高级检索

融合注意力机制的OpenPose人体跌倒检测算法

OpenPose Human Fall Detection Algorithm Based on Attention Mechanism

  • 摘要: 人员密集场所跌倒事件易引发公共安全问题, 对人体跌倒进行实时监测和预警可降低安全风险. 针对现有基于姿态估计跌倒检测方法模型规模大、时效性差等问题, 提出一种融合注意力机制的OpenPose人体跌倒检测算法DSC-OpenPose. 首先借鉴DenseNet稠密连接思想, 将每层与之前所有层在通道维度上直接连接, 实现特征复用, 减小模型参数规模; 然后在不同阶段之间添加坐标注意力机制, 获取特征图空间方向依赖和精确位置信息, 提高姿态估计精度; 最后提出一种基于人体外椭圆参数、头部高度、下肢高度共同识别跌倒行为的方法, 实现人体目标的跌倒检测. 实验结果表明, 在COCO数据集上, 所提算法在模型规模和精度之间取得了较好的平衡效果;  在RF数据集上, 所提跌倒检测方法的准确率达到98.2%, 精度达到96.6%, 检测速度达到20.2 帧/s, 且模型规模较小, 满足嵌入式设备实时推理需求.

     

    Abstract: Falls in crowded places are easy to cause safety problems, and real-time monitoring can reduce safety risks. Aiming at the problems of large scale and poor timeliness of existing fall detection methods based on pose estimation, this paper proposes an OpenPose human fall detection algorithm DSC OpenPose that integrates attention mechanism. Drawing on DenseNet’s dense connection idea, each layer is directly connected with all previous layers in the channel dimension to achieve feature reuse and reduce the scale of model parameters; A method of identifying fall behavior based on the outer ellipse parameters, head height and lower limb height is proposed to realize the fall detection of human objects. The experimental results on COCO dataset show that compared with other algorithms, this algorithm achieves a good balance between model size and accuracy. At the same time, the fall detection method proposed in this paper has an accuracy  of 98.2%, an precision of 96.6%, and a detection speed of 20.2 frame/s on the RF data set, and the model scale is small to meet the real-time reasoning needs of embedded devices.

     

/

返回文章
返回