Cai Yinfan, Tian Kaikai, Ji Liling, Xiao Yongxuan, Pang Dapeng, Hou Pengfei, Ji YunFeng, Wang Lanrong, Li Xiaonan, Lu Jingru, Zhang Wenwen, Wu Jun, Cui Peng, Zhang Baowei
School of Life Sciences, Anhui University, Hefei, 230601, Anhui, China.
School of Artificial Intelligence, Anhui University, Hefei, 230601, Anhui, China.
Sci Rep. 2025 May 10;15(1):16323. doi: 10.1038/s41598-025-00042-1.
Infrared Camera Traps (ICTs) are widely used in ecological research as a noninvasive wildlife monitoring technique, particularly for the detection and identification of animal targets. Existing ICT data screening methods face challenges in recognizing animals against complex backgrounds, particularly fast-moving or small targets. To address these issues, we proposed a target-oriented enhanced data-screening method called GFD-YOLO, which emphasized key locations in images to effectively guide the focus of the model toward target regions, thereby improving detection accuracy. We compared the effects of different preprocessing methods on detection performance. Results revealed that the proposed method improved the mean Average Precision (mAP) by 16.96%, precision by 10.13%, and recall by 24.85% compared to the YOLOv11n model. Therefore, the preprocessing method proposed in this study had significant advantages in reducing false negatives and false positives and was adaptable to wildlife detection tasks under different background conditions. In addition, this method demonstrated higher robustness in scenarios involving lighting variations and fast-moving targets.
红外相机陷阱（ICTs）作为一种非侵入性野生动物监测技术，在生态研究中被广泛应用，尤其用于动物目标的检测和识别。现有的ICT数据筛选方法在识别复杂背景下的动物时面临挑战，特别是快速移动或小型目标。为解决这些问题，我们提出了一种名为GFD-YOLO的面向目标的增强数据筛选方法，该方法强调图像中的关键位置，以有效地引导模型将焦点对准目标区域，从而提高检测精度。我们比较了不同预处理方法对检测性能的影响。结果表明，与YOLOv11n模型相比，该方法的平均精度均值（mAP）提高了16.96%，精确率提高了10.13%，召回率提高了24.85%。因此，本研究提出的预处理方法在减少误报和漏报方面具有显著优势，并且适用于不同背景条件下的野生动物检测任务。此外，该方法在涉及光照变化和快速移动目标的场景中表现出更高的鲁棒性。
