Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine
Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine
复制标题
通过形状特征和改进的极限学习机进行基于深度的人体跌倒检测
DOI：
10.1109/jbhi.2014.2304357
复制
发表时间：
2014-11-01
影响因子：
7.7
通讯作者：
Li, Yibin
中科院分区：
文献类型：
--
作者：
Ma, Xin;Wang, Haibo;Li, Yibin
福尔斯是导致老年人伤害的主要原因之一。使用可穿戴设备进行跌倒检测成本高，可能会给老年人的日常生活带来不便。在本文中，我们提出了一种自动跌倒检测方法，只需要一个低成本的深度相机。我们的方法结合了两种计算机视觉技术-基于形状的跌倒表征和基于学习的分类器，以区分福尔斯从其他日常行动。给定一个秋天的视频剪辑，我们提取曲率尺度空间（CSS）功能的人体轮廓在每一帧，并表示一袋CSS的话（BoCSS）的行动。然后，我们利用极端学习机（ELM）分类器来识别BoCSS表示从其他动作的下降。为了消除ELM对超参数的敏感性，提出了一种变长粒子群优化算法来优化ELM的隐层神经元数目、相应的输入权值和偏置。使用低成本的Kinect深度摄像头，我们构建了一个动作数据集，该数据集由十个受试者的六种类型的动作（跌倒，弯腰，坐下，蹲下，行走和躺下）组成。对数据集的实验表明，我们的方法可以达到高达91.15%的灵敏度，77.14%的特异性和86.83%的准确性。在一个公共数据集上，我们的方法可以执行最先进的跌倒检测方法，这些方法需要多个摄像头。
Falls are one of the major causes leading to injury of elderly people. Using wearable devices for fall detection has a high cost and may cause inconvenience to the daily lives of the elderly. In this paper, we present an automated fall detection approach that requires only a low-cost depth camera. Our approach combines two computer vision techniques-shape-based fall characterization and a learning-based classifier to distinguish falls from other daily actions. Given a fall video clip, we extract curvature scale space (CSS) features of human silhouettes at each frame and represent the action by a bag of CSS words (BoCSS). Then, we utilize the extreme learning machine (ELM) classifier to identify the BoCSS representation of a fall from those of other actions. In order to eliminate the sensitivity of ELM to its hyperparameters, we present a variable-length particle swarm optimization algorithm to optimize the number of hidden neurons, corresponding input weights, and biases of ELM. Using a low-cost Kinect depth camera, we build an action dataset that consists of six types of actions (falling, bending, sitting, squatting, walking, and lying) from ten subjects. Experimenting with the dataset shows that our approach can achieve up to 91.15% sensitivity, 77.14% specificity, and 86.83% accuracy. On a public dataset, our approach performs comparably to state-of-the-art fall detection methods that need multiple cameras.