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.
One of the main problems faced by blind learners is a lack of drawing technologies that support images and diagram drawing without the help of a sighted support worker. Even though some technologies have been experimented with in the past, blind learners have not been keen on tactile drawing due to: the difficulty of the drawing task, the length of time taken to complete a simple task, and the inefficiency...
The neocognitron is a deep (multi-layered) convolutional neural network that can be trained to recognize visual patterns robustly. In the intermediate layers of the neocognitron, local features are extracted from input patterns. In the deepest layer, based on the features extracted in the intermediate layers, input patterns are classified into classes. A method called IntVec (interpolating-vector)...
This paper presents the design problem of furniture arrangement in a residential interior living space, and addresses it by means of evolutionary computation. Interior arrangement is an important and interesting problem that occurs commonly when designing living spaces. It entails determining the locations of interior elements such as tables, seating elements, projection screens etc., in order to...
Convolutional neural networks play an increasingly important role in computer vision tasks, especially in the field of visual object recognition. Many prominent models, such as Inception, Maxout, ResNet, and NIN, have been proposed to significantly improve recognition performance. Inspired from those models, we propose a novel module called self-adaptive module (SAM). SAM consists of four passes and...
The trends are reviewed in the development of unmanned transport systems. There is highlighted an increasingly important part of various range vision/location systems. There is described an architecture of the on-board computer network supplying information to the control systems of the mobile vehicles with the enhanced level of independence and totally unmanned. The proposed architecture provides...
This paper presents a novel framework for the visual tracking problem. This framework predicts the exact location of the object using a regression. In this work, we first select an approximate region based on object location in the previous frame and then predict the exact location of the object in the current frame by a deep convolutional network that its last layer replaced with a regression. The...
Deep learning architectures have shown great success in various computer vision applications. In this study, we investigate some of the very popular convolutional neural network (CNN) architectures, namely GoogleNet, AlexNet, VGG19 and ResNet. Furthermore, we show possible early feature fusion strategies for visual object classification tasks. Concatanation of features, average pooling and maximum...
Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of convolutional neural networks (CNNs) from the big data perspective. We analyze recent studies and different network architectures both in terms of running time and accuracy...
Static diagrams are the most prevalent artifact used in visualizing component-and-connector architectures and supporting software architecture learning. The use of such artifacts exhibits a fundamental disconnect from the dynamic nature of software systems, deemphasizes the importance of architectural interactions with a focus on static structure, and does not support a high degree of learner engagement...
This paper proposes a virtual Vital Signs Sensor (VSS) for visualization of half illness (so called "Mibyou") and sudden illness. Since both half and sudden illnesses, which are located in between wellness and illness, are categorized in healthy(H) to illness(I) transition(T) status. So, we name this status as HIT. Since HIT happens in an ordinary life, VSS for HIT visualization should work...
We consider the design of vision-based control algorithms for unmanned aerial vehicles (UAVs), so as to enable a UAV to autonomously follow a person. A new vision-based control architecture is proposed with the goals of 1) robustly following the user and 2) implementing following behaviors programmed by manipulation of visual patterns. This is achieved within a detection/tracking paradigm, where the...
Over the years, computer vision researchers have spent an immense amount of effort on designing image features for the visual object recognition task. We propose to incorporate this valuable experience to guide the task of training deep neural networks. Our idea is to pretrain the network through the task of replicating the process of hand-designed feature extraction. By learning to replicate the...
The theory behind deep learning, the human visual system was investigated and general principles of how it functions are extracted. Our finding is that there are neuroscience theories that are not utilized in deep learning. Therefore, in this work, a novel model utilizing some of those theories is developed. The new model addresses the parallel nature of the human brain compared to the hierarchal...
Mis-orientation in unfamiliar domain is a common problem for new visitors when they visit a new location. This study proposes a unique solution by visualizing the real world to 3D model similarly (congruent) while the visitor on the move. Our approach provides visualization of 3D maps in virtual 3D workspace environments which assist a user to navigate to a target location to meet with others. This...
Generating descriptions for visual data (images and video) automatically has been a complicated task in the field of Computer Vision and Artificial Intelligence. This paper discusses the working of and improvements on an algorithm called Neural Image Captioner (NIC) by Oriol Vinyals and his team, which uses a deep convolutional and recurrent architecture to generate natural language sentences to describe...
This paper on the. Net platform three layer architecture of online bookstore system design process were research and exploration, and the second layer architecture comparison of advantages and disadvantages. Three layer architecture thought take the strategy of "divide and conquer", the separation of system design key points of each to a separate layer implementation, and through mutual...
Nowadays visual sensor networks are used in emergency or time of surveillance of remote area where human reach is not possible. There situations arise when mobility of nodes is required in visual sensor network. In this paper we considers mobility of visual sensor nodes and tries to maximize the lifetime of network using priority if nodes. We use hierarchical and heterogeneous architecture for deploying...
This paper is aimed at proposing a machine learning approach to analyze and make sense out of the ancient rock arts by exploring them through cloud infrastructure. The visual language of the rock art is proposed to be interpreted and transformed into the current language of human cognition. The rock arts can be captured as 3D motion pictures; ultrasonically detected images; pictures captured using...
Vision and video applications are becoming pervasive in mobile and embedded systems. Consumer wearable devices require capabilities for real-time video analytics and prolonged battery lifetimes, which is further driving the need for innovative system designs with low-power, reliability and high performance. Further, the increasing resolution of image sensors in these mobile systems places an increasing...
We describe the Ignite Distributed Collaborative Scientific Visualization System (IDCVS), a system which permits real-time interaction and visual collaboration around large data sets, with an initial emphasis on scientific data. The IDCVS offers such a collaborative environment, with real-time interaction on any device between users separated across the wide area. It provides seamless interaction...
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.