Roadways_Material_detection Computer Vision Project

The project is centered around the task of detecting and classifying different types of roadways, particularly focusing on identifying anthracite and grey concrete surfaces, as well as concrete blocks commonly found within construction sites. This task is crucial for various applications, including autonomous navigation systems for vehicles and machinery operating in such environments.

To gather the necessary data for training and evaluation, a camera was mounted on a bulldozer to capture images of the surrounding environment. These images were then processed and annotated to create a comprehensive dataset suitable for machine learning tasks.

During the preprocessing stage, various techniques were applied to extract relevant features and labels from the raw image data. This involved segmenting the images to isolate different roadway types and concrete blocks, as well as removing any irrelevant background elements.

The resulting dataset was then divided into training, testing, and validation sets to facilitate the development and evaluation of machine learning models. These models are trained to recognize and classify different roadway types and concrete blocks accurately.

Ultimately, the goal of the project is to deploy a robust and reliable detection system that can accurately identify various roadway features in real-time, aiding in navigation and decision-making processes for vehicles and machinery operating in construction environments.