Detection and counting of pothole using image processing techniques

Pothole are the primary cause of accidents, hence identification and classification using image processing techniques is very important. In this paper image pre-processing based on difference of Gaussian-Filtering and clustering based image segmentation methods are implemented for better results. From the results the K-Means clustering based segmentation was preferred for its fastest computing time and edge detection based segmentation is preferred for its specificity. The main goal of this paper is to identify a better method which is highly efficient and accurate compared to the conventional methods. Different image pre-processing and segmentation methods for pothole detection where reviewed using performance measures.