The growth in the road networks in India and other developing countries have influenced the growth in transport industry and other industries, which depends on the road network for operations. The industries such as postal services or mover services have influenced the similar growths in these industries as well. However, the dependency of these industries is high on the road surface conditions and any deviation on the road surface conditions can also influence the performance of the services provided by the mentioned services. Nonetheless, the conditions of the road surface are one of the prime factors for road safety and number of evidences are found, which are discussed in subsequent sections of this work, that the bad road surface conditions are increasing the road accidents. Several parallel research attempts are deployed in order to find out, the regions where the road surface conditions are not proper, and the traffic density is higher. Nevertheless, outcomes of these parallel works are highly criticised due to the lack of accuracy in detection of the road surface defects, detection of accurate location of the defects and detection of the traffic density data from various sources. Thus, this work proposes a novel framework for detection of the road defect and further mapping to the spatial data coordinates resulting into the detection of the accident-prone zones or accident affinities of the roads. This work deploys a self-adjusting parametric coefficient-based regression model for detection of the risk factors of the road defects and in the other hand, extracts the traffic density of the road regions and further maps the accident affinities. This work outcomes into 97.69% accurate detection of the road accident affinity and demonstrates less complexity compared with the other parallel research outcomes