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 work proposes a gesture-based left and right hand recognition algorithm for dynamic interface adjustment by using the information of the accelerometer and the touch screen on a mobile device. We design a warping method that aligns accelerometer signals with their corresponding positions of unlock-screen gestures. By projecting samples onto feature space and using a support vector machine classifier,...
In this paper, we propose an integer-based pixel blurriness measure scheme. All values are formed as combination of an integer and a fraction. Three fixed-point operations are implemented, including fractional addition, fractional multiplication, and fractional division. Moreover, mean and variance are computed based on fixed-point operations. Pixel blurriness is defined as slope of pixels' difference...
This paper presents a Bayesian network-based method for estimating a distress of road structures from inspection data. The distress is represented by a damage of road structures and its degree. In the previous work, the distress was estimated by utilizing Bayesian network based on categories of road structures, details of road structures and damaged parts. However, inspection data include not only...
Depth from Defocus (DFD) is known as the technology which is able to estimate depth in the scene by a monocular camera without any additive devices. Using this advantage of DFD, we improved the speed of Auto Focus (AF). To apply DFD to AF, it is necessary to capture 2 images that have a small amount of “difference in focal positions” (we call DiFP). In this paper, we show the performance of the depth...
This paper proposes an unsupervised technique for detecting planar surfaces on single depth map image. The proposed method can detect planar surfaces by adopting dynamic seed growing technique without using texture information. So aided with this mechanism to control the growing process, each seed patch can grow to its maximum extent and then the next seed patch begins to grow. This process avoids...
The function of depth perception may be related to the ability to perform vergence eye movements during the viewing of three-dimensional stereoscopic movies.
The GrabCut, which uses the graph-cut iteratively, is popularly used as an interactive image segmentation method since it can produce the globally optimal result. However, since the initialization of the GrabCut is roughly performed by the manual interaction, the accuracy of the segmentation result is not guaranteed when the user defines an inaccurate guide. To solve this problem, in this paper, we...
In this paper, we propose a stand-alone mobile visual search system based on binary features and bag of visual words framework. The contribution of this paper is two-fold: (1) a visual word-dependent substring extraction method is proposed; (2) a modified version of the local NBNN scoring method is proposed in the context of image retrieval. The proposed system improves retrieval accuracy by 11% compared...
Traffic sign recognition contributes to the safety of drivers and people around the car. The system analyzes the road ahead images taken by on-vehicle camera, but blurred and distorted images make it difficult to recognize correct traffic sign. In this paper, we propose a method that deforms from ellipses to perfect circles and applies template matching with distorted sign templates.
Brain machine interfaces (BMIs) transform modulation of electroencephalogram (EEG) elicited by cognitive and mental events users voluntarily perform into words and commands in accordance with their intents to communicate with somebody else or machines the users want to control. One of the leading paradigms in BMIs includes a method which utilizes the modulation of a steady state visual evoked potentials...
GPS performs considerably well in the outdoor LoS conditions. However, its performance rapidly deteriorates when it is used in non-LoS indoor environments. This paper analyzes the performance of Wi-Fi based positioning in the outdoor environments. Our tests reveal that scene analysis can achieve high accuracies even in the outdoor setups. All observations reported in this work are based on experimental...
In this paper, we studied Stacked Denoising Autoencoder(SDA) model for Human pose-based action recognition. We used public dataset Chalearn 2013 which contains Italian body language actions from 27 persons. We studied two model of SDA for pose clustering: 1) Traditional SDA with epoch and Neural Network supervised classifier and 2) Marginalized SDA which faster and ELM supervised classifier. We used...
With the increasing demand for video streaming in mobile environment, we have been tackling a research on throughput prediction based on the measurement history data in order to improve service quality[1][2]. Since throughput fluctuation occurs sharply in mobile environment, useless packet loss or congestion occurs when available network bandwidth is insufficient compared to the bit rate of video...
In this paper we present a simple and convenient user interface for the elderly with an open source system platform used in smartphones. This design provides a simplified interface, a large font, a big button and a simple user interface starter for easy operation, and offers the elderly a method for those who are more accustomed to dial phones. Our design includes an improved selective reply text...
This paper presents a unified framework for recognizing and scoring dance motion using 2-layer classifier so that computation complexity is distributed into two layers. This research examines the performance of sliding window, hidden Markov Model (HMM) and conditional random field (CRF) as the first layer classifier to segment the input video into a sequence of motion primitive label. The second layer...
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.