The invention discloses a truck overload detection method based on machine vision. The truck overload detection method comprises the steps of: extracting a hub area of a wheel, a hub outer contour of the hub area and circle center coordinates of the hub outer contour sequentially; extracting a wheel outer contour and a contour point set I, taking the circle center of the wheel hub outer contour as the circle center of the tire outer contour, and determining the tire radius; calculating the distance between each contour point of the contour point set I and the circle center of the tire, and putting the contour points of which the distances are smaller than the radius of the tire into a contour point set II; finding out a contour point p (x0, y0) of which the x coordinate is the same as the x coordinate of the circle center of the tire from a contour point set II, finding out a contour point of which the y coordinate is located in [y0-d, y0+d] from the contour point set II, and putting the contour point into a contour point set III; and traversing the contour point set III, obtaining the maximum value L of the distance between the two contour points, taking the ratio of the distance L to the tire diameter as a detection parameter, and if the detection parameter is greater than a set threshold, judging that the truck is overloaded. In addition, the arrangement position can be flexibly set according to requirements.
本发明公开了一种基于机器视觉的货车超载检测方法,包括:依次提取车轮的轮毂区域、轮毂区域的轮毂外轮廓及轮毂外轮廓的圆心坐标;提取车轮外轮廓及轮廓点集Ⅰ,将轮毂外轮廓的圆心作为轮胎外轮廓的圆心,确定轮胎半径;计算轮廓点集Ⅰ各轮廓点距轮胎圆心的距离,将距离小于轮胎半径的轮廓点放入轮廓点集Ⅱ;在轮廓点集Ⅱ中找出x坐标与轮胎圆心x坐标相同的轮廓点p(x0,y0),在轮廓集Ⅱ中查找y坐标位于[y0‑d,y0+d]的轮廓点,放入轮廓点集Ⅲ;遍历轮廓点集Ⅲ,获取两轮廓点间的距离最大值L,将距离L与轮胎直径的比值作为检测参数,若检测参数大于设定阈值,则判定该货车超载。实现货车超重的初步检测,此外设置位置可根据需求进行灵活性设定。
Truck overload detection system and method based on machine vision
基于机器视觉的货车超载检测系统及方法
2021-04-06
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Overload detection method and system for high-speed truck
European Patent Office | 2023
|Muck truck overload detection method and system based on intelligent network connection
European Patent Office | 2024
|