S
Sohaib Khan
Researcher at Lahore University of Management Sciences
Publications - 40
Citations - 2168
Sohaib Khan is an academic researcher from Lahore University of Management Sciences. The author has contributed to research in topics: Engineering & Structure from motion. The author has an hindex of 17, co-authored 32 publications receiving 2039 citations. Previous affiliations of Sohaib Khan include University of Central Florida & Umm al-Qura University.
Papers
More filters
Journal ArticleDOI
Consistent labeling of tracked objects in multiple cameras with overlapping fields of view
Sohaib Khan,Mubarak Shah +1 more
TL;DR: It is shown that, if the FOV lines are known, it is possible to disambiguate between multiple possibilities for correspondence, and once these lines are initialized, the homography between the views can also be recovered.
Proceedings ArticleDOI
Nonrigid Structure from Motion in Trajectory Space
TL;DR: It is shown that generic bases over trajectories, such as the Discrete Cosine Transform (DCT) basis, can be used to compactly describe most real motions.
Journal ArticleDOI
Trajectory Space: A Dual Representation for Nonrigid Structure from Motion
TL;DR: A dual approach to describe the evolving 3D structure in trajectory space by a linear combination of basis trajectories is proposed and the Discrete Cosine Transform (DCT) is used as the object independent basis and it is demonstrated that it approaches Principal Component Analysis (PCA) for natural motions.
Proceedings ArticleDOI
Object based segmentation of video using color, motion and spatial information
Sohaib Khan,Mubarak Shah +1 more
TL;DR: A maximum a posteriori probability (MAP) framework that uses multiple cues, like spatial location, color and motion, for segmentation, and shows good results on videos that are not suited for either of these approaches.
Proceedings ArticleDOI
Human tracking in multiple cameras
TL;DR: A system for tracking people in multiple uncalibrated cameras that is able to discover spatial relationships between the camera fields of view and use this information to correspond between different perspective views of the same person.