizhu delocodecoupledlocationcontextguidedframeworkforwildlifespeciesclassificationusingcameratrapimages AT yetian delocodecoupledlocationcontextguidedframeworkforwildlifespeciesclassificationusingcameratrapimages AT junguozhang delocodecoupledlocationcontextguidedframeworkforwildlifespeciesclassificationusingcameratrapimages |