Damien Jade Duff

Papers

Total Citations

H-Index

About

Damien Jade Duff is a researcher whose work sits at the intersection of computer vision, robotics, and physics-based simulation. His primary research areas include 3D object tracking, physical simulation for visual estimation, and the integration of perception with robotic manipulation planning. Duff’s most significant contribution is his pioneering approach to monocular 3D model-based tracking, where he demonstrated that incorporating physical models of object dynamics dramatically improves tracking robustness when traditional visual methods fail—particularly during fast motion or occlusion. His 2011 paper on this topic, "Physical simulation for monocular 3D model based tracking," has accumulated 23 citations, reflecting its influence on the field. In related work, his doctoral thesis applied these same physical simulation principles to visual motion estimation of rigid bodies, further establishing his expertise in building resilient vision systems. Duff also explored the critical challenge of tightly coupling 3D object recognition with task planning for robotic manipulation, as reported in his 2013 preliminary study using RoboCup@Work competition objects. His work is notable for addressing a fundamental limitation in tracking—the failure of purely visual methods—by leveraging the predictable physics of the real world.