Department of Software Engineering, University of Management and Technology, UMT Road, C-II Johar Town, Lahore 54000, Pakistan.
Department of Computer Science, Information Technology University (ITU), 346-B, Ferozepur Road, Lahore, Punjab 54000, Pakistan.
Sensors (Basel). 2018 Jun 12;18(6):1918. doi: 10.3390/s18061918.
Fall induced damages are serious incidences for aged as well as young persons. A real-time automatic and accurate fall detection system can play a vital role in timely medication care which will ultimately help to decrease the damages and complications. In this paper, we propose a fast and more accurate real-time system which can detect people falling in videos captured by surveillance cameras. Novel temporal and spatial variance-based features are proposed which comprise the discriminatory motion, geometric orientation and location of the person. These features are used along with ensemble learning strategy of boosting with J48 and Adaboost classifiers. Experiments have been conducted on publicly available standard datasets including () and achieving percentage accuracies of 99.2, 99.25 and 99.0, respectively. Comparisons with nine state-of-the-art methods demonstrate the effectiveness of the proposed approach on both datasets.
跌倒造成的伤害对老年人和年轻人来说都是严重的事件。实时自动且准确的跌倒检测系统可以在及时的药物治疗中发挥重要作用，最终有助于减少伤害和并发症。在本文中，我们提出了一种快速且更准确的实时系统，可检测监控摄像机拍摄的视频中的人跌倒。提出了新的基于时间和空间方差的特征，这些特征包含了人的有区别的运动、几何方向和位置。这些特征与 J48 和 Adaboost 分类器的集成学习策略提升一起使用。实验是在包括（）和（）在内的公开标准数据集上进行的，分别实现了 99.2%、99.25%和 99.0%的准确率。与九种最先进方法的比较表明，该方法在两个数据集上都具有有效性。
