This report proposed a new adaptive approach for segmentation of traffic signs in different conditions and countries for the Intelligent Transportation Systems (ITS) using Kohonen’s Self-Organizing Maps (SOM). HSV colour space, which is considered as stable, is used for the training of the SOM network. The main concentration of the report is red, blue and yellow colours. Search boundary values for these colours are obtained after research on the traffic sign images in different conditions. The dynamic segmentation is done by BMU’s obtained with SOM for the test image close to the desired colours in the search boundary in traffic sign images and discarding the unwanted areas. The image segmented by Adaptive Segmentation Algorithm is passed to the Region Growing Algorithm (RGA) which removes additional unwanted areas from the segmented region. Multistage Median Filter is then applied to remove the salt and pepper noise from the segmented image to give the final segmented image. The Adaptive algorithm designed is giving promising results for the segmentation of these colours in the traffic signs for different environmental conditions such as fog, highlight, bad lighting, rainfall, snowfall and other conditions such as faded and blurred images. A good improvement of 73% is observed in the faded signs as compared to 53.3 % of the Shadow and Highlight Invariant Algorithm. The adaptability of the system is evident from the segmentation of the traffic sign images from various countries where the result is 100 % for 6 out of 9 countries. The algorithm is giving very good results for the blue and yellow colours of traffic signs as well reflecting its powerful nature.