Developed a Deep Learning Model for Automated Hailstorm Damage Detection in Automobiles of Different Makes and Models

The Need

Our Customer, a leading automobile insurance company based in Europe was looking for the development of a solution for automated hailstorm damage detection.

Our Solution

• To meet the above requirement, we have developed and deployed an advanced NN model to classify dents caused by hail-storm along with body panels for different automobile makes and models.
• We have leveraged a 2D model for the solution.
• Many challenges were overcome as:
  • Detected dents accurately while reducing false positives like an actual gap between the doors or curves of panel design
  • Detect small hailstorm dents which could be only a few pixels in the image, while noise should not be classified as false positives
• YOLOv3 with improved FPN was selected because
  • Its feature extraction capability does not let small features vanish as we go to deeper layers and
  • At the same time, it can improve speed and accuracy for small dent detection on low resolution images
• Multiple alternate techniques were used to improve small feature detection like:
  • Change the anchor size – By explicitly providing the network with information about the size of objects by using relevant anchor size helps in improving small object detection 
  • Splitting image into tiles – As we reduce the size of image to fit the network say 448*448 of Yolo many small features will be lost . To avoid this, we split the images to preserve small objects.
  • Tap the network early – by detecting till where small objects were going, earlier tap points were added by reducing the layers 
• Using above techniques and customization of FPN, the accuracy of detection was improved compared to using normal networks. Apart from this many pre/post processing techniques were applied to the data to suit the problem

Tools & Technologies

• Advanced NN model
• YOLOv3 with improved FPN

Representative Images

The Model Architecture