Method and system for automatically identifying urban traffic accident

Abstract

The invention belongs to the field of intelligent traffic video image monitoring and video image analysis, and in particular relates to a method and a system for automatically identifying an urban traffic accident. The method for automatically identifying the traffic accident comprises the following steps of: acquiring an urban road video image sequence; performing foreground vehicle separation based on a mixed Gaussian background model; performing a multi-target vehicle tracing algorithm based on a Camshift algorithm and a kalman filtering combination; extracting traffic accident determiningparameters such as speed variation, horizontal position variation, vertical position variation, moving direction variation and the like; and proposing a multi-featured weighted fusion automatic accident identification algorithm. Traffic accident information is transmitted to a traffic control center in time by a transmission unit and a display unit, so that the traffic accident can be quickly treated, an effective and flexible road traffic monitoring means with high cost performance is provided for traffic management, and new thought is provided for the development of a high-efficiency intelligent video traffic accident system.

Description

technical field [0001] The invention relates to the fields of intelligent traffic video image monitoring and video image analysis, in particular to a method and system for automatic identification of urban traffic accidents. Background technique [0002] In recent years, with the rapid development of China's economy, urban infrastructure construction and the number of motor vehicles have achieved rapid development, which has brought great convenience to people. At the same time, traffic congestion and the frequency of traffic accidents have also increased, which has affected to people's production, life and other aspects. According to statistics, in 2009 alone, there were more than 23,000 road traffic accidents across the country, resulting in 67,000 deaths, 27,000 injuries, and direct property losses of 910 million yuan. The study of traffic accidents is becoming an extremely important research field in modern traffic. Traffic video research based on video image technolog...

AI Technical Summary

Problems solved by technology

However, due to its immature technology, it is easily affected by various factors, so the false detection rate and missed detection rate are relatively high.

At present, urban traffic accidents based on video detection technology are often used as a part of traffic event detection. Simply using a single parameter such as speed and lane occupancy rate cannot identify traffic accidents well, nor can it realize automatic alarms.

Images