Road jamming detection method and device

Abstract

The invention discloses a road jamming detection method and device. The method comprises steps of acquiring monitoring video data; classifying and preprocessing the monitoring video data so as to obtain processed data; carrying out iteration trainings so as to obtain a lane detection model and a vehicle detection model; obtaining vehicle information in a to-be-identified image; integrating the lane information and the vehicle information so as to obtain a target image; for each lane in the target image, calculating a lane occupation rate corresponding to the to-be-identified image; and according to the corresponding relation between the lane occupation rate corresponding to the to-be-identified image and a preset threshold vale, and the corresponding relation between the preset threshold value and the jamming grade, acquiring the jamming grade corresponding to the to-be-identified image. According to the invention, road jamming detection is quite accurate.

Description

technical field [0001] The present invention relates to a congestion detection method and device, more particularly to a road congestion detection method and device. Background technique [0002] With the improvement of my country's economic development level, more and more families choose to buy cars for travel. With the increase in car sales, road congestion has become a headache for drivers. Therefore, how to detect congested road sections is a technical problem that needs to be solved urgently. [0003] At present, the following steps can be used to obtain the congestion status of the road: first process the acquired video image of the current road to obtain the background and foreground of the current road. Carry out modeling for each pixel; classify vehicles and road surfaces; calculate the connected areas of the foreground, and judge whether the size of each connected area is smaller than the set value, and if so, classify the corresponding pixels into the background...

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, the width of the vehicle is smaller than the width of the lane. If the occupancy rate of the road is calculated only based on the pixels of the vehicle, the calculation of the occupancy rate of the road will not be accurate enough, which will lead to inaccurate road congestion detection.

Images