This project uses machine learning to detect various objects in a given floor plan using YOLOv5, a state-of-the-art object detection model, as well as OpenCV to detect basic shapes and circles. The input to the model is an image of the floor plan, and the output is a list of bounding boxes and class labels corresponding to the detected objects, as well as a visual representation of the floor plan with detected objects and shapes overlaid on top in a .svg file.
To use the object and shape detection model, simply run the detect.py script with the path to the floor plan image as the argument. The script will output the detected objects and shapes as well as the generated .svg file.
This machine learning model provides a powerful tool for architects, interior designers, and other professionals to quickly and accurately analyze floor plans and identify key features and design elements. The combination of YOLOv5 and OpenCV allows for comprehensive object and shape detection, while the .svg file output provides a clear visual representation of the floor plan.