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...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Zhu, Enting Zhao, Chunhe Hu, Jiangjian Xie, Junguo Zhang, Huijian Hu
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