Vehicle damages are increasingly becoming a liability for shared mobility services. A large number of handovers between drivers demands for an accurate and fast inspection system, which locates small damages and classifies these into the correct damage category. To address this, a damage detection model is developed to locate vehicle damages and estimate the repair cost estimation by using 3 models. The first model decides whether the car is damaged or not, the second model classifies the area where the damage is located and the third model identifies the intensity of the damage on the car. On the basis of the above three judgments, repair cost estimation is done using a specific algorithm.