The population in Barcelona has almost doubled over the past 50 years, however the city size remains quite unchanged. How can we then accommodate for the urban infrastructure required by a modern and growing society? We decided to look at human mobility to try to find out which spaces humans are occupying, and more importantly which spaces they aren't. Obviously human occupancy is only a one aspect to take into account in city planning among many others, but our project aimed to focus on this one variable by tackling this problem using computer vision to detect, track and record human movement in a city, and introduce urban utility where space can be found.

Using the YOLOv4 Convoluted Neural Network for real-time object detection w/ DeepSORT for identification & tracking, we recorded pedestrian paths & used satellite data to homographize those coordinates & generate a 2D occupancy grid.

We also generated a 3D point cloud and mesh of the space using photogrammetry and LIDAR scanning, then performing point cloud segmentation we can obtain the different features such as the ground, walls and trees using Metashape & Open3D in python.
Finally we created an algorithm in Grasshopper to populate those voids with urban furniture and greenery.