Sparse coding has recently become a popular approach in computer vision to learn dictionaries of natural images. In this paper we extend the sparse coding framework to learn interpretable spatio-temporal primitives. We formulated the problem as a tensor factorization problem with tensor group norm constraints over the primitives, diagonal constraints on the activations that provide interpretabi...

This paper presents a method to estimate the 3D object position and occupancy given a set of object detections in multiple images and calibrated cameras. This problem is modelled as the estimation of a set of quadrics given 2D conics fit to the object bounding boxes. Although a closed form solution has been recently proposed, the resulting quadrics can be inaccurate or even be non valid ellipso...

Touch-less based fingerprint verification systems are free from the problems of image deformation, latent fingerprint issues and so forth that appear in the contemporary touch based fingerprint verification systems. Coupled with template protection mechanism, a touch-less fingerprint verification system is further enhanced. In this paper, a secure end-to-end touch-less fingerprint verification ...

The problem of estimating rigid motion from projections may be characterized using a nonlinear dynamical system, composed of the rigid motion constraint and the perspective map. The time derivative of the output of such a system, which is called the “motion field” and approximated by the “optical flow”, is bilinear in the motion parameters, and may be used to specify a subspace constraint on ei...

5.1 ROOT MOTION .....................................................................................................................................................4 5.2 KINEMATIC CONSTRAINTS....................................................................................................................................5 5.3 MOTION CYCLIFICATION .................................................

One of the most used techniques for full-body human tracking consists of estimating the probability of the parameters of a human body model over time by means of a particle filter. However, given the high-dimensionality of the models to be tracked, the number of required particles to properly populate the space of solutions makes the problem computationally very expensive. To overcome this, we ...

This paper presents a computational technique for creating whole-body motions of human and animal characters without reference motion. Our work enables animators to generate a natural motion by dragging a link to an arbitrary position with any number of links pinned in the global frame, as well as other constraints such as desired joint angles and joint motion ranges. The method leads to an int...

A two-stage optimization method is presented by employing the evolutionary structural optimization (ESO) and ant colony optimization (ACO), which is called ESO-ACO method. To implement ESO-ACO, size optimization is performed using ESO, first. Then, the outcomes of ESO are employed to enhance ACO. In optimization process, the weight of double layer grid is minimized under various constraints whi...

Project Description At Carnegie Mellon University’s Personal Robotics Lab, we aim to create algorithms that enable robots to seamlessly and autonomously collaborate with and around people in human-centric environments, such as the home. One of the many challenges in creating this future is giving our robots the skill set to perform many of the tasks we do on a daily basis, from the simple to th...

Robot Motion Generating based on Constraints Masahiko ONOSATO and Hiroyuki YOSHIKAWA This paper describes a systematic method which can generate effective robot motion for handling constrained objects automatically. In this study, constraints which appear in the time of object manipulation are divided into following three parts. The first one is a natural constraint which is observed between an...