A vehicle speed identification method based on vehicle body feature point location

Abstract

The invention discloses a vehicle speed identification method based on vehicle body feature point positioning, and provides a vehicle speed identification method based on vehicle body feature point positioning and inter-frame interpolation. The vehicle speed identification method comprises the following steps of video analyses, feature point extracting and positioning, inter-frame interpolation and speed calculations. Vehicle body feature points are extracted through an edge detection algorithm based on Sobel operators, and therefore errors caused by manual extracting are avoided. When the vehicle speed is calculated, two feature points are precisely determined through the time interval of fixed points in an inter-frame interpolation mode to avoid calculation errors caused by frame rates. Furthermore, feature point positioning precision and time interval calculation precision are improved through the vehicle speed identification method, and the vehicle speed of a vehicle within a video range at any time can be acquired through the vehicle speed identification method and a continuous vehicle speed variation curve can be drawn at the same time; accordingly, vehicle running state analyses and accident process rebuilding are facilitated.

Description

technical field [0001] The invention belongs to the field of vehicle speed identification based on video images, and relates to a method for extracting vehicle body feature points, in particular to a vehicle speed identification method based on vehicle body feature point positioning. Background technique [0002] Video surveillance is more and more used in traffic control and social security. Using video images to identify the speed of vehicles in traffic accidents has become a key link in traffic accident investigation. Among them, calculating vehicle speed based on body feature points is one of the most commonly used vehicle speed identification methods. The basic idea is: select two feature points on the vehicle to be identified, and observe the time interval Δt between the two feature points passing through a certain point i in space i , this time interval is the frame number difference / frame rate when two feature points pass through a fixed point. Measure the horizonta...

AI Technical Summary

Problems solved by technology

[0003] The above-mentioned vehicle speed identification method based on body feature points is simple and feasible, but it has the following two defects: (1) The feature point extraction will lack accuracy due to the subjective arbitrariness of the extractor, and large pixel errors will be generated here

(2) The frame rate is not infinite, there is always a time interval between frames, and the moment when the feature point coincides with the fixed point is very likely to appear in the inter-frame interval, resulting in the time interval Δt between the two feature points passing the fixed point i It cannot be calculated accurately, resulting in errors caused by frame rate

Images