Real-time 3D object detection and pose estimation from multiple cameras

The project aims to build a 3D object detection system by using a number of images from multiple cameras. The system will train on instances of objects to detect other instances of the same object. This means that if, for example, we want to detect a sphere, we will make the system learn how a sphere looks like by giving some example images. Now when the system encounters a new object which looks similar to the example images, the system will detect the new object to be a sphere. Similarly the system will train for detection of more complex objects. Another component of the system is pose detection which will detect the orientation of the object defected. This means if the object detected is a cylinder, the system will detect whether the cylinder is standing upright, lying horizontally or placed in some other orientation.

Intern: 
Amanjot Kaur
Faculty Supervisor: 
Dr. Sven Dickinson
Province: 
Ontario
Discipline: 
Program: