Sharif Digital Repository

Attention is a cognitive process in which the mind reacts to certain stimuli or stimuli of the environment while other environmental stimuli are ignored. Attention might be an overt or covert process. Overt attention is a process in which based on the purpose, we selectively choose an object or place among other objects and places to focus on and we are aware of it. However, the covert attention originates from hidden source, and we are not aware of it. In fact, the covert attention causes a clear and rapid movement of the eye toward the stimulus or space to be taken into consideration and the time when the movement of the eye it means overt attention has occurred. Visual attention is given... 

Due to the recent advances in the learning of multimodal data, humans tend to use computer systems in order to solve more complex problems. One of them is Visual Question Answering (VQA), where the goal is finding the answer of a question asked about the visual contents of a given image. This is an interdisciplinary problem between the areas of Computer Vision, Natural Language Processing and Reasoning. Because of recent achievements of Deep Neural Networks in these areas, recent works used them to address the VQA task. In this thesis, three different methods have been proposed which adding each of them to existing solutions to the VQA problem can improve their results. First method tries to... 

Hand gesture recognition is one of the most applicable and hot research topics in computer vision community. The recent advances in imaging devices, like Microsoft Kinect, have received a great deal of attention from researchers to reconsider problems such as gesture recognition from depth information. Hand gesture recognition refers to the classification of dynamic hand movements in action videos. Generally, hand gesture recognition includes three main steps: hand detection, feature extraction and classification. The first step plays an important role in hand gesture recognition. The most challenging part of hand gesture recognition is the second step which is the process of extracting high... 

Simultaneous localization and mapping (SLAM) is the action of detecting robot pose in an unknown environment and building the environment map by use of input data that captured from robot sensors. In visual SLAM, the input data for the robot, is limited to camera sensors. Nowadays, SLAM is one of the main challenges in robotic research.For autonomous action, we need robot pose in the map of the environment. The map production in the indoor environment, there is no GPS data, is one of the research issue in robotic community, in last decade. In this thesis, a new and efficient method is proposed for SLAM at the level of objects. The maps produced by state of the art methods don’t have a... 

Nowadays TV broadcasting of soccer matches has attracted a lot of viewers. With advancement of technology, the broadcasting is also going under changes. One of these changes is using free-viewpoint video. In free-viewpoint video users can interactively choose any view to watch the match from. Generally free-viewpoint problem is defined as follows. We have sequential frames of a soccer match video from different views as input. We want to create sequential frames of the same video from a different view as output. There are several methods for solving this problem. We can classify these methods into to general approaches. Image-based and geometry-based. We will examine these approaches in... 

Vision-based localization and 3D orientation estimation of a moving camera, has been for long a vast research area including robot localization and mapping, virtual reality and structure from motion. By introduction of RGB-D cameras in 2010, many sparse methods which are based on key-point extraction and tracking, moved towards dense methods. Dense methods utilize the RGB-D depth and gray-scale values in the images and define the odometry estimation problem as an image registration optimization, without the need to make key-point correspondance in images. Although RGB-D cameras impose specific constraints such as limited depth, depth errors and medium resolution, dense methods have shown... 

Most of current state-of-the-art methods for object tracking use adaptive tracking-by-detection. The performance of state-of-the-art methods is almost real-time with acceptable accuracy. These methods use tracking-by-detection because of its robustness. Tracking-bydetection methods use a detector as a tracker and sweep input for object of interest. They use their predictions to adapt their parameters and therefore be adaptive to appearance change in target. While suitable for cases when the object does not disappear from the scene, these methods tend to fail on occlusions. In this work, we build on a novel approach called Tracking-Learning-Detection (TLD) that overcomes this problem. In... 

One major problem in sport match analysis and interpretation is that there are restricted viewpoints of the game. 3D reconstruction allows us to have virtual replay from any viewpoint so that the events such as penalties can be detected easily. For achieving this purpose, we use many cameras with overlapped views that cover almost all parts of the field. After some preprocessing, 3D reconstruction and texture mapping, we can enhance the viewer experience by having arbitrary viewpoint of the match. In this research, we use two different visual hull methods for 3D reconstruction. In the first method, the visual hull of an object is computed efficiently and robustly from image contours. This... 

Bag of words-based image classification systems have achieved state-of-the-art accuracies in the image classification task recently. These systems can be decomposed into four separate subsystems, each of which has its own objectives: Feature extraction, Feature learning and coding, Pooling, and classification. The effects of the feature learning stage, in which each extracted feature is represented as a linear combination of several visual words, can not be neglected in the success of the whole system. The importance of this part has attracted several researchers to develop different methods in order to alleviate the existing issues. Although several methods have been proposed so far, there... 

Visual tracking is a classic problem, but is continuously an active area of research, in computer vision. Given a bounding box defining the object of interest (target) in the first frame of a video sequence, the goal of a general tracker is to determine the ob-ject’s bounding box in subsequent frames. Utilizing sparse representation, we propose a robust tracking algorithm to handle challenges such as illumination variation, pose change, and occlusion. Object appearance is modeled using a dictionary composed of target patch images contained in previous frames. In each frame, the target is found from a set of candidates via a likelihood measure that is proportional to the sum of the... 

With increasing use of computers in everyday life, improved communication between machines and human is needed. To make a right communication and understand a humankind face which is made in a graphical environment, implementing the audio and visual projects like lip reading, audio and visual speech recognition and lip modelling needed. The main goal in this project is natural representation of strings of lip movements for Farsi language. Lack of a complete audio and visual database for this application in Farsi language made us provide a new complete Farsi database for this project that is called SFAVD. It is a unique audio and visual database which covers the most applicable words, all... 

To overcome challenges such as object appearance changes and environment illumination variations in tracking methods, online algorithms are suggested to be used instead of offline ones. Online algorithms update the model by the information acquired in the last processed frame. The main challenge of using online algorithms is the accumulation of small errors after several steps of updating of the model (drift) which disturbs the model and causes tracking failure. Using the object information in the first frame in each update can be considered as a solution. The proposed online semi-supervised boosting algorithms can overcome the drift problem at the expense of decreasing their capabilities in... 

Tracking is one of the old and still not thoroughly solved problems in machine vision. Its importance lies on its many applications. These applications vary from security surveillance to examining the motion pattern of atomic particles. There is not a tracker which has acceptable results in all situations, yet. A tracker faces many difficulties such as change in illumination and occlusion. In past, tracking was done by using filters or optical flows. By use of the advances in machine learning and pattern recognition, many models have been proposed to accomplish tracking by using these new learning methods. In this dissertation, we proposed a new tracking method which utilizes sparse... 

When an object or its background changes, occlusion or shape change occurs, most of the existed methods fail to track the target. To tackle this problem, we want to use sparse representation that has a great power in classification and reconstruction. Sparsity is a typical and practical hypothesis in many spaces. If a signal isn’t sparse in a space, it can be transformed to another space that is sparse in it. Articles that are published on visual tracking using sparse representation show that this field has attracted a lot of interest in the recent years. Here we have proposed two new methods that have reasonable results. Moreover, while it is well known that sparse representation-based... 

Cracks are the earliest signs of damage in structures which are needed to get detected through structural inspection before causing failure. Regular inspection and post-disaster inspection of structures are usually conducted manually by engineers. These kinds of visual inspections could be expensive, subjective, not reliable, and most importantly inefficient. Computer vision developments help automate this process by analyzing digital images captured from the surface of structures. Despite the fact that masonry structures have more complex surfaces than other kinds of structures, limited studies have focused on presenting machine-vision-based techniques for crack detection in those... 

The purpose of this paper is to estimate the stiffness and strength of damaged rectangular reinforced concrete shear walls after an earthquake using surface crack patterns. Assessing the damage severity of buildings after an earthquake is an important part of the emergency inspection operation of buildings. Expert inspectors tag buildings into two categories of safe or unsafe that are usually affected by subjective decisions, which may result in catastrophic events reported in previous earthquakes. In this research, an extensive database on the images of damaged rectangular reinforced concrete shear walls (RCSWs) is collected and used to develop predictive equations for updated stiffness and... 

Aquatic plants play an important role in water environment. Increasing drag force, distorting the velocity and turbulence structures and other related parameters, are the results of the presences of plants. These changes affect the dispersion and mass transport in the aquatic areas. This thesis presents laboratory visualizations and measurements of wave motion, and passive solute surface dispersion (longitudinal and lateral) in arrays of cylinders, a model for emergent, rigid aquatic plants. In the range of (where is Keulegan–Carpenter number, is the maximum oscillatory velocity perpendicular to the cylinder axis, is the period of oscillation, and is the diameter of the cylinder), and (where... 

Encompassing an interaction between the phase change material (PCM) and the droplets of a heat transfer fluid, the direct contact (DC) method provides a state-of-the-art solution for the meager melting and solidification rates of PCMs. In the DC procedure, when impinging on the molten PCM pool, droplets evaporate, solidifying the portion of the PCM. For the first time, the impact of single and simultaneous double ethanol droplets, having an average diameter of 2.68 mm, on the molten paraffin wax has been scrutinized exhaustively. Experiments have been carried out through high-speed imaging for various Weber numbers ranging from 179 to 464, pool temperatures from 70 to 95°C, and horizontal... 

The error of the inertial navigation system increases over time due to the cumulative errors of sensors. Inertial navigation system couples with sensors or other systems to prevent navigation system errors growth. One of the systems that can be used to couple with inertial navigation system is visual odometry. Visual odometry can calculate relative position of the camera at any time and estimate the device path through input images from one camera (Monocular) or multiple cameras (Stereo). Visual odometry algorithms improvements in recent decade cause this system used as real time. In this thesis, DSO algorithm, which is a direct method and monocular approach, couples with an inertial system... 

Pulsating heat pipe (PHP) is a type of wickless heat pipe that has a simple structure and an outstanding thermal performance. Nanofluid is a type of fluifid in which nanoparticles are dispersed in a base fluid and has a better thermal conductivity in comparison with its base fluid. In this article, the performance of a nanofluid PHP is investigated. In order to simultaneously investigate the thermal performance and flow regimes in the PHP, a one-turn copper PHP with a Pyrex glass attached to its adiabatic section was used. A one-turn Pyrex PHP was also used to fully visualize flow patterns in the PHP. Our results showed that the material that a PHP made of and temperature of working fluid...