AF‐TigerNet: A lightweight anchor‐free network for real‐time Amur tiger ( Panthera tigris altaica ) detection

Abstract

Monitoring the critically endangered Amur tiger ( Panthera tigris altaica ) is crucial for the conservation of the natural environment. This paper proposes a novel lightweight deep‐learning network for detecting Amur tigers in mobile and resource‐constrained environments, like those using unmanned aerial vehicles. The network uses an anchor‐free mechanism with modified CSPNet and cross stage partial (CSP)‐path aggregation network (PAN) structures, which improves the model's feature extraction capabilities. Label assignment strategy is also improved to stabilize the model training process. Additionally, the random Mosaic and Mixup data augmentation strategy is utilized to address the overfitting issue due to insufficient data in the data set. The model achieves 55.5% mean average precision (mAP [0.5:0.95]) with only 0.617 million parameters and 73.58 frames per second on mobile CPU with pixels input. Results show that the model is an accurate, fast, and practical detector of the Amur tiger, serving as a reference for wildlife detectors of other species. 监测濒危的东北虎（ Panthera Tigris altaica）对自然环境的保护至关重要。本文提出了一种新型轻量级深度学习网络，用于在移动和资源受限的环境下检测东北虎，如使用无人机。该网络采用无锚机制，采用改进的CSPNet和CSP‐PAN结构，提高了模型的特征提取能力。改进了标签分配的策略，以稳定模型的训练过程。此外，采用随机Mosaic和Mixup数据增强策略，以解决数据集中数据不足导致的过拟合问题。本文模型仅含有61.7万个参数，在移动CPU上以416 × 416像素输入，每秒能处理73.58帧，mAP（0.5:0.95）达到了55.5％。结果表明，该模型是一种准确、快速和实用的东北虎检测器，可作为其他物种野生生物检测器的参考。 This research can be applied in real‐time surveillance to help practitioners quickly and automatically detect the Amur Tiger. This research provides a new technical reference for wildlife detector research and development. This research can be combined with animal posture estimation to help study the animal's behavior and combined with re‐identification to provide a log of tiger population density estimates through time.