Detecció i tracking de vianants en la mobilitat urbana des de diferents perspectives.
Elbaz Trojman, Míriam · UPCommons institutional repository (Universitat Politècnica de Catalunya) · 2023
This thesis is about exploring the possibility to make a system that could be implemented in e-scooters to help their users to use them in a secure manner. The objective of this thesis is to find if it is possible to train a detector to distinguish between pedestrians, bikes and e-scooters and being able to track them. I trained an object detector that classifies between the 3 categories mentioned above and used a multi-object tracking algorithm. The results from the Yolov5 detector results were 0.97 of map0.5 and 0.80 of map0.5:0.95, which for this case are good results. The result from the StrongSORT tracker regarding the HOTA metric was 90.87. We can conclude that the results are good. It is possible to detect, classify and track pedestrians, cyclists, and e-scooter users, but the time taken is too large for an implementation in real-time.