Revision history [back]

I am pretty new to open CV.My project involves identifying traffic signal status in pedestrian crossing,Its either a walk symbol in green,red or yellow.In some places its also text like "WALK" and "DONT WALK". I need to identify this using open CV .My initial thoughts are extracting the highest RGB value pixels, then using clustering algorithm to group the pixels to a cluster, then use template matching to filter out other clusters and finally find the color the cluster that has passed filtering. Is this an optimal way of doing? Or is there any other algorithm or approach I need to take in order to complete this with fast and accurate.Please help

I am pretty new to open CV.My project involves identifying traffic signal status in pedestrian crossing,Its either a walk symbol in green,red or yellow.In some places its also text like "WALK" and "DONT WALK". I need to identify this using open CV .My initial thoughts are extracting

Extracting the highest RGB value pixels, then using pixels. Using clustering algorithm to group the pixels to a cluster, then use cluster.
Using template matching to filter out other clusters and finally clusters.
Finally find the color the cluster that has passed filtering. filtering.

Is this an optimal way of doing? Or is there any other algorithm or approach I need to take in order to complete this with make the whole process fast and accurate.Please help