Monitoring method of lane space occupancy based on videos

Abstract

The invention discloses a monitoring method of lane space occupancy based on videos, comprising the following concrete steps: step 1: arranging an effective monitoring field of view, and acquiring basic data; step 2: carrying out nonlinear correction of a lane: calibrating the lane, computing the gradients of the upper bottom and the lower bottom of a calibrated trapezoid, computing the weight of each row in the calibrated trapezoid, carrying out curve fitting on the corrected weight, iterating and optimizing weight corrected parameters, and computing the actual length of the corrected calibrated trapezoid region lane, the fitting actual length obtained after curve fitting and the height of a triangle capable of being expressed by the inclination angles of the upper bottom and the lower bottom of the calibrated trapezoid region; and step 3: computing the space occupancy of the lane to obtain the actual value of the lane space occupancy. The method of the invention can effectively reduce the computing error of the lane occupancy since vehicles are big in a near place and are small in a far place in traffic video monitoring.

Description

technical field [0001] The invention belongs to the technical field of video monitoring, and relates to a video-based monitoring method for lane space occupancy. Background technique [0002] Traffic flow information statistics is a key link in the intelligent transportation system. Lane occupancy rate is an important indicator to measure traffic conditions in traffic flow information. Lane occupancy rate is divided into time occupancy rate and space occupancy rate. The time occupancy rate refers to the ratio of the cumulative time of vehicles passing through a section to the unit measurement time per unit time. The space occupancy rate refers to the ratio of the length of the road surface occupied by all vehicles on the known road section to the length of the road section measured at a certain moment. [0003] The traffic information counted by the time occupancy rate usually has problems in some extreme cases. For example, when the time occupancy rate is low, it may be be...

AI Technical Summary

Problems solved by technology

However, in the video surveillance mode, there will be a problem when using the space occupancy rate to calculate the lane occupancy rate, because the movement of a vehicle in the monitoring field of view, the lane with the same physical length, and the target vehicle with the same physical length will all be caused by The projection from the three-dimensional space to the two-dimensional plane has the problem of different lengths in different positions, that is, the distance from the lens is longer, and the distance is shorter.

In addition, the size of different vehicles driving on the road is usually different. Therefore, if the ratio between the length of the target extracted from the monitoring screen and the length of the road section is directly calculated, a large deviation will occur.

Images