3D object detection and pose estimation using RGBD cameras

3D object detection and pose estimation (ODPE) is an important area in computer vision, which has many real world applications such as robotics and augmented reality. Estimating an accurate pose from RGB cameras alone is challenging. Given the increased popularity of RGBD sensors, such as Microsoft Kinect, we propose a hybrid method for ODPE based on both RGB and depth (3D surface) information. The additional depth information is expected to provide significant improvements in both speed and accuracy of the resulting system. The system will be evaluated on robotics and augmented reality applications, which are areas of strategic importance for Epson and as well as areas of active research in academia.

Faculty Supervisor:

Sven Dickinson

Student:

Liwen Xu

Partner:

Epson Canada Ltd

Discipline:

Computer science

Sector:

Advanced manufacturing

University:

University of Toronto