Roadside vehicle parking behavior detection method based on high-order camera

Abstract

The invention discloses a roadside vehicle parking behavior detection method based on a high-order camera, and belongs to the field of roadside vehicle parking recognition. The method solves the problems of imprecise vehicle detection and high error correction cost of a parking space-dominated parking condition judgment method at present, and comprises the following steps: firstly, defining a parking space frame in a fixed camera picture, wherein the parking space frame represents a parking area; detecting and judging whether a moving object exists or not for each frame of image in the subsequent images; judging whether a moving frame and the parking space frame are overlapped or not, judging whether the moving object is a vehicle or not if the moving frame and the parking space frame areoverlapped, and acquiring a real outline of the moving object if the moving object is the vehicle, recording a moving track of the moving object by utilizing a tracker, and judging a vehicle behaviorby utilizing the overlap ratio of the real outline and the parking space frame and the moving track; otherwise, ignoring the frame of image; according to the method, the roadside vehicle parking condition can be judged more precisely, and the error correction cost is low.

Description

technical field [0001] The invention relates to the field of roadside vehicle parking recognition, in particular to a method for detecting roadside vehicle parking behavior based on a high-position camera. Background technique [0002] With the growth of vehicles, there are often many parking spaces on the roadside of urban streets. At present, parking fees are mainly collected manually. A toll collector is needed for a section of the street. Toll collection alone requires a lot of human resources. At present, the automatic recognition of urban street parking based only on image information is not very mature. There are two main types: the first type is to use the yolo deep learning model to track the vehicle appearing in the video, when the coordinates of the vehicle in the video After the coordinates of the parking space set in advance coincide to a certain extent, it is judged that the vehicle is entering, and the vehicle is judged to be leaving in the same way. Using thi...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for detecting parking behavior of roadside vehicles based on a high-position camera, which can solve the problems of inaccurate vehicle detection and high cost of error correction in the current parking situation judgment method dominated by parking spaces

Images