Predictive parsing method for track of vehicle

Abstract

The invention discloses a predictive parsing method for track of vehicle, and the method comprises the steps as follows: obtaining the original video of the camera, having the information of the license plate number and recording the time of real time; obtaining the place point set of the target vehicle during the inquiring time region, calculating the average time interval of two adjacent place points and obtaining the best sub way of the adjacent place points, connecting to the best sub way for outputting predictive track. The predictive parsing method for track of vehicle fuses the surveillance video, information of the license plate number, time information and city topology for rationally forecasting the track of vehicle through the incomplete and discrete data; the video content analysis of the method is executed by each intelligent camera, the server pressure is reduced, the processing speed is fast; the camera sends the information of the license plate number to the server, the network cost is small and the transmission speed is fast.

Description

technical field [0001] The invention relates to the field of intelligent traffic monitoring, in particular to a vehicle track prediction and analysis method. Background technique [0002] The scale of the city is constantly increasing, and the number of vehicles is constantly increasing, and the resulting traffic problems are becoming more and more serious. At present, most traffic problems are collected by cameras, and the current smart cameras have reached a certain level of imaging and computing capabilities, so they can complete many basic analysis tasks, such as target recognition, vehicle classification, Pedestrian detection and more. [0003] Although smart cameras can provide many precious raw materials, the current monitoring system only provides very simple applications or services, such as playback video, vehicle counting or vehicle violations of a certain camera. However, there are still a large amount of valuable information stored in the hard disk, such as ma...

AI Technical Summary

Problems solved by technology

[0009] In order to solve the problem that the vision-based and GPS-based methods in the prior art are not suitable for vehicle trajectory prediction and cannot fuse discrete and incomplete information, the present invention provides a vehicle trajectory prediction and analysis method, which solves the problem of vehicle trajectory prediction in intelligent transportation. prediction problem

Images