CNN based Tyre Life Prediction and Defect Identification System

The only part of the vehicle in contact with the road is the tyre. The tyre tread depth has a significant impact on the vehicle's braking ability and should be checked on a regular basis for driving protection. Slippage, a longer stopping time, and even flat tyres are all symptoms of worn tyres, which can lead to a car accident. If there is an automated inspection method that will allow the vehicle users to monitor their tyre life with their own hands instead of getting the vehicle to the garage spending time to diagnose it, resolving such types of the defect will boost the confidence while drive and saves significant money by extracting the maximum out of the tyres without compromising on safety. The prediction involves capturing the image of the thread section and sidewall of the tyre to be predicted. Then, the image will be processed to extract the thread and wall condition from an image for defect identification and to further improve the result and life predictions the vital information inputs are taken from the user through a mobile app. The proposed research work utilizes the CNN based prediction algorithm in order to leverage the best prediction result and recommendations to improve the tyre life.