K
Kaustubh Srikrishna Patwardhan
Researcher at Indian Institute of Technology Bombay
Publications - 5
Citations - 76
Kaustubh Srikrishna Patwardhan is an academic researcher from Indian Institute of Technology Bombay. The author has contributed to research in topics: Gesture recognition & Gesture. The author has an hindex of 4, co-authored 5 publications receiving 75 citations.
Papers
More filters
Journal ArticleDOI
Hand gesture modelling and recognition involving changing shapes and trajectories, using a Predictive EigenTracker
TL;DR: A novel eigenspace-based framework to model a dynamic hand gesture that incorporates both hand shape as well as trajectory information is presented and encouraging experimental results are shown on a such a representative set.
Proceedings ArticleDOI
Robust shape based two hand tracker
Ketan Avinash Barhate,Kaustubh Srikrishna Patwardhan,Sumantra Dutta Roy,Subhasis Chaudhuri,Santanu Chaudhury +4 more
TL;DR: A robust shape-based on-line tracker for simultaneously tracking the motion of both hands, that is robust to cases of background clutter, other moving objects, occlusions of one hand by the other and a wide range of illumination variations is presented.
Proceedings ArticleDOI
On line predictive appearance-based tracking
Namita Gupta,Pragya Mittal,Kaustubh Srikrishna Patwardhan,S. Dutta Roy,Santanu Chaudhury,Subhashis Banerjee +5 more
TL;DR: A novel predictive statistical framework is presented to improve the performance of an eigentracker and incorporates a new importance sampling mechanism which increases the robustness of the eigent racker and enables it to track nonconvex objects better.
Proceedings Article
Dynamic Hand Gesture Recognition Using Predictive Eigen Tracker.
TL;DR: A novel framework to model a dynamic hand gesture by k-dimensional vector that incorporates both the hand shape as well as the trajectory information and utilise inter-gesture distances for gesture recognition is presented.
Proceedings ArticleDOI
Modelling and recognising spatio-temporal hand gestures with an uncalibrated camera
TL;DR: This work presents a robust tracker for highly articulated 3-D objects such as human hands with an uncalibrated camera which works well in spite of cases of other similar moving objects, and background clutter.