Automated and Distributed Street Parking Slot Detection
Mentor: Luis Miguel Bergasa Pascual
Email: luism.bergasa@uah.es
Phone: (+34) 918856569
University: Universidad de Alcalá
Partner Host Institution: Pixcellence
- 2nd year of applied research compulsory This research line has been developed by or together with Pixcellence.The second year of applied research in Pixcellence is compulsory under this line.
Keywords: Parking slot detection, semantic segmentation, visual odometry, distributed SLAM, mobile app

Automated and Distributed Street Parking Slot Detection

The goal of the proposed research line is to develop an automated parking detection system based on computer vision techniques distributed in a mobile application across several users, together with a centralized server that maps the city parking slots and their availability by using user’s data. The server would construct a complete map view of the street parking slots in the city by making use of the processed camera information from the user’s phones, which is geolocated to the user’s location by using GPS and visual odometry. The server would continuously feed the built map and information about available spots to the users, so they can take advantage of this data to find a parking slot much faster. Such a system could significantly lower the time that drivers spend looking for parking slots, directly reducing the associated costs of parking and congestion in cities.
Developing such a project would require extensive research in several Computer Vision fields such as Vehicle Detection, Parking Slot Detection, Semantic Segmentation, 3D Camera Transformations, Visual Odometry, Simultaneous Localization and Mapping and others, along with other technical knowledge in the areas of frontend (mobile) and backend development.
The Robesafe group from UAH and Pixcellence will collaborate in this project, UAH as the academic institution and Pixcellence as the industrial partner. Both institutions have wide experience in computer vision techniques and smart city applications. Robesafe has carried out research in many vision-based solutions such as a fully electric autonomous car that has a complete understanding of the surrounding scene, a smartphone application called DriveSafe to evaluate driver behaviours on the road and warn about dangerous situations, and a smart parking system that is currently working in Guadalajara.

Collaboration with Pixcellence
Pixcellence has developed and is currently developing many projects ranging from Parking slot detection from a parkimeter’s view, Overhead parking detection, Person Detection, House alarms/doorbells and other embedded analytics solutions. Additionally, Pixcellence has provided complete hardware and software designs to large companies in the US such as a day/night vision doorbell for SkyBell and the camera module that Lytx is using for their widespread fleet management tool DriveCam.

Departament: Electronics
Research Group: Robotics and e-Safety Unit
More Information: www.robesafe.uah.es, http://pixcellencetech.com/
http://www.robesafe.uah.es/personal/bergasa/
Relevants projects on the area:
Relevants publications on the area: 1.- L. M. Bergasa, D. Almería, J. Almazán, J. J. Yebes and R. Arroyo,"DriveSafe: an App for Alerting Inattentive Drivers and Scoring Driving Behaviors", in IEEE Intelligent Vehicles Symposium (IV), pp. 240-245, Dearborn, Michigan (United States), June 2014. BEST POSTER AWARD.
2.- E. Romera, L. M. Bergasa and R. Arroyo, "A Real-time Multi-scale Vehicle Detection and Tracking Approach for Smartphones", in IEEE Intelligent Transportation Systems Conference (ITSC), pp. 1298-1303, Las Palmas, Canary Islands (Spain), September 2015.