Skip links

Dent Detection on vehicles due to Hailstorm

Client

Automative industry,Insurance Industry

Scroll down

Technologies used

Python

Tensorflow

Darknet

OpenCV

Challenges

Identify and localize small dents caused by hailstorm on vehicles for an Insurance application

All small dents had to be detected whereas an actual gap like between the doors or curves as part of panel design should not be misclassified

Detect small hailstorm dents which could be only a few pixels in the image, while noise should not be classified as false positives

Solutions

Develop and deploy an advanced NN model to classify dents caused by hailstorm

Choose a model whose feature extraction capability does not let small features vanish as we go to deeper layers

At the same time, it could improve speed and accuracy for small dent detection on low resolution images

Retrain the model whenever there is any misclassification or when a new dent shape is detected

Benefits

Accurate and automatic detection of dents

Since there is no manual intervention, this solution enables improved and high-speed insurance settlements without any frauds during hailstorm season