[Automatic Systems 2] Person detection with laser scanners
Automatic Systems has developed an extensive portfolio of turnstiles as shown on AS website. One of the main issues in the high-security market is to accurately detect and count persons in the turnstile. The detection method must be resilient to a wide range of lighting conditions, person morphologies, person behaviors, frauds,…The current detection systems use discrete IR cells.
The aim of the proposed thesis is to develop a new detection system using low-cost LIDAR or laser scanner. For example, sensors developed by BEA could be used (see BEA website for further details).
The main work packages are:
- Review and select the sensors,
- Develop a test bench. The objective of the test bench is to record data on a set of real-life usage patterns. The test bench will be built by the Automatic Systems prototyping team,
- Develop an algorithm to reconstruct 2D images from the sensors data,
- Develop the detection SW using tracking algorithms,
- Evaluate the detection performances and compare to the current system.