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.
The rapid evolution of media services has having a strong impact on the way users process and share their data. At the same time, users are becoming every day more aware of the risks that might arise while exchanging or processing video data through the net. The need for frameworks enabling processing and sharing of the content under user control is becoming a very important issue since adequate level...
In application of human computer interaction, modeling of human vision is an approach seems appropriate but has not yet been accomplished. The main contribution in this paper is proposing an intuitive system for human computer interaction by modeling human vision using human sight position and human body part position, as well as an evaluation method to estimate the characteristic of the proposed...
This paper presents an interoperability analysis of Ginga-NCL and HbbTV applications, which consist on using a NCL player implemented as a web application to be executed on an HbbTV platform. This work presents the integration of a web-based NCL player and the subsequent testing using an HbbTV emulator.
The LDA-based face recognition using face images by actual distance as training images showed good performance. However, it causes user inconvenience as it requires the user to move multiple distance in person to acquire face images for initial user registration. In this paper, LDA-based face recognition applicable to robotic environments is proposed. The proposed method can get face images by distance...
We present an efficient pose tracking method for mobile augmented reality. Although the conventional pyramid-based coarse-to-fine approach has good precision and robustness, it is too complex for low-spec mobile devices and speeding up pose tracking is essential. The proposed method focuses on the rapidity and linearity of the movement between successive frames, and omits unnecessary processing such...
This paper proposes a novel scene-change detection to recognize the change in a moving image for the frame rate up-conversion. The proposed algorithm calculates two-dimensional histogram. Then, it performs the positional analysis to extract a histogram shape and finally detects the scene change. In the experimental results, the proposed algorithm enhanced the average F1 score, compared to the benchmark...
A fast and robust camera's auto exposure algorithm is proposed by modeling its luminance characteristics as a concave/convex function of a control parameter. A proper parameter value is computed using a modified secant algorithm with fast convergence. The superior performance of the proposed algorithm is confirmed by experimental results.
A novel and high-quality system for moving object detection in sequences recorded with moving cameras is proposed. This system is based on the collaboration between an automatic homography estimation module for image alignment, and a robust moving object detection using an efficient spatio-temporal nonparametric background modeling.
Optical sensor-based health care systems have to be both cost-efficient and easily integrable into a domestic environment. Consequently, the reduction of the overall number of necessary sensors is a crucial issue. We present an optical system employing a single omnidirectional stereo sensor for human behavior analysis in complex living environments.
We approach the challenging problem of generating highlights from sports broadcasts utilizing audio information only. A language-independent, multi-stage classification approach is employed for detection of key acoustic events which then act as a platform for summarization of highlight scenes. Objective results and human experience indicate that our system is highly efficient.
This paper presents a wind-noise suppressor with wind-burst detection based on a stationary noise estimate. Input that exceeds an estimated stationary noise level is detected as wind burst. Upon detection, the spectral gain is reduced to apply maximum suppression determined by a floor gain. False detection of a speech onset as wind is minimized by speech-wind discrimination with spectral smoothness...
A multicopter is now becoming a crucial part in the broadcasting industry for capturing videos. When they are not able to reach places, men can control multicopters and take desired videos. However, there still exist many problems in capturing sound because the multicopter is often placed far from the sound source and the sound of the propellers interferes with the recording target sound. Capturing...
In this paper, an upmixing method is proposed which converts nearly monaural audio signals into 5.1-channel ones for portable multimedia devices. Since spatial information is not clear due to close spacing between stereo microphones in portable devices, the proposed method tries to estimate the source direction depending on the frequency using azimuth-frequency analysis instead of directly estimating...
This paper presents the speech enabled location based data services by employing the location associated elements to VoiceXML. Specifically, <location> elements and the related system behaviors are defined and integrated into the Voice Applications. Besides, we implemented the Voice Applications platform with the GPS emulator to verify the location functionalities. With this new feature, the...
Notwithstanding a proliferation of wearable devices and mobile apps for activities monitoring, no model has been put forth to complementarily integrate the monitored data. We propose an enriched activity model to reorganize personal activity logs from heterogeneous sensors and to visualize logs in a harmonized way with a meaningful summary.
This paper presents an algorithm to mine basic patterns of human activities on a daily basis using non-negative matrix factorization (NMF). The greatest benefit of the algorithm is that it can elicit patterns from which meanings can be easily interpreted. To confirm its performance, the proposed algorithm was applied to PC logging data collected from three occupations in offices. Daily patterns of...
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.