A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Forward rotation avoidance type three-dimensional parking obstacle avoidance method and system based on machine vision
The invention discloses a forward rotation avoidance type three-dimensional parking obstacle avoidance method and system based on machine vision, and the method comprises the steps: collecting an image containing a garage bottom plate and a target detection object, carrying out the recognition of the garage bottom plate and the target detection object in the collected image through a YOLO target detection algorithm, and obtaining the position information of the garage bottom plate and the target detection object; processing the image of the garage bottom plate by adopting an adaptive histogram equalization algorithm, performing edge detection to draw the contour of the garage bottom plate, obtaining four points in the contour through an iteration method, calculating a perspective transformation matrix according to the four points, and obtaining the contour of the garage bottom plate according to the perspective transformation matrix; the method comprises the following steps of: obtaining a linear unary equation of six line segments for distinguishing an equipment area and an operation area in an obstacle avoidance area through a formula of a perspective transformation matrix, calculating a y value of a point by taking the dead center point of a target detection object as a main judgment point, comparing the y value with an actual y value of the dead center point, and judging the relationship between the target detection object and the obstacle avoidance area.
本发明公开了基于机器视觉的前移旋转避让型立体停车避障方法及系统，方法中采集包含车库底板和目标检测物的图像，通过YOLO目标检测算法对采集的图像中的车库底板和目标检测物进行识别，获取车库底板和目标检测物的位置信息；采用自适应直方图均衡算法对车库底板的图像进行处理，进行边缘检测画出车库底板的轮廓，通过迭代方法获取轮廓中的四个点，根据四个点计算透视变换矩阵，再通过透视变换矩阵的公式逆推得到避障区域的区分设备区与运行区的6条线段的一元一次方程，以目标检测物的正中心点为主要判断点，计算该点的y值，然后与该正中心点的实际y值进行对比，判断目标检测物与避障区域之间关系。
Forward rotation avoidance type three-dimensional parking obstacle avoidance method and system based on machine vision
The invention discloses a forward rotation avoidance type three-dimensional parking obstacle avoidance method and system based on machine vision, and the method comprises the steps: collecting an image containing a garage bottom plate and a target detection object, carrying out the recognition of the garage bottom plate and the target detection object in the collected image through a YOLO target detection algorithm, and obtaining the position information of the garage bottom plate and the target detection object; processing the image of the garage bottom plate by adopting an adaptive histogram equalization algorithm, performing edge detection to draw the contour of the garage bottom plate, obtaining four points in the contour through an iteration method, calculating a perspective transformation matrix according to the four points, and obtaining the contour of the garage bottom plate according to the perspective transformation matrix; the method comprises the following steps of: obtaining a linear unary equation of six line segments for distinguishing an equipment area and an operation area in an obstacle avoidance area through a formula of a perspective transformation matrix, calculating a y value of a point by taking the dead center point of a target detection object as a main judgment point, comparing the y value with an actual y value of the dead center point, and judging the relationship between the target detection object and the obstacle avoidance area.
本发明公开了基于机器视觉的前移旋转避让型立体停车避障方法及系统，方法中采集包含车库底板和目标检测物的图像，通过YOLO目标检测算法对采集的图像中的车库底板和目标检测物进行识别，获取车库底板和目标检测物的位置信息；采用自适应直方图均衡算法对车库底板的图像进行处理，进行边缘检测画出车库底板的轮廓，通过迭代方法获取轮廓中的四个点，根据四个点计算透视变换矩阵，再通过透视变换矩阵的公式逆推得到避障区域的区分设备区与运行区的6条线段的一元一次方程，以目标检测物的正中心点为主要判断点，计算该点的y值，然后与该正中心点的实际y值进行对比，判断目标检测物与避障区域之间关系。
Forward rotation avoidance type three-dimensional parking obstacle avoidance method and system based on machine vision
基于机器视觉的前移旋转避让型立体停车避障方法及系统
ZHANG BITAO (author) / HUANG LIANRONG (author)
2023-09-12
Patent
Electronic Resource
Chinese
IPC:
G06T
Bilddatenverarbeitung oder Bilddatenerzeugung allgemein
,
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
/
E04H
Gebäude oder ähnliche Bauwerke für besondere Zwecke
,
BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES
/
G06V
/
G08G
Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs
,
TRAFFIC CONTROL SYSTEMS
Forward rotation non-avoidance mechanical parking control system and control method
| European Patent Office | 2021
| European Patent Office | 2020