Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
Automated fire flame detection in the surveillance system has drawn significant attention. This paper presents a novel fire flame detection algorithm using motion estimation and color information. The key idea is using irregular motion vectors of the fire flame. This paper presents a novel fire flame detection algorithm using motion estimation and color information. The proposed algorithm consists...
Steel has played a leading role in the development of human civilization and technology. To achieve the goal of industry 4.0 for steel industry, intelligent automated manufacturing becomes increasingly important. One of the key steps on the automatic production line of steel products is automatic inspection of surface detects. In this paper, we propose a fast vision-based surface inspection framework...
Automatic loudness control (ALC) for broadcasting service has been deployed to guarantee the loudness legislation. In this paper, we introduce the low delay automatic loudness control (LD-ALC) in order to reduce the service degradation from the additional algorithmic delay. Performance results have shown that the proposed ALC provides no audible difference with low algorithmic delay fulfilled with...
In this paper, we introduce the virtual SoC platform based on Aldebaran quad-core. The virtual platform provides an efficient method for architecture performance analysis and software profiling using a virtualized system and high performance emulation at the process level.
The recent attentions on video analysis have led to the extensive enhancement of computer vision technologies. However, it is still necessary to closely monitor the results of video analysis by human operators. This paper introduces a trajectory-based scene retrieval system that can help human operators look closely at desired scenes based on a trajectory query. The system includes the index and mapper...
A study on gait pattern identification and classification is presented using a smart insole FootLogger equipped with 3-axis accelerometer and 8 pressure sensors at the bottom. Based on 3 accelerometer outputs and 8 pressure sensor output, we provide a simple signal processing steps to obtain gait signature to be used to identify and classify personal gait signature.
This paper presents a compression method to reduce the number of parameters in convolutional neural networks (CNNs). Although neural networks have an excellent recognition performance in computer vision application, there is a need for a large memory for storing amount of parameters and also necessary in a high-speed computational block. Therefore we propose two the compression schemes (pruning, weight...
As the number of devices using LTE network increases, the demand for real-time applications such as mobile cloud access, augmented reality, and voice over IP (VoIP) is also on the increase. To support such real-time applications in mobile environments, a new handover technology for low latency is required. In 5G systems, network functions virtualization (NFV) can be implemented for low latency handover...
High dimensional feature vectors are extracted for supporting the content-based image search. The indexing schemes for efficiently searching high-dimensional feature vectors are needed. In this paper, we propose a dynamic high dimensional indexing scheme for efficient contents based image retrieval. The proposed index scheme reduces the size of internal node information by eliminating internal node...
The Ultra High Definition (UHD) broadcasting is being prepared to start globally. However, due to a huge amount of data compared with HD data, a processing them in real-time is very difficult. The editing of broadcasting is more difficult because it has to support multiple channels simultaneously. In this paper, we propose a dedicated Very Large Scale Integration (VLSI) to accelerate and control the...
In vehicular ad hoc networks, network coding and cooperative for message propagation have attracted considerable attention as ways to reduce the outage probability to improve the system performances. In this paper, we analyze the exact expression of outage probability and give an approximated expression over the Nakagami-m fading channel with dynamic network coding(DNC) and MIMO dynamic networks coding(MIMO-DNC)...
We implemented media lifelog system with highlighting system with image analysis, video analysis and audio segmentation modules. Image analysis module has image classification, saliency region detection, face detection and facial expression recognition process. Video analysis module has cut detection and key frame detection process. And the result images of key frame detection is used as the input...
Robot is being more intelligent with the visual information and analysis. Specially, the functionality of the object or scene recognition with a high accuracy is essential for the autonomous control and navigation. However, they are too complicated to be implemented in an embedded platform for mobile robots driven by a battery. In this paper, for the high processing speed with low power consumption...
In an image fusion, misalignment errors are generated in the boundaries between objects and background. To solve this problem, this paper presents an image fusion method using the optimal mask that contains main objects. The proposed method consists of three steps: i) pre-processing and global warping to register a tele-view image to a wide-view image, ii) generating seam-based optimal mask to detect...
We propose a modeling and simulation method to control the pose of a projector mounted on a simple robotic device to be deployed in SAR (spatial augmented reality) application where a virtual content should be projected over a desired target area in the real world. For this purpose, the principal axis and four edges of a frustum, which are the key geometric features of projection, are kinematically...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.