Robot Vision

Robotic Vision has become a prominent area of research in the last decade or so. While structure and motion estimation from a video sequence had been an active topic in vision for last two decades the present decade has seen modification of vision techniques towards robotic state estimation algorithms such as SLAM, terrain understanding, place recognition and exploration. Our main contributions have been towards motion detection by geometry and vision guided exploration. Our focus for next few years would be towards vision guided navigation in both outdoors and indoor worlds that include dynamic/mobile entities.

Please visit Robot Vision for more information.

Prominent Publications:
1. Image Based Exploration for Indoor Environments using Local Features Aravindhan K Krishnan, K Madhava Krishna and Supreeth Achar. AAMAS 2010.
2. Moving Object Detection by Multi-View Geometric Techniques from a Single Camera Mounted Robot Abhijit Kundu, K Madhava Krishna and J. Sivaswamy. IROS 2009.
3. On-line Convex Optimization based Solution for Mapping in VSLAM, A H Abdul Hafez, S Bhuvanagiri, K Madhava Krishna and C V Jawahar IROS 2008.

Faculty

1. Madhava Krishna (Head)