检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Yu-Chun Lin Yi-Ming Chan Luo-Chieh Chuang Li-Chen Fu Shih-Shinh Huang Pei-Yung Hsiao Min-Fang Luo Intelligent Robot and Automation Laboratory Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan National Taiwan University Taipei TW Department of Computer and Communication Engineering National Kaohsiung First University of Science and Technology Kaohsiung Taiwan Department of Electrical Engineering National University of Kaohsiung Kaohsiung Taiwan System development center Chung-Shan Institute of Science and Technology Longtan Shaiang Taoyuan Taiwan

Pedestrian detection is important in the computer vision field. In the nighttime, pedestrian detection is even more valuable. In this paper, we address the issue of detecting pedestrians in video streams from a moving camera at nighttime. Most nighttime human detection approaches only use single feature extracted from images. The effective image features in daytime environment may suffer from textureless, high contrast and low light problems at night. To deal with these issues, we first segment the foreground by using the proposed Smart Region Detection approach to generate candidates. Then we design a nighttime pedestrian detection system based on the AdaBoost and the support vector machine (SVM) classifiers with contour and histogram of oriented gradients (HOG) features to effectively recognize pedestrians from those candidates. Combining different type of complementary features improve the detection performance. Results show that our pedestrian detection system is promising in the nighttime environment.

关键词： Feature extraction Image segmentation Cameras Humans Databases Lighting Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A no-reference image quality evaluation based on power spectrum

A no-reference image quality evaluation based on power spect...

引用

3DTV Conference

作者： Yan Zhang Ping An Qiuwen Zhang Liquan Shen Zhaoyang Zhang School of Communication and Information Engineering Shanghai University China Department of Computer Science and Technology Anhui University of Finance and Economics China Key Laboratory of Advanced Displays and System Application Ministry of Education China

ISBN: (纸本)9781612841618

No-reference quality evaluation is more difficult because it does not refer to any image. However, in some cases, like virtual view images, can not find the reference image, no-reference method had to be used. With the free viewpoint video technology development and application, measuring the performance of the multiview video system is essential and virtual view image quality evaluation is one of the key technologies in the system. The characteristic of virtual view image quality evaluation is that most of the virtual view images haven't reference images and can't be assessed using general measures such as PSNR of full-reference. Therefore, this paper proposed a no-reference image quality evaluation method based on image power spectrum. Experimental results show that the proposed method is consistent with PSNR.

关键词： PSNR Image quality Three dimensional displays Transform coding Mathematical model Speckle

来源：评论

学校读者我要写书评

暂无评论

Improved multi-view depth estimation for view synthesis in 3D video coding

Improved multi-view depth estimation for view synthesis in 3...

引用

3DTV Conference

作者： Qiuwen Zhang Ping An Yan Zhang Liquan Shen Zhaoyang Zhang School of Communication and Information Engineering Shanghai University China Key Laboratory of Advanced Displays and System Application Ministry of Education China Department of Computer Science and Technology Anhui University of Finance and Economics China

ISBN: (纸本)9781612841618

Multi-view depth estimation is an important part in the virtual view synthesis and depth map coding within the 3DV/FTV applications. However, existing depth estimation methods generally have difficulty to generate good depth results around object edges or in areas with less texture. To solve this problem, we propose an improved algorithm to obtain a smooth and accurate depth map for view synthesis in 3D video coding. The proposed method aims to preserve details in the depth map and simultaneously smooth depths in object boundary occluded area, less texture and discontinuity regions, to avoid blurring in the synthesized views. Experimental results show a significant improvement of the initial input depth maps and coding efficiency, as well as a reduction of view synthesis artifacts.

关键词： Estimation Pixel Three dimensional displays Encoding Rendering (computer graphics) Image coding Transform coding

来源：评论

学校读者我要写书评

暂无评论

Efficient rendering distortion estimation for depth map compression

Efficient rendering distortion estimation for depth map comp...

引用

IEEE International Conference on Image Processing

作者： Qiuwen Zhang Ping An Yan Zhang Zhaoyang Zhang School of Communication and Information Engineering Shanghai University China Key Laboratory of Advanced Displays and System Application Ministry of Education China Department of Computer Science and Technology Anhui University of Finance and Economics China

A depth map represents three-dimensional (3D) scene information and is used to synthesize virtual views in 3D video. Since the quality of synthesized virtual views highly depends on the quality of depth map, efficient depth compression is crucial to realize the 3D video system. However compressing depth map using existing video coding techniques yields unacceptable distortions while rendering virtual views. To solve this problem, we propose an efficient depth map compression method for the view rendering, a novel distortion metric base on view rendering distortions instead of distortion of depth map itself. First, we derive relationships between distortions in coded depth map and rendered view. Then, a region based video characteristics distortion model is proposed for precisely estimation distortion in view synthesis. Finally, experimental results have shown that 1.8 dB coding gain in terms of PSNR and subjective quality improvement of synthesized views are achieved by the proposed method.

关键词： Image coding Rendering (computer graphics) Three dimensional displays Cameras Geometry Encoding Estimation

来源：评论

学校读者我要写书评

暂无评论

An improved depth map estimation for coding and view synthesis

An improved depth map estimation for coding and view synthes...

引用

IEEE International Conference on Image Processing

Inaccuracy depth estimation may influence on depth coding and virtual view rendering in the free-viewpoint television (FTV) system, an improved depth map estimation is proposed to solve the problem for coding and view synthesis. Firstly, check the consistency of initial depth, and the influence of initial miss-matches is minimized by introduction of an additional adaptive matching error selection that penalizes the unreliable matches. Then according to certain criteria, the multi-reference depth maps are merged into one disparity map to improve the quality of disparity map. Finally, a multilateral filtering is used to preserve details in the depth map and simultaneously smooth the depths in occluded areas at object boundary, less texture and discontinuity regions. Experimental results show a significant improvement of the initial input depth maps and coding efficiency, as well as a reduction of view synthesis artifacts.

关键词： Estimation Image coding Rendering (computer graphics) Transform coding Three dimensional displays Filtering

来源：评论

学校读者我要写书评

暂无评论

A network partitioning recovery process in Mobile Ad-Hoc Networks

A network partitioning recovery process in Mobile Ad-Hoc Net...

引用

IEEE International Conference on Wireless and Mobile Computing, Networking And communications (WiMob)

作者： Mikhail Tarasov Jochen Seitz Oleksandr Artemenko Division of Communication Networks Faculty of Electrical Engineering and Information Technology Ilmenau University of Technology Ilmenau Germany Applied Computer Science Department Erfurt University of Applied Sciences Erfurt Germany

Mobile Ad-hoc Networks (MANETs) are of significant scientific and practical interest in many areas of human life. MANETs also play a vital role in providing an uninterrupted communication service between members of a rescue team in natural or anthropogenic disasters. One of the most common problems of MANETs is network partitioning. In this situation, the network splits up into several isolated fragments incapable of communicating with each other. Network partitioning can lead to dramatic consequences especially in disaster scenarios. In this paper, we propose a solution for the above mentioned problem, a system which detects and recovers from network partitioning using additional mobile nodes. Besides, the proposed novel system is scalable and robust due to a self-organizing, distributed architecture. Furthermore, it is also energy efficient during its reactive behavior, what is especially important for mobile nodes with limited battery capacity.

关键词： Mobile computing Ad hoc networks Mobile communication IP networks Routing Wireless sensor networks Network topology

来源：评论

学校读者我要写书评

暂无评论

Boxing Punch Analysis Using 3D Gyro Sensor

Boxing Punch Analysis Using 3D Gyro Sensor

引用

SICE Annual Conference

作者： Manabu Morita Kajiro Watanabe Kazuyuki Kobayashi Yousuke Kurihara Department of System Engineering Faculty of Engineering Hosei University Department of System Engineering Hosei University Department of Computer and Information Science Seikei University

ISBN: (纸本)9784907764388

The objective of this study was to discriminate different types of punches based on signals measured by gyro sensors. If a boxer consistently uses the same pattern of attack, his opponent could easily determine what type of punch is coming next. Thus, by feeding back information on the frequency of each type of punch, the attack pattern can be identified and the counterattack can be improved.

关键词： 3D gyro sensor Angular velocity Cross-correlation Boxing

来源：评论

学校读者我要写书评

暂无评论

Creating granular learning object towards reusability of Learning Object in e-learning context

Creating granular learning object towards reusability of Lea...

引用

International Conference on Electrical engineering and Informatics, ICEEI

作者： Siti Fadzilah Mat Noor Norazah Yusof Siti Zaiton Mohd Hashim Universiti Kebangsaan Malaysia Bangi Selangor MY Software Engineering Department Faculty of Computer Science & Information System University Technology of Malaysia Universiti Teknologi Malaysia Skudai Johor MY

Learning Object (LO) is one of the main research topics in the e-learning community in the recent years, and most researchers pay attention to the issue of Learning Object Reusability. The most obvious motivation is the economic interest of reusing learning material instead of repeatedly authoring it. In this paper we present the process of creating granular learning object for enabling the reusing of LO in e-Learning context. Reusability requires the LO to be in a fine-grain form because raw media elements are often much easier to reuse then aggregate assemblies. In other words, as the LO size decreases (lower granularity), its potential for reuse increases. A prototype of learning objects repository that contain granular LO has been developed to show the process of granularizing LO. Each of existing LO will be extracted into granular element with the metadata and the system generated unique id for each LO based on its identifier (URL of LO) and save automatically the metadata contain in the LO. These metadata will be used for searching and retrieval process of the granule LO.

关键词： Materials Electronic learning XML Economics Context Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Using P2P Networks to Repair Packet Losses in Digital Video Broadcasting systems

Using P2P Networks to Repair Packet Losses in Digital Video ...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Yung-Tsung Weng Ce-Kuen Shieh Tzu-Chi Huang Yu-Ben Miao Department of Management Information System Far East University Tainan Taiwan Institute of Computer and Communication Engineering Department of Electrical Engineering National Cheng Kung University Tainan Taiwan Department of Electric Engineering Lunghwa University of Science and Technology Taoyuan Taiwan Information and Communications Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan

Digital multimedia broadcasting services require resiliency against signal fading due to signal encounters with bad weather, terrain obstructions, such as tree, building, etc. There are several solutions that use peer-to-peer network to repair packet losses. But they have some shortcomings such as long lookup latency, control message overhead, flash crowd problem and low chunk availability. In this paper we propose a novel solution that considers load distribution in structured peer-to-peer networks and repairing packet losses in short lookup latency. Our proposed solution doesn't need to modify the codec technology for multimedia stream. Our proposed solution can achieve load evenly distributed, high chunk availability, short lookup latency and low control message overhead by using peer-to-peer network to repair packet losses in digital multimedia broadcasting systems.

关键词： Peer to peer computing Digital video broadcasting Media Message systems Streaming media Receivers Multimedia communication

来源：评论

学校读者我要写书评

暂无评论

Quantum-limited phase-matching effect in a Λ-type laser system

引用

Physical Review A 2011年第6期83卷 063846-063846页

作者： Deshui Yu Jingbiao Chen Department of Applied Physics The University of Tokyo Bunkyo-ku Tokyo 113-8656 Japan Institute of Quantum Electronics and State Key Laboratory of Advanced Optical Communication System & Network School of Electronics Engineering & Computer Science Peking University Beijing 100871 P.R. China

The theory of a quantum-limited phase-matching effect in a Λ-type lasing system is studied in detail based on the quantum Langevin approach. Two quasimonochromatic fields are directly generated based on two lasing transitions. We find that the coherence between two lasers can well exceed the linewidth of either laser field. This result denotes that two field phases match each other although either laser field has a high phase fluctuation. Unlike the phase-matching effect based on atomic absorption, the final coherence between two laser fields here is not limited by saturation broadening, and the higher laser intensities lead to a higher coherence. Additionally, based on a linear stability analysis, we find that the instability of the field steady state can substantially restrict the occurrence of this phase-matching effect in the bad-cavity limit for a high pump rate. We also discuss the spectrum of amplitude fluctuations of output fields, and the result shows that the squeezing of amplitude fluctuations at low frequencies for a single field oscillating inside the cavity is damaged in the case of two fields oscillating.

关键词： LASERS LIGHT amplifiers OPTOELECTRONIC devices NONLINEAR optics BASES (Linear topological spaces)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：