摘要
针对电梯门现有防夹保护装置的缺陷,提出了一种基于视频数据的防夹检测算法,用于在轿厢门区内检测物体;首先,采用改进的双边滤波方法滤除视频帧和背景图像中的噪声;然后,差分视频帧与背景图像,并采用极大熵粒子群算法来二值化差分图像;接着,将二值图像进行形态学滤波以检测出轿厢门区范围内的物体;最后,利用Surendra算法更新背景图像;实验结果表明,提出算法可以在轿厢门区范围内实时且准确地检测出物体,为电梯门防夹功能的改进提供了可靠的保障。
For the defects of the existing anti-pinch protection device,an anti-pinch detection algorithm is proposed to detect objects in the elevator door area.First,an improved bilateral filtering method is used to remove the noise of the video frame and background image.Then,a difference image of the video frame and the background image is calculated,and the maximum entropy particle swarm optimization algorithm is employed to obtain binary image of the difference image.Next,objects in the door area are detected from the binary image by morphology processing.Final,the Surendra algorithm is adopted to update the background image.Experimental results show that the proposed algorithm can detect objects accurately in the elevator door area.It provides a reliable guarantee for the improved anti-pinch function of elevator door.
引文
[1]高勇,屈名胜.电梯门系统的防夹保护分析[J].中国特种设备安全,2017,33(4):74-76.
[2]回晓明.对电梯防碰撞装置引起事故的思考[J].中国特种设备安全,2013,29(4):48-49.
[3]曾晰,赵国军,王渊平,等.一种基于图像识别技术的电梯门控方法[J].信息与控制,2011,40(2):243-247.
[4]程淑红,高许,程树春,等.基于计算机视觉的运动车辆检测[J].计量学报,2017,38(3):288-291.
[5]Wang M,Chen W,Li X D.Hand gesture recognition using valley circle feature and Hu’s moments technique for robot movement control[J].Measurement,2016,94:734-744.
[6]Feng D,Wenkang S,Liangzhou C,et al.Infrared image segmentation with 2-D maximum entropy method based on particle swarm optimization(PSO)[J].Pattern Recognition Letters,2005,26(5):597-603.
[7]Pham T X,Siarry P,Oulhadj H.Image Clustering Using Improved Particle Swarm Optimization[A].International Conference on Industrial Networks and Intelligent Systems.Springer[C].Ho Chi Minh City,Vietnam:,Springer,2017:359-373.
[8]Bana S,Kaur D D.Fingerprint recognition using image segmentation[J].International Journal of Advanced Engineering Sciences and Technologies,2011,5(1):12-23.
[9]Audebert N,Le Saux B,Lefèvre S..Segment-before-detect:Vehicle detection and classification through semantic segmentation of aerial images[J].Remote Sensing,2017,9(4):368-1-檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳檳18.
[10]董小舒,陈岗,卞志国.一种改进的基于混合高斯模型的运动目标检测方法[J].应用光学,2012,33(5):877-883.
[11]王敏,郑嘉豪,王金宝.基于DSP车辆视频检测背景更新算法[J].电子科技,2012,25(5):129-132.
[12]Cheon M,Lee W,Yoon C,et al.Vision Based Vehicle Detection System with Consideration of the Detecting Location[J].IEEE Transaction on Intelligent Transportation Systems,2012,13(3):1243-1252.
[13]王丹,刘怀.基于改进混合高斯模型的背景提取与更新[J].南京师范大学学报(工程技术版),2015,15(2):60-64.
[14]Wu W,Yang J,Xu Z.The detection algorithm of irregular dynamic objects[J].Multimedia Tools and Applications,2017,76(13):14599-14615.