Automatically detecting the wild giant panda using deep learning with context and species distribution model |
| |
| Institution: | 1. Key Laboratory of Bio-Resources and Eco-Environment (Ministry of Education), Sichuan University, Chengdu 610064, China;2. College of Mathematics, Sichuan University, Chengdu 610044, China;3. School of Informatics, University of Edinburgh, Edinburgh EH8 9YL, UK;4. Wolong National Nature Reserve Administration, Aba 623000, China;1. Agricultural and Ecological Research Unit, Indian Statistical Institute, Kolkata, India;2. Kerala University of Digital Sciences, Innovation and Technology, Thiruvananthapuram, Kerala, India;3. Department of Statistics, Visva-Bharati, Santiniketan, Birbhum, India;1. School of Resources, Environment and Materials, Guangxi University, 530004 Nanning, China;2. State Key Laboratory of Pollution Control and Resources Reuse, School of the Environment, Nanjing University, Nanjing 210023, China;1. Key Laboratory of Ministry of Education for Coastal Wetland Ecosystems, College of the Environment and Ecology, Xiamen University, Fujian 361102, China;2. Fujian Provincial Key Laboratory for Coastal Ecology and Environmental Studies, Xiamen University, 361102, China;3. Xiamen Key Laboratory of Urban Sea Ecological Conservation and Restoration (USER), Xiamen University, 361102, China;4. Coastal and Ocean Management Institute, Xiamen University, 361102, China;5. School of Energy and Environmental Engineering, University of Science and Technology Beijing, 30 Xueyuan Road, Haidian District, Beijing 100083, China;6. Beijing Key Laboratory of Resource-oriented Treatment of Industrial Pollutants, Beijing 100083, China;1. Unidade Acadêmica de Ciências Biológicas, Universidade Federal de Jataí – UFJ, Jataí, GO, Brazil;2. Departamento de Botânica, Universidade Estadual de Campinas – UNICAMP, Campinas, SP, Brazil;1. Department of Health Science and Biostatistics, School of Health Sciences, Swinburne University of Technology, Hawthorn, Victoria, Australia;2. Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia;3. Sir Peter MacCallum Department of Oncology, The University of Melbourne, Victoria, Australia |
| |
| Abstract: | The giant panda is a flagship species in ecological conservation. The infrared camera trap is an effective tool for monitoring the giant panda. Images captured by infrared camera traps must be accurately recognized before further statistical analyses can be implemented. Previous research has demonstrated that spatiotemporal and positional contextual information and the species distribution model (SDM) can improve image detection accuracy, especially for difficult-to-see images. Difficult-to-see images include those in which individual animals are only partially observed and it is challenging for the model to detect those individuals. By utilizing the attention mechanism, we developed a unique method based on deep learning that incorporates object detection, contextual information, and the SDM to achieve better detection performance in difficult-to-see images. We obtained 1169 images of the wild giant panda and divided them into a training set and a test set in a 4:1 ratio. Model assessment metrics showed that our proposed model achieved an overall performance of 98.1% in mAP0.5 and 82.9% in recall on difficult-to-see images. Our research demonstrated that the fine-grained multimodal-fusing method applied to monitoring giant pandas in the wild can better detect the difficult-to-see panda images to enhance the wildlife monitoring system. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
