基于机器视觉技术的电梯空间超载检测方法

传统电梯轿厢通常采用称重式方法来检测其超载状况,导致电梯运行过程中存在不必要的停靠,从而增加电梯能耗及降低运行效率.基于机器视觉技术改进传统的电梯超载检测方法,提出了一种新型的空间超载检测方法.首先,采用中值滤波消除电梯视频图像噪声;然后,运用最大类间方差法(又称OTSU算法)进行图像前背景分离,并采用改良的形态学方法将其处理为二值图像;最后,计算空间占有率.通过仿真试验对所提方法进行验证,结果表明该方法能更准确地判断电梯是否超载,减少电梯不必要的停靠次数,进而节约能源及提高效率.

Elevator Space Overload Detection Method Based on Machine Vision Technology

The weighing method is usually used to detect the overload condition by the traditional elevator car. It may lead to unnecessary stops of the elevator during the operation, which could increase the energy consumption and reduce the operation efficiency. A novel elevator space overload detection method was proposed based on the machine vision technology to improve traditional methods. Firstly, the elevator video image noise was eliminated by the method of median filter. Secondly, the maximum between-class variance (also known as OTSU) algorithm was used to separate the foreground and background, and then the improved morphology method was used to convert the image to the binary one. Finally, the space occupancy rate was calculated. The proposed method was verified by simulation experiments. Simulation results show that the method can make the elevator overload judged more accurately and make the unnecessary stopping times reduced, which can contribute to the energy conservation and efficiency improvement.