General Hough transformation-based method for detecting position of traffic signal lamp

Abstract

The invention belongs to the technical field of digital image processing and pattern recognition and discloses a general Hough transformation-based method for detecting the position of a traffic signal lamp, which comprises the following steps: by taking an image sequence as input, calculating image gradient information by adopting a first-order differential operator on an image by using image gradation; establishing a traffic lamp shape describing function; defining mapping from an image point to the space of an accumulator; and searching the extreme value of the space of the accumulator to acquire the coordinates of the traffic lamp to provide positional information for traffic lamp state identification. The general Hough transformation-based method for detecting the position of the traffic signal lamp can cope with the significant change of illumination, is insensitive to the influence caused by image sampling color cast and can cope with the traffic lamp with various common shapes.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, in particular to a method for detecting the position of a traffic signal light in a video image. technical background [0002] With the continuous development of the economy, the urban population and the number of motor vehicles are increasing rapidly. The incidence of traffic accidents and the number of deaths due to traffic accidents every year are very alarming. One of the important reasons is that motor vehicle drivers drive illegally outside the sight of the traffic police. The situation is very common. In order to manage traffic more extensively and provide traffic police with off-site law enforcement capabilities, the electronic police system has emerged as an important component of the Intelligent Transportation System (Intelligent Transportation System). It realizes all-weather and large-scale management requirements for urban roads, and at the s...

AI Technical Summary

Problems solved by technology

These methods are very good at solving the factors of color instability. However, because standard two-dimensional geometric figures are used to describe the traffic light model, this is quite different from the traffic light imaging results in real scenes, and ultimately lacks practicability.

[0007] Traffic light detection is affected by illumination changes, color bias, and shape differences. Some current methods cannot achieve satisfactory accuracy in practical applications.

Images