Simplifying Tire Inspections Using Machine Learning

Client

Headquartered in Germany, our client is the research and development center for the world’s largest manufacturer of premium and commercial vehicles. The center focuses on research, IT engineering, and product development.

Industry

Automobile

Overview

As a critical component for vehicle performance and stability, automobile manufacturers implement specialized inspection processes to ensure the integrity and quality of tires. Frequent quality checks on aspects such as tread depth, sidewall texture, and rigidity help determine the quality of a tire. The tire inspection system enables tread depth measurement using a mobile application. A deep learning model based on Convolutional Neural Network (CNN) was implemented and trained on thousands of images. Deep learning and traditional computer vision approaches were used to develop a custom CNN architecture that rendered the desired accuracy in tread depth measurement.

Show More Show Less

Business Requirement

The application needed to:

Detect tread depth using images of the tire surface
Replace manual inspections with automated quality inspections

QBurst Solution

The solution measures the depth of tire treads using image processing for edge detection. Our data scientists trained the deep neural network to predict the relative depth of tires based on reference images. This proven approach in estimating measurements using a neural network helped implement a deep regression network.

Business Benefits

Automation resulted in reduced manual intervention and increased efficiency, with a renewed focus on productivity and product design
66% increase in accuracy and low defect rates resulted in reduced warranty claims and improved quality
Preventive maintenance enabled by real-time tire analysis and monitoring
Improved vehicle safety without requiring specialized operator training

Key Features

Custom CNN architecture development for depth detection using established architectures such as UNet and DenseNet as base
Proved the concept of high-quality monocular image depth detection on minute relative distances (in the range of millimeters)
Accuracy level of +/-1.5 mm on 90% of independent test images
APIs to reject images due to reasons such as insufficient tire surface, overexposure, and poor quality
Ability to acquire valid tire tread depth images from thousands of tire images

Technologies

TensorFlow
Pytorch
Numpy
Python
Django

Business Requirement

The application needed to:

Detect tread depth using images of the tire surface
Replace manual inspections with automated quality inspections

QBurst Solution

Business Benefits

Automation resulted in reduced manual intervention and increased efficiency, with a renewed focus on productivity and product design
66% increase in accuracy and low defect rates resulted in reduced warranty claims and improved quality
Preventive maintenance enabled by real-time tire analysis and monitoring
Improved vehicle safety without requiring specialized operator training

Key Features

Custom CNN architecture development for depth detection using established architectures such as UNet and DenseNet as base
Proved the concept of high-quality monocular image depth detection on minute relative distances (in the range of millimeters)
Accuracy level of +/-1.5 mm on 90% of independent test images
APIs to reject images due to reasons such as insufficient tire surface, overexposure, and poor quality
Ability to acquire valid tire tread depth images from thousands of tire images

Technologies

TensorFlow
Numpy
Django

Pytorch
Python

Download PDF

Cloud Enablement

Data & AI

Digitalization

End-to-End

SaaS

Simplifying Tire Inspections Using Machine Learning

Client

Industry

Overview

Business Requirement

QBurst Solution

Business Benefits

Key Features

Technologies

Business Requirement

QBurst Solution

Business Benefits

Key Features

Technologies

More Stories

Car Dealer Chatbot

Project Tracking Application

Social Media Analytics