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...