Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring
Wildlife monitoring using camera traps is a vital tool for ecosystem health assessment. However, camera traps often face high rates of false-triggered images (empty shots), significantly impacting data processing efficiency. This study proposes a metric learning-based method for false-triggered imag...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125001001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850147343921315840 |
|---|---|
| author | Rui Zhu Enting Zhao Chunhe Hu Jiangjian Xie Junguo Zhang Huijian Hu |
| author_facet | Rui Zhu Enting Zhao Chunhe Hu Jiangjian Xie Junguo Zhang Huijian Hu |
| author_sort | Rui Zhu |
| collection | DOAJ |
| description | Wildlife monitoring using camera traps is a vital tool for ecosystem health assessment. However, camera traps often face high rates of false-triggered images (empty shots), significantly impacting data processing efficiency. This study proposes a metric learning-based method for false-triggered image recognition. By integrating K-means clustering for sample selection and a triplet loss function for model optimization, the approach effectively distinguishes subtle feature differences in false-triggered images. Experiments demonstrate that the proposed method achieves 80.17% Accuracy, 79.79% Recall, and a reduced false positive rate (FPR) of 19.48% on test datasets collected from various regions. Compared to traditional models, it improves Accuracy and Recall by 5.5% and 5.96%, respectively, while reducing the FPR by 5%. On embedded device Jetson Nano, the method achieves a single-image inference time of just 0.076 s, showcasing its potential for deployment in resource-constrained environments. This research addresses challenges related to high intra-class diversity and inter-class similarity in false-triggered images, offering a novel solution to enhance wildlife monitoring efficiency. The code is available at https://github.com/hzl-bjfu/AIPL/tree/master/RFTI. |
| format | Article |
| id | doaj-art-6e0409344af8461c8cb8a798f2556389 |
| institution | OA Journals |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-6e0409344af8461c8cb8a798f25563892025-08-20T02:27:35ZengElsevierEcological Informatics1574-95412025-07-018710309110.1016/j.ecoinf.2025.103091Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoringRui Zhu0Enting Zhao1Chunhe Hu2Jiangjian Xie3Junguo Zhang4Huijian Hu5School of Technology, Beijing Forestry University, Beijing, 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing, 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing, 100083, China; Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation, Beijing, 100083, China; Research Center for Biodiversity Intelligent Monitoring, Beijing Forestry University, Beijing, 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing, 100083, China; State Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing, 100083, China; Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation, Beijing, 100083, China; Research Center for Biodiversity Intelligent Monitoring, Beijing Forestry University, Beijing, 100083, China; Corresponding authors.School of Technology, Beijing Forestry University, Beijing, 100083, China; State Key Laboratory of Efficient Production of Forest Resources, Beijing Forestry University, Beijing, 100083, China; Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation, Beijing, 100083, China; Corresponding authors.Guangdong Key Laboratory of Animal Conservation and Resource Utilization, Guangdong Public Laboratory of Wild Animal Conservation and Utilization, Institute of Zoology, Guangdong Academy of Sciences, Guangzhou 510260, ChinaWildlife monitoring using camera traps is a vital tool for ecosystem health assessment. However, camera traps often face high rates of false-triggered images (empty shots), significantly impacting data processing efficiency. This study proposes a metric learning-based method for false-triggered image recognition. By integrating K-means clustering for sample selection and a triplet loss function for model optimization, the approach effectively distinguishes subtle feature differences in false-triggered images. Experiments demonstrate that the proposed method achieves 80.17% Accuracy, 79.79% Recall, and a reduced false positive rate (FPR) of 19.48% on test datasets collected from various regions. Compared to traditional models, it improves Accuracy and Recall by 5.5% and 5.96%, respectively, while reducing the FPR by 5%. On embedded device Jetson Nano, the method achieves a single-image inference time of just 0.076 s, showcasing its potential for deployment in resource-constrained environments. This research addresses challenges related to high intra-class diversity and inter-class similarity in false-triggered images, offering a novel solution to enhance wildlife monitoring efficiency. The code is available at https://github.com/hzl-bjfu/AIPL/tree/master/RFTI.http://www.sciencedirect.com/science/article/pii/S1574954125001001Wildlife monitoringCamera trapsFalse trigger imagesConvolutional neural networkMetric learningYOLO |
| spellingShingle | Rui Zhu Enting Zhao Chunhe Hu Jiangjian Xie Junguo Zhang Huijian Hu Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring Ecological Informatics Wildlife monitoring Camera traps False trigger images Convolutional neural network Metric learning YOLO |
| title | Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring |
| title_full | Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring |
| title_fullStr | Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring |
| title_full_unstemmed | Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring |
| title_short | Metric learning unveiling disparities: A novel approach to recognize false trigger images in wildlife monitoring |
| title_sort | metric learning unveiling disparities a novel approach to recognize false trigger images in wildlife monitoring |
| topic | Wildlife monitoring Camera traps False trigger images Convolutional neural network Metric learning YOLO |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125001001 |
| work_keys_str_mv | AT ruizhu metriclearningunveilingdisparitiesanovelapproachtorecognizefalsetriggerimagesinwildlifemonitoring AT entingzhao metriclearningunveilingdisparitiesanovelapproachtorecognizefalsetriggerimagesinwildlifemonitoring AT chunhehu metriclearningunveilingdisparitiesanovelapproachtorecognizefalsetriggerimagesinwildlifemonitoring AT jiangjianxie metriclearningunveilingdisparitiesanovelapproachtorecognizefalsetriggerimagesinwildlifemonitoring AT junguozhang metriclearningunveilingdisparitiesanovelapproachtorecognizefalsetriggerimagesinwildlifemonitoring AT huijianhu metriclearningunveilingdisparitiesanovelapproachtorecognizefalsetriggerimagesinwildlifemonitoring |