Vehicle speed real-time measurement method based on video processing

Abstract

The invention discloses a vehicle speed real-time measurement method based on video processing. An object on a pavement is converted into a pavement coordinate system (x,z) defined in the descriptionfrom a video image coordinate system (u,v) defined in the description, wherein a is the distance between two parallel lane lines in the pavement coordinate system, b is the length of a lane line in the pavement coordinate system, v is v-axis coordinates of a vanishing point in the video image coordinate system, uleft and uright are intersection point coordinates of the two parallel lane lines on the pavement and a u axis in the video image coordinate system respectively, and v1 and v2 are v-axis coordinates of the two ends of the same lane line in the video image coordinate system respectively; and the speed of the moving object on the pavement can be obtained by dividing a coordinate moving distance after the same moving object in two adjacent frames of video images is converted to the pavement coordinate system by a time difference between the two adjacent frames of the video images. According to the method, a perfect existing road traffic video monitoring network in china is used asan original data source to implement automatic, convenient and accurate vehicle speed real-time measurement.

Description

technical field [0001] The invention relates to the technical field of traffic management. More specifically, the present invention relates to a method for real-time measurement of vehicle speed based on video processing. Background technique [0002] The traffic management system is an effective means to control traffic congestion, and has important application prospects in many aspects such as traffic flow control, driving efficiency improvement, traffic accident risk reduction, energy saving and emission reduction. During the operation of this system, important traffic parameters such as vehicle speed and flow at each point in the road network need to be collected in real time. At present, the main means of collecting such data include induction coil detection, laser detection, radar detection and so on. The induction coil needs to be buried underground, and both construction and maintenance require excavation and reconstruction of the road surface, so the cost is high,...

AI Technical Summary

Problems solved by technology

The induction coil needs to be buried underground, and both construction and maintenance require excavation and reconstruction of the road surface, so the cost is high, and the maintenance process will block normal traffic. In addition, the service life of the induction coil is inversely proportional to the average traffic flow. In recent years, the explosive growth of highway traffic has had a huge impact on the service life of induction coils, further reducing its cost performance and product competitiveness.

Laser speed measurement has a high probability of false detection and missed detection due to low laser divergence, and laser speed measurement has a certain risk of eye injury to the drivers and passengers of the vehicle

The current popular radar speed measurement generally needs to limit the movement direction of the speed measurement object (the radar wave and the movement direction need to be less than 15 degrees) to ensure measurement accuracy. In addition, radar speed measurement is often affected by similar radio frequency bands (such as vehicle-mounted vehicles installed to avoid speed measurement radar) Radar interference equipment) or the interference of radar waves reflected from other vehicle surfaces adjacent to the test object, resulting in missed or false detections

Finally, there is a common defect in the above three speed measurement methods, that is, none of them can directly record the identity of the speed measurement object. Therefore, when the identity of the speed measurement object needs to be determined, it is necessary to install additional high-speed camera equipment to simultaneously capture the speed measurement objects one by one. , which not only significantly increases the complexity and cost of use of these two speed measurement methods, but also has a certain negative impact on their reliability

Images