A video analysis method to estimate the distance between the left and right elevator doors when they are closing or opening is proposed in this paper. Firstly, we load the monitoring videos of the elevator door. Next, each frame of the video is converted to a grayscale image. Then we use the edge detection operator to get a binary image which is converted by a grayscale image. The binary image is clearly showing the edge of objects. Finally, we find the line representing the edge of the elevator door and estimate the distance. In the process of detecting the edge, we use the Canny operator to detect the edge in video. We use the genetic algorithm to optimize the two parameters in the Canny edge detection operator. Setting a suitable fitness function is the key to optimize the parameters. As a result, for estimating the distance, the average of estimating the correct rate is up to 97.8%.
Analysis of Dynamic Movement of Elevator Doors Based on Camera Videos
Smart Innovation, Systems and Technologies
Advances in Smart Vehicular Technology, Transportation, Communication and Applications ; Kapitel : 2 ; 9-18
2021-07-02
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch