Publications

  1. Appu Shaji, Sharat Chandran and David Suter Manifold Optimisation for Motion Factorisation To appear in the proceedings of International Conference on Pattern Recognition, 2008 [pdf - 840K]

    Abstract

    This paper presents a novel formulation for the popular factorisation based solution for Structure from Motion. Since our measurement matrices are populated with incomplete and inaccurate data, SVD based total least squares solution are less than appropriate. Instead, we approach the problem as a non-linear unconstrained minimisation problem on the product manifold of the Special Euclidean Group ($SE_3$). The restriction of the domain of optimisation to the $SE_3$ product manifold not only implies that each intermediate solution is a plausible object motion, but also ensures better intrinsic stability for the minimisation algorithm. We compare our method with existing state of art, and show that our algorithm exhibits superior performance.

  2. Appu Shaji and Sharat Chandran Riemannian Manifold Optimisation for Non-rigid Structure from Motion in the proceedings of the IEEE CVPR workshop, NORDIA 2008, Anchorage [pdf - 300K]

    Abstract

    This paper address the problem of automatically extracting the 3D configurations of deformable objects from 2D features. Our focus in this work is to build on the observation that the subspace spanned by the motion parameters is a subset of a smooth manifold, and therefore we hunt for the solution in this space, rather than use heuristics (as previously attempted earlier). We succeed in this by attaching a canonical Riemannian metric, and using a variant of the non-rigid factorisation algorithm for Structure from Motion. We qualitatively and quantitatively show that our algorithm produces better results when compared to the state of art.

  3. Appu Shaji, Behajt Siddiquie, Sharat Chandran and David Suter Human Pose Extraction from Monocular Videos using Non-rigid Factorization in the proceedings of British Machine Vision Conference, 2007 [pdf - 2.2 MB]

    Abstract

    We focus on the problem of automatically extracting the 3D configuration of human poses from 2D image features tracked over a finite interval of time . This problem is highly non-linear in nature and confounds standard regression techniques. Our approach effectively marries a non-rigid factorization algorithm with prior learned statistical models from archival motion capture database. We show that a stand alone non-rigid factorization algorithm is highly unsuitable for this problem. However, when coupled with the learned statistical model in the form of a constrained non- linear programming method, it yields a substantially better solution.

  4. Ameya Vaidya, Appu Shaji and Sharat Chandran Vision-Based Posing of 3D Virtual Actors in the proceedings of Asian Conference of Computer Vision, IIIT Hyderbad, 2006 [pdf - 351KB]

    Abstract

    Construction of key poses is one of the most tedious and time consuming steps in synthesizing of 3D virtual actors. Recent alternate schemes expect the user to specify two inputs. Along with a neutral 3D reference model, more intuitive 2D inputs such as sketches, photographs or video frames are provided. Using these, of all the possible configurations, the "best" 3D virtual actor is posed

    In this paper, we provide a solution to this ill-posed problem. We first give a solution to the problem of finding an approximate view consistent with the 2D sketch. Elements of this rigid-body solution are novel. Next, we provide a new solution to the process of extending or retracting limbs to more accurately suit the sketch. This posing algorithm, is based on a search based scheme inspired by anthropometric evidence. Less physical work is required by the actor to reach the desired pose from the base position. We also show that our algorithm converges to an acceptable solution much faster compared to the previous methods.

  5. Vishal Mammania, Appu Shaji and Sharat Chandran, Markerless Motion Capture from Monocular Videos Proceedings of Fourth Indian Conference on Computer Vision, Graphics and Image Processing, ISI Calcutta, Dec 2004 [pdf -297KB]

    Abstract

    We present a method to determine the 3D spatial locations of joints of a human body from a monocular video sequence of a Bharatanatyam dance. The proposed method uses domain specific knowledge to track major joints of the human in motion from the two dimensional input data. We then make use of various physical and motion constraints regarding the human body to construct a set of feasible 3D poses. A dynamic programming based method is used to find an optimal sequence of feasible poses that represents the original motion in the video.

Sheetal Joseph