Real-time detection of people and bicycles in pedestrian crossings
Instant detection of people and bicycles in pedestrian crossings
Our interactive technological demonstration instantly detects people (and bicycles) at pedestrian crossings. The system enables fast detection with only a single camera aiming to alert only those drivers whose vehicles are approaching the crossing area (connected cars).
Analysis of pedestrian crossings areas
The system extracts a set of data and statistics from a video of a pedestrian crossing that helps cities manage mobility efficiently (number of people and bicycles crossing the area, the average/minimum/maximum time to cross the area, the average/minimum/maximum waiting time, etc.)
For instance, it allows the detection of:
- Very crowded hours may require police monitoring.
- Too short crossing intervals produced by too brief traffic light time
- Excessively long waiting times produced by a bad traffic light configuration
- Too many bicycles indicate the need for a bicycle lane.
These solutions are use cases developed by the CVC within the ‘FEMIoT: Connected Street Infrastructures’ project. FEMIoT is a project coordinated by i2CAT and co-funded by the European Regional Development Fund within the framework of the FEDER Operational Program of Catalonia 2014-2020, to foster collaboration and develop new projects based on the Internet of Things.
More information: https://femiot.cat