Abstract:

With the deepening of population aging， fall detection has become a key issue in the medical and health field. Concerning the low accuracy of fall detection algorithms in complex scenes， an improved fall detection model PDD-FCOS （PVT DRFPN DIoU-Fully Convolutional One-Stage object detection） was proposed. Pyramid Vision Transformer （PVT） was introduced into the backbone network of baseline FCOS algorithm to extract richer semantic information without increasing the amount of computation. In the feature information fusion stage， Double Refinement Feature Pyramid Networks （DRFPN） were inserted to learn the positions and other information of sampling points between feature maps more accurately， and more accurate semantic relationship between feature channels was captured by context information to improve the detection performance. In the training stage， the bounding box regression was carried out by the Distance Intersection Over Union （DIoU） loss. By optimizing the distance between the prediction box and the center point of the object box， the regression box was made to converge faster and more accurately， which improved the accuracy of the fall detection algorithm effectively. Experimental results show that on the open-source dataset Fall detection Database， the mean Average Precision （mAP） of the proposed model reaches 82.2%， which is improved by 6.4 percentage points compared with that of the baseline FCOS algorithm， and the proposed algorithm has accuracy improvement and better generalization ability compared with other state-of-the-art fall detection algorithms.

Key words: object detection, pedestrian fall detection, Pyramid Vision Transformer (PVT), attention mechanism, Double Refinement Feature Pyramid Networks (DRFPN), Distance Intersection over Union (DIoU)

摘要：

随着人口老龄化程度的不断深化，跌倒检测成为医疗与健康领域的一个关键问题。针对复杂场景下跌倒检测算法准确率偏低的问题，提出一种改进的跌倒检测模型——PDD-FCOS（PVT DRFPN DIoU-Fully Convolutional One-Stage object detection）。在基准FCOS算法的骨干网络中引入金字塔视觉转换器（PVT），以不增加计算量为前提提取更丰富的语义信息；在特征信息融合阶段插入双重细化特征金字塔网络（DRFPN），更加准确地学习特征图之间采样点的位置和其他信息，并通过上下文信息捕获特征通道之间更准确的语义关系，从而提升检测性能；训练阶段采用距离交并比（DIoU）损失进行边界框回归，通过优化预测框与目标框中心点的距离，使回归框收敛得更快更准确，从而有效提高跌倒检测算法的准确率。实验结果表明，所提模型在开源数据集Fall detection Database上平均精确度均值（mAP）达到82.2%，与基准FCOS算法相比，所提算法的mAP提升了6.4个百分点，且相较于其他主流目标检测算法有精度上的提升以及更好的泛化能力。

关键词: 目标检测, 行人跌倒检测, 金字塔视觉转换器, 注意力机制, 双重细化特征金字塔网络, 距离交并比