A critical element to enabling assisted-driving technologies is vision: the vehicle should be equipped with tools to observe, interpret, and process its surroundings. Based on the required level of driving automation, analysis can be performed at different granularities: nearby people and other vehicles can be detected up to pixel-level precision, coupled with information related to their distance from the car itself. Furthermore, adverse weather conditions are found to negatively affect both the aforementioned computer vision, as well as the human vision itself, therefore techniques for the digital removal of weather-related artifacts are also fundamental.
The talk will cover these and other topics, presenting current challenges and solutions from the point of view of computer vision and image processing.
On September 26th, in the INE auditorium, a lecture on "Computer vision for the analysis and processing of street scenes" was held with the participation of Dr. Marco Buzzelli, researcher at the University of Milano-Bicocca, Italy.
The lecture presented the challenges and current solutions from the point of view of computer vision and image processing.
Marco Buzzelli obtained his Bachelor's Degree and Master's Degree in Computer Science respectively in 2012 and 2014, focusing on Image Processing and Computer Vision tasks. He got his PhD in Computer Science in 2019 at the University of Milano – Bicocca (Italy), where he is currently employed as a post-doctoral researcher. His main topics of research include the characterization of digital imaging devices, and object recognition in complex scenes.
The session will be held at the INE Auditorium of NOVA IMS, located in Campus de Campolide, Lisbon.
Transports
Metro: S. Sebastião (Blue and Red Line); Praça de Espanha (Blue Line)
Carris: 701, 713, 716, 726, 742, 746, 756, 758, 770