As part of the people tracking from multiple cameras research, we track and analyze the behavior of players in team sports. This could be greatly enhanced by using 3D information provided by devices such as the Kinect. We now have an ongoing project aiming to merge the depth maps of multiple Kinects, and then estimate the positions of multiple people in a scene.
This semester project involves internal and external calibration of a Kinect, in order to know its position and orientation in a room. After having a working calibration tool, the second phase of the project is to make a publicly available web based interface for calibrating such cameras.
For 1 student.
Students should have experience in The student should have experience in C++ programming, in addition to PHP and MySQL.
30% Theory, 50% Implementation, 20% Practical experiments
For further information, send an e-mail regarding the project.
Contact: Horesh BenShitrit (office BC 307, tel 3 81 91).