Illegal-parking vehicle and breakdown vehicle vision detection system based on deep convolution nerve network

Abstract

Provided is an illegal-parking vehicle and breakdown vehicle vision detection system based on deep convolution nerve network, comprising a camera disposed on a city road, a traffic cloud server, and aroad traffic event automatic detection system. In the system, various vehicles on the road can be extracted through deep convolution nerve network technology, and the optical flow method is adopted to calculate, identify and determine whether the vehicles are still or not. If a still vehicle is identified, and the rest time exceeds the parking time threshold value, the vehicle will be determinedas illegal parking. Means like WebGIS or broadcasting and road caution boards will be adopted for real-time report, so that the traffic police will rapidly arrange people to remove the traffic obstacles, and simultaneously remind the following vehicles of the accidents on the road in front of them. Accordingly, relevant measures will be taken to avoid secondary accident. The invention is advantageous in that robustness is quite good, and identification precision is quite high.

Description

technical field [0001] The invention relates to the application of artificial intelligence, convolutional neural network and computer vision in the detection of illegal parking and broken down vehicles, and belongs to the field of intelligent transportation. Background technique [0002] Today's traffic problems have become a global "urban common problem", and illegal parking is the main manifestation of the city's "traffic disease". The "cause" of illegal parking in cities stems from a variety of factors, and illegal parking and broken down vehicles directly affect the smoothness of the road and the safety of pedestrians. Illegal parking of vehicles has always been a persistent problem in traffic management. How to regulate the driver's driving behavior and conduct timely and accurate evidence collection and investigation of violations of traffic rules is a key to road monitoring. [0003] Statistical analysis of road traffic accidents shows that traffic events have the fo...

AI Technical Summary

Problems solved by technology

[0019] In order to overcome the disadvantages of poor robustness and low recognition accuracy of the existing detection methods for illegal parking and broken down vehicles, the present invention provides an illegal parking based on deep convolutional neural network with good robustness and high recognition accuracy. and visual detection system for broken down vehicles

Images