The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper addresses the task of designing a modular neural network architecture that jointly solves different tasks. As an example we use the tasks of depth estimation and semantic segmentation given a single RGB image. The main focus of this work is to analyze the cross-modality influence between depth and semantic prediction maps on their joint refinement. While most of the previous works solely...
A solution for the estimation of an unknown scale of the optical image is presented. The method does not require any scale reference or additional depth sensing apparatus other than a conventional digital camera. The estimation is performed by the multiparametric model approximation of the image acquired. A proposed image model introduces the ability to estimate the image scale by means of preliminary...
A major goal of computer vision is to enable computers to interpret visual situations — abstract concepts (e.g., “a person walking a dog,” “a crowd waiting for a bus,” “a picnic”) whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for...
Video Analytics on low/high resolution security camera images has received a considerable interest in recent years. Traffic density estimation from traffic camera images can be considered as one of these subjects. Traditionally GPS data from commercial vehicle fleets have been utilized to estimate traffic density on roads. Traffic density estimation has been implemented using image processing and...
In this work, eye pupil center estimation was performed by using Convolutional Neural Network (CNN) from deep learning methods which are mentioned frequently in the field of machine learning recently, without need for any special hardware. 64×64 image patches created with four different scales were trained through the Caffe framework using the AlexNet model, which was arranged according to its input...
Image registration plays a major role in many areas such as remote sensing, astronomy, biomedical imaging, and so on. Our main contribution in this paper is to present a new subpixel image registration that aligns translated of pair images. This algorithm combines well-known phase correlation technique with the differential methods of the optical flow field, especially the Locus-Kanade technique to...
The technology world for visually impaired people has evolved over the past few years, making their day-to-day life more functional. However, there are still gaps such as in the area of aesthetics and visual image that need to be more explored. Thus, this article describes the first validation in the development of a Web platform in aid of the combination of clothing for blindness people. This project...
Nowadays, one of the most interesting and active research topic in computer vision is the analysis of crowd behavior. Crowd is a set of individuals gathered in a particular physical area. Analyzing crowd behavior involves many ways viz., crowd density estimation, crowd motion detection, crowd tracking and crowd behavior recognition. We provide a brief literature survey on crowd behavior analysis from...
We propose a new variational method for the completion of moving shapes through binary video inpainting that works by smoothly recovering the objects into an inpainting hole. We solve it by a simple dynamic shape analysis algorithm based on threshold dynamics. The model takes into account the optical flow and motion occlusions. The resulting inpainting algorithm diffuses the available information...
Dynamic texture describes images sequence that continuously demonstrates movement of pixels intensity change patterns in time, for example, smoke, fire, waterfall, sea-waves, foliage, traffic on highway and so on. Motion coherence analysis on dynamic textures is usually observed through their motion vector fields. We implement strategic motion coherence analysis to evaluate the coherent motion on...
Egocentric, or first-person vision which became popular in recent years with an emerge in wearable technology, is different than exocentric (third-person) vision in some distinguishable ways, one of which being that the camera wearer is generally not visible in the video frames. Recent work has been done on action and object recognition in egocentric videos, as well as work on biometric extraction...
Human behavior analysis based on surveillance camera is one of hot topics in security, marketing as well as computer vision and pattern recognition, and these are useful for commercial facilities such as convenience stores or book stores. In general, since surveillance camera is placed on the ceiling near store wall to monitor customer behaviors, the majority of this research utilize human model adapted...
Detection of corner is the most essential process in a large number of computer vision and image processing applications. We have mentioned a number of popular contour-based corner detectors in our paper. Among all these detectors chord to triangular arm angle (CTAA) has been demonstrated as the most dominant corner detector in terms of average repeatability. We introduce a new effective method to...
In many applications of computer vision it is important to smooth images while leaving unchanged the boundaries, which is called edge-preserving smoothing. One possibility to solve this problem is to use anisotropic diffusion filtering, which has a parameter that is necessary to assess before its usage. In this paper, it is presented an algorithm, which is used to assess such value of the parameter...
Crowd density analysis is very imperative for intellectual video surveillance to help in management and control of crowds for safety. In recent years, more and more datasets dedicated to crowd density estimation, crowd analysis and anomaly detection in crowded scenes have been created. The use of these dataset allows us to compare different crowd density estimation methods with the same input data...
In this paper, a monocular vision navigation algorithm using optical flow with Principal Direction Screen Strategy is proposed. Firstly, we present an optical flow extraction and adjusting method based on Speed-up robust features (SURF), which makes the distribution of optical flow vectors more well-distributed and increases the accuracy of optical flow. Secondly, we constructive a complete ego-motion...
Cost aggregation is one of the popular method for stereo matching due to efficiency and effectiveness. Their limitation is a high complexity and some error near the contour, which makes them not to implement in real time. Furthermore, the weakness makes them unattractive for many applications which require the accurate depth information. In this paper, we present a cost aggregation method using the...
Optical flow is one of the key components in computer vision research area. Since the seminal work proposed by Horn and Schunck [1], numerous advanced algorithms have been proposed. Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. However, despite their major advances over last decade, conventional optical flow methods...
Convolutional Neural Network (CNN) has been used successfully in solving different computer vision tasks such as classification, detection, and segmentation. This paper addresses the problem of estimating object depth from a single RGB image. While stereo depth estimation is a straightforward task, predicting depth map of an object from a single RGB image is a more challenging task due to the lack...
Human can recognize an object just by looking at the environment, this capability is very useful for designing the reference of humanoid robot with the ability of adapting it on its environment. By knowing the field conditions that exist in such environments, robot can understand the obstacles or anything that can be passed. To do that, robot vision needs to have a knowledge to understanding an obstacles...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.