Sharif Digital Repository

3D scene understanding is an open challenge in the field of computer vision. Most of the focus is on 2D methods in which the semantic labeling of each RGB pixel is considered. But, in this paper, the 3D semantic labeling of RGB-D images is considered. In the proposed method, to extract some meaningful features, the superpixel generation algorithm is applied to the RGB image to segment it into a set of disjoint pixels. After that, the set of three powerful classifiers are utilized to semantically label each superpixel. In the proposed method, the probability outputs of these classifiers are concatenated as the novel feature vector for each superpixel. Consequently, to analyze the strengths... 

3D scene understanding is one of the most important problems in the field of computer vision. Although, in the past decades, considerable attention has been devoted on the 2D scene understanding problem, now with the development of the depth sensors (like Microsoft Kinect), the 3D scene understanding has become a very challenging task. Traditionally, the scene understanding problem was considered as the semantic labeling of each image pixel. Semantic labeling of RGB-D images has not attained a comparable success, as the RGB semantic labeling, due to the lack of a challenging dataset. With the introduction of an RGB-D dataset, called NYU-V2, it became possible to propose a novel method to... 

One of the most important steps towards 3D scene understanding is the semantic segmentation of images. The 3D scene understanding is considered as the crucial requirement in computer vision and robotic applications. With the availability of RGB-D cameras, it is desired to improve the accuracy of the scene understanding process by exploiting the depth along with appearance features. One of the main problems in RGB-D semantic segmentation is how to fuse or combine these two modalities to achieve more advantages of the common and specific features of each modality. Recently, the methods that encounter deep convolutional neural networks have reached the state-of-the-art results in dense... 

Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints of these devices. Recently, some architectures have been proposed to overcome these limitations by considering specific hardware-software equipment. In this paper, the lightweight residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed method decreases the cost of training and inference processes without using any special... 

Semantic segmentation is one of the most important tasks in the field of computer vision. It is the main step towards scene understanding. With the advent of RGB-Depth sensors, such as Microsoft Kinect, nowadays RGB-Depth images are easily available. This has changed the landscape of some tasks such as semantic segmentation. As the depth images are independent of illumination, the combination of depth and RGB images can improve the quality of semantic labeling. The related research has been divided into two main categories, based on the usage of hand-crafted features and deep learning. Although the state-of-the-art results are mainly achieved by deep learning methods, traditional methods... 

Determining an object location in a specific region is an important task in many machine vision applications. Different parameters affect the accuracy of the localization process. The quantization process in charge-coupled device of a camera is one of the sources of error that causes estimation rather than identifying the exact position of the observed object. A cluster of points, in the field of view of a camera are mapped into a pixel. These points form an uncertainty region. In this paper, we present a geometrical model to analyze the volume of this uncertainty region as a criterion for object localization error. The proposed approach models the field of view of each pixel as an oblique... 

Comparison of the traditional linear heating method of TPD with an original stepwise heating scheme was reported for the first time. Stepwise heating TPD was carried out by keeping the temperature constant as soon as ammonia desorption signal rises until the signal returns to the baseline. More ammonia desorption peaks on a SAPO-34 catalyst were identified using TPD with stepwise heating. The effect of temperature ramp on desorption peak broadening in TPD curve was also addressed. The more distinct ammonia desorption peaks in stepwise TPD indicates that ammonia adsorbs in about five or six different ways on SAPO-34, and attribution of different adsorptions may be explained considering some... 

Most part of Iran is dominated by arid and semi-arid areas due to low annual rainfall. The need for production of fresh water from brackish water is considerably high, especially in dry regions. In this study 1 month daily-based experimental data from a solar still site has been reported. The technical and operational problems of this site which finally contributed to the total cease of the site are described. Then a detailed analysis is investigated on progress of a prototype which constructed in order to solve the site's problems. The results of 1 month of experimental data of the final design showed that the last prototype could be used to solve the current problems of the site. The... 

Hydrocracking is one of the most versatile petroleum refining processes for production of valuable products including gasoline, gas oil, and jet fuel. In this paper, a five-parameter continuous lumping model was used for kinetic modeling of hydrocracking of vacuum gas oil (VGO). The model parameters were estimated from industrial data obtained from a fixed bed reactor operating at an average temperature of 400°C and residence time of 0.3 h. Product distributions were obtained in terms of the weight fraction of various boiling point cuts. The model parameters were estimated using the Nelder-Mead optimization procedure and were correlated with temperature. Comparison of experimental and... 

Purpose - The purpose of this paper is to present an improved methodology for design of custom-made hip prostheses, through integration of advanced image processing, computer aided design (CAD) and additive manufacturing (AM) technologies. Design/methodology/approach - The proposed methodology for design of custom-made hip prostheses is based on an independent design criterion for each of the intra-medullary and extra-medullary portions of the prosthesis. The intra-medullar part of the prosthesis is designed using a more accurate and detailed description of the 3D geometry of the femoral intra-medullary cavity, including the septum calcar ridge, so that an improved fill and fit performance... 

In this letter, we propose a method for real-time high density impulse noise suppression from images. In our method, we first apply an impulse detector to identify the corrupted pixels and then employ an innovative weighted-average filter to restore them. The filter takes the nearest neighboring interpolated image as the initial image and computes the weights according to the relative positions of the corrupted and uncorrupted pixels. Experimental results show that the proposed method outperforms the best existing methods in both PSNR measure and visual quality and is quite suitable for real-time applications  

The disposal of used tires is a major environmental problem. With increasing interest on recovery of wastes, pyrolysis is considered as an alternative process for recovering some of the value in scrap tires. An accurate kinetic model is required to predict product yields during thermal or catalytic pyrolysis of scrap tires. Pyrolysis products contain a variety of hydrocarbons over a wide boiling range. A common approach for kinetic modeling of such complex systems is lumping where each lump is defined by a boiling point range. Available experimental data for thermal and catalytic pyrolysis of scrap tires from the literature were used to evaluate two types of lumping models; discrete and... 

Compared with flat linear structures, tubular linear machines do not face edge effects, making their performance better than their flat counterparts. In this article, a novel linear variable-reluctance resolver with tubular configuration is proposed. To optimize the design of an electromagnetic structure, modeling methods are used. Thus, in this article, an analytical model for the proposed resolver is presented. This model is based on the magnetic equivalent circuit (MEC) method and is considerably less time-consuming than finite element analysis (FEA), yet provides accurate results. A conformal mapping is employed to compute the permeance of the air-gap. The proposed model is then utilized... 

In Brukner and Zeilinger's interpretation of quantum mechanics, information is introduced as the most fundamental notion and the finiteness of information is considered as an essential feature of quantum systems. They also define a new measure of information which is inherently different from the Shannon information and try to show that the latter is not useful in defining the information content in a quantum object. Here, we show that there are serious problems in their approach which make their efforts unsatisfactory. The finiteness of information does not explain how objective results appear in experiments and what an instantaneous change in the so-called information vector (or catalog of... 

Low silicon content SAPO-34 was successfully synthesized using the conventional hydrothermal crystallization in the static condition. Effects of different synthesis conditions including crystallization temperature and the silicon source were investigated through X-ray diffraction patterns. It was concluded that the silicon source had a significant effect on silicon incorporation into the alumino-phosphate building blocks in the course of crystallization. Using precipitated silica instead of silica sol resulted in the formation of impurities of alumino-phosphates phases whose crystalline structures collapse at the high temperature of calcination. For the low silicon SAPO-34 synthesis, the... 

Let R be a left Noetherian ring and ZD(R) be the set of all zero-divisors of R. In this paper, it is shown that if RZD(R) is finite, then R is finite  

Numerous methods for direction of arrival (DOA) estimation, used in smart antennas have been already reported in previous studies. The precision of DOA estimation depends on the choice of the algorithm and the geometrical configuration of the antenna array. In this work, the performance of new geometrical configurations, i.e. 2D with equal area and 3D with equal volume including circular, square, triangular, hexagonal and star geometries, with equal number of antenna elements, are examined and compared to each other to find the most proper geometry. Monte-Carlo simulations are performed to evaluate the DOA precision of the proposed arrays using the MUSIC algorithm. It is shown that in three...