Abstract:

To address the challenges of background interference， keypoint localization deviation， and target occlusion in Unmanned Aerial Vehicle （UAV） aerial view human pose estimation， an enhanced human pose estimation algorithm named YOLO-AirPose was proposed for non-ground view scenarios. Firstly， a symmetric flip augmentation strategy based on keypoint topology constraint， named IPSFA （Index-Preserved Symmetric Flip Augmentation）， was designed to improve generalization under multi-view scenarios. Secondly， a C2BRA （C2 Bi-level Routing Attention） module was constructed by integrating BRA （Bi-level Routing Attention） mechanism to replace the original C2PSA （Cross stage Partial with Spatial Attention）， thereby enhancing the model’s perception of small-scale targets and occluded keypoints. Thirdly， combining spatial modeling ability of Transformer， an AIFI （Adaptive Interaction Feature Integration） module was embedded into the backbone network， so that 2D positional encoding was combined to improve keypoint localization performance. Finally， a C3k2-DAttention module based on deformable attention mechanism was designed to strengthen the network’s global modeling and receptive field adjustment abilities. Experimental results show that YOLO-AirPose achieves improvements of 3.0， 5.0， 4.6， and 6.8 percentage points in precision of object detection and precision， recall， and mAP@0.5 of pose estimation compared to the baseline model YOLO-Pose， respectively， while maintaining low computational cost and parameter quantity. It can be seen that the proposed algorithm provides an improved solution to the accuracy limitations in UAV aerial view human pose estimation and enhances adaptability to complex human poses.

Key words: human pose estimation, Unmanned Aerial Vehicle (UAV), YOLOv11-Pose, object detection, region awareness

摘要：

针对无人机（UAV）航拍视角下人体姿态估计中存在的复杂背景干扰、关键点定位偏移和目标遮挡等问题，提出一种适用于非地面视角下的增强型人体姿态估计算法YOLO-AirPose。首先，设计基于关键点拓扑约束的对称翻转增强策略IPSFA （Index-Preserved Symmetric Flip Augmentation），提升多视角场景下的泛化能力；其次，融合BRA（Bi-level Routing Attention）机制构建C2BRA（C2 Bi-level Routing Attention）模块替代原有的C2PSA（Cross stage Partial with Spatial Attention），增强模型对小尺寸目标与遮挡关键点的表达能力；再次，结合Transformer的空间建模能力，将AIFI（Adaptive Interaction Feature Integration）模块嵌入主干网络，以结合2D位置编码优化关键点定位性能；最后，设计基于可变形注意力机制的C3k2-DAttention模块，以增强网络的全局建模与感受野调控能力。实验结果表明，在保持较低计算量和较低参数量的前提下，YOLO-AirPose在目标检测的精确率以及姿态估计的精确率、召回率和mAP@0.5上相较于基准模型YOLO-Pose分别提升了3.0以及5.0、4.6和6.8个百分点。可见，所提算法为UAV俯视视角下人体姿态估计精度不足问题提供了改进方案，同时还提升了对人体复杂姿态的适应能力。

关键词: 人体姿态估计, 无人机, YOLOv11-Pose, 目标检测, 区域感知