Electronic Information Communication Research Center, Pukyong National University, Busan 608-737, Korea.
Sensors (Basel). 2012;12(1):573-84. doi: 10.3390/s120100573. Epub 2012 Jan 5.
Vision-based abnormal event detection for home healthcare systems can be greatly improved using visual sensor-based techniques able to detect, track and recognize objects in the scene. However, in moving object detection and tracking processes, moving cast shadows can be misclassified as part of objects or moving objects. Shadow removal is an essential step for developing video surveillance systems. The goal of the primary is to design novel computer vision techniques that can extract objects more accurately and discriminate between abnormal and normal activities. To improve the accuracy of object detection and tracking, our proposed shadow removal algorithm is employed. Abnormal event detection based on visual sensor by using shape features variation and 3-D trajectory is presented to overcome the low fall detection rate. The experimental results showed that the success rate of detecting abnormal events was 97% with a false positive rate of 2%. Our proposed algorithm can allow distinguishing diverse fall activities such as forward falls, backward falls, and falling asides from normal activities.
基于视觉的异常事件检测在家庭医疗保健系统中可以得到极大的改善，使用基于视觉传感器的技术能够在场景中检测、跟踪和识别物体。然而，在移动目标检测和跟踪过程中，移动的遮挡物可能会被错误地分类为物体或移动物体的一部分。阴影去除是开发视频监控系统的重要步骤。主要目标是设计新颖的计算机视觉技术，以便更准确地提取物体，并区分异常和正常活动。为了提高物体检测和跟踪的准确性，我们采用了所提出的阴影去除算法。提出了基于视觉传感器的异常事件检测方法，利用形状特征变化和 3-D 轨迹来克服低跌倒检测率的问题。实验结果表明，异常事件的检测成功率为 97%，假阳性率为 2%。我们提出的算法可以区分不同的跌倒活动，如向前跌倒、向后跌倒和向侧面跌倒，以及正常活动。
