This paper introduces a novel moving vehicle color
recognition method. By processing videos recorded by monocular
camera on traffic, we get single color image of vehicles which are
crossed the traffic in any direction. First, paper employed a H-S
two dimension histogram method to detect the color of the
vehicles, and distinguish red, yellow, green and blue four color
vehicles. Due to deal with the vehicles that do not satisfy above 4
colors, Regional Color Judgment method is proposed. This
method consists of the following five steps: Firstly, position the
color detection region by identifying the travelling direction of
the vehicle. Then pick out the candidate color extraction region
used to vehicle recognition. At last extract the color of the
candidate region and match the color with the templates we
predefined, the color of the best fit template is the color of the
vehicle.
This paper introduces a novel moving vehicle color
recognition method. By processing videos recorded by monocular
camera on traffic, we get single color image of vehicles which are
crossed the traffic in any direction. First, paper employed a H-S
two dimension histogram method to detect the color of the
vehicles, and distinguish red, yellow, green and blue four color
vehicles. Due to deal with the vehicles that do not satisfy above 4
colors, Regional Color Judgment method is proposed. This
method consists of the following five steps: Firstly, position the
color detection region by identifying the travelling direction of
the vehicle. Then pick out the candidate color extraction region
used to vehicle recognition. At last extract the color of the
candidate region and match the color with the templates we
predefined, the color of the best fit template is the color of the
vehicle.
การแปล กรุณารอสักครู่..
![](//thimg.ilovetranslation.com/pic/loading_3.gif?v=b9814dd30c1d7c59_8619)