Sharif Digital Repository

In this paper, employing recorded images of multiple cameras, we propose a novel fast approach for three-dimensional (3D) human pose reconstruction. Opening a new framework to the pose estimation application, the proposed method is inspired by optical 3D reconstruction algorithms conventionally used for integral imaging. Thanks to the fact that the pose estimation can be carried out by using only key features of the raw recorded images, the computation time and the complexity of our method are considerably reduced. Furthermore, utilizing the here proposed algorithm, rapid variations in actions can be easily tracked. The validity of the proposed method is demonstrated by several experimental... 

For a moving camera recognizing that it has seen a place before now, is one the most important issues in the 3D reconstruction problems. In these problems, the main goal is to create a three-dimensional model from a sequence of 2D captured images during different times. That part of the scene which is rendered by a camera is often modeled by a frustum. Calculating the amount of intersection of two camera view frustums at different times can help to solve this problem. However, there are two major difficulties. First, calculating the intersection of two frustums, in general, is so complicated. And second, there are some uncertainties in the moving camera parameters over time. In this paper,... 

Autonomous robots' vision is one the most important parts in their navigation system and omni-directional stereo vision is an approach to improve this module. Conventional cameras have restricted field of view while omni-directional cameras provide 360-degree field of view. Depth information obtained from stereo vision is very useful for robot navigation in complex environments. This paper presents an omni-directional stereo vision system for Arvand robots constructed by Sharif CE Middle size RoboCup team. We have used two catadioptric cameras aligned vertically. To compute depth, we have used a neural network. In our approach, we trained the neural network without unwrapping the images and... 

A novel algorithm for recovering the 3D shape of deformable objects purely from realistic monocular video is presented in this paper. Unlike traditional non-rigid structure from motion (NRSfM) methods, which have been studied only on synthetic datasets and controlled lab environments that needs some prior constraints (such as manually segmented objects, limited rotations and occlusions, or full-length trajectories), the proposed method has been described and tested on realistic video sequences, which have been downloaded from some social networks (such as Facebook and Twitter). In order to apply NRSfM to the realistic video sequences, because of no-prior information about the scene and... 

Recovering the 3D surface of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. It has been shown that preventing the surface from either shrinking or stretching is an effective way to resolve the ambiguities inherent to this problem. State-of-the-art solutions to nonrigid 3D shape recovery rely on the fact that distances between adjacent surface points must be preserved. Although the results obtained with such a constrained have small reconstruction error, they are still far away from a real-time reconstruction. The authors therefore exploit a two-level weighting schema in a new approach to inextensible and smooth surface reconstruction. This approach... 

In soccer matches, 3D reconstruction is a main part of many applications including free-viewpoint broadcasting, match analysis, augmented reality, and refereeing examination. The main challenge of 3D reconstruction in soccer scenes is the human body reconstruction. Although 3D reconstruction methods have been improved to a high extent in controlled condition, still there are lots of uncovered issues in outdoor scene reconstructions with uncontrolled conditions. In this paper, a view-dependent depth optimization method is presented which addresses two of these issues in soccer scenes. These issues include inaccurate camera calibrations and limited number of input cameras. This method will... 

The use of human hand gestures as a natural interface tool has motivated researchers to conduct research in the modeling, analyzing and recognition of various hand movements. In particular, human computer intelligent interaction has been a focus for research in vision-based gesture recognition. In this work, we introduce a 3D hand model reconstruction method which offers flexible and elaborate representation of hand gestures. We used 20 landmarked points on tips and joints of the fingers and calculated the 3D coordinates of these points through a stereo vision system. Our results show that such reconstruction provides a precise 3D hand model only to be influenced by intrinsic and extrinsic... 

A novel algorithm to reconstruct the three-dimensional (3D) structure of non-rigid shapes based on a single view video, considering the perspective projection camera model, is presented in this paper. Even though perspective projection is considered to be the most realistic model and is ideal for a wide range of cameras in machine vision applications, but because of its complex and often non-linear equations, mostly, is approximated by some simpler camera projection models such as orthographic projection, weak perspective projection and so forth. Orthographic reconstruction of non-rigid surfaces has been done by singular value decomposition algorithm and using the orthogonal characteristics... 

A state-of-the-art algorithm for perspective projection reconstruction of non-rigid surfaces from single-view and realistic videos is proposed. It overcomes the limitations arising from the usage of orthographic camera model and also the complexity and non-linearity issues of perspective projection equation. Unlike traditional non-rigid structure-from-motion (NRSfM) methods, which have been studied only on synthetic datasets and controlled lab environments that require some prior constraints (such as manually segmented objects, limited rotations and occlusions, and full-length trajectories); the proposed method can be used in realistic video sequences. In addition, contrary to previous...