Vehicle number and traffic flow speed based highway congestion detection method

Abstract

The invention provides a vehicle number and traffic flow speed based highway congestion detection method. The method comprises the steps of making statistics on a vehicle number; calculating a traffic flow speed; and according to the vehicle number and the traffic flow speed, judging a highway congestion state. According to the method, non vehicle characteristic points are not generated, most errors can be avoided, and only a certain vehicle (less than or equal to a threshold N) region is selected, so that the calculation amount is greatly reduced; and based on a TIDM8127 camera platform, the test rate of a 352x288 cif video reaches 15fps (frame per second), so that real-time accurate detection is realized.

Description

technical field [0001] The invention relates to the intelligent application field of video monitoring. Background technique [0002] By the end of 2014, the total mileage of expressways opened to traffic reached 112,000 kilometers, surpassing the United States to rank first in the world. In 2015, 23,300 kilometers of expressways (including local expressways) will be needed. Due to such a large mileage, real-time detection of expressway congestion caused by subsidence, landslides, vehicle accidents, etc. has become a difficult problem that expressway management departments and transportation departments are eager to solve. [0003] In the prior art, there are some methods for judging the vehicle congestion on the expressway, for example, using the method of separating the foreground and the background, extracting the vehicles on the expressway, judging the congestion, or directly using the method of subtracting two frames; GMM background modeling is used, and the vehicle inf...

AI Technical Summary

Problems solved by technology

The general processing method of detecting the speed of traffic flow through video is to use trajectory analysis, but because trajectory tracking can only describe the movement trend of the target, it is not accurate enough to describe the vehicle speed

Another processing method is to use the optical flow field of the entire image to obtain it. The entire algorithm needs to calculate a large image area, resulting in a large amount of calculation, slow speed, and is susceptible to interference from the optical flow field of non-vehicle parts, such as roadbeds, Barrier etc.

Images