Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)

+ Advanced search
226 articles

The BSN application and realization of FPGA system with a rapid signal compression algorithm

Sun Hao, Chen Wei
The applications of BSN (Body Sensor Network) require the wearable computing system’s power consumption as low as possible. Compared to other components, the wireless communication link is the most power demanding part of the BSN. While effective compression algorithm can sharply cut the data volume...

A PCA-based Face Recognition Method by Applying Fast Fourier Transform in Pre-processing

Zhang Dehai, Ding Da, Li Jin, Liu Qing
Principal Component Analysis (PCA) is a well-studied method in face recognition. Noticing that few researches focus on pre-processing of images, which will also improve the performance of feature extraction of PCA algorithm, we present an improved approach of PCA based face recognition algorithm using...

A Visual Method to Find Performance Bottlenecks for Mobile Web and Hybrid Applications

Cai Tao, Li Li, Chou Wu, Yan Ching Man, Fu Haifeng, Wah Wong Ka, Wu Kangheng, Lei Zhibin
It is very difficult to test web performance on a smart mobile, where performance is often an issue, because of lacking such kinds of tools. In this paper, we provide a new method to let mobile web developers to find the performance bottlenecks of their web and hybrid applications easily. The method...

Study on Soldering Technology for Laser Rod by Finite Element Method

Ming-ming Hao, Guo-guang Lu, Zhi-feng Lei, Yun Huang, Yunfei En
With the increase demand of high power, high efficient and good beam quality solid-state lasers, thermal management become more important for the lasers. Thermal resistance between laser crystal and heat sink can be effectively reduced by soldering technology, but the technology might induce huge heat...

A Packet-layer Quality Assessment System for VoIP

Jiang Liangliang, Yang Fuzheng
A packet-layer quality assessment system is proposed to monitor the quality of VoIP service in this paper. The proposed system is composed of three modules, where the quality assessment module evaluates the voice quality in terms of the information extracted by the packet header analysis module and silence...

Classifications Modification Based FCM with Spatial Information for Image Segmentation

Li Zhao, Zhou Xiaoming
Image segmentation is the foundation of computer vision and pattern recognition but is still a challenging problem. FCM has been used in image segmentation many years but its problem that is sensitive to noise still cannot be solved effectively. This paper proposes an improved algorithm that incorporates...

Image Encryption Using Keystreams Dependent on Plain-images

Ye Ruisong, Fu Rong, Zeng Shaojun, Lai Chuting, Ma Junming
A novel chaos-based image encryption scheme is proposed in this paper. The encryption scheme consists of one permutation process and one diffusion process, in which the key streams are both one-time keys in the sense that they are dependent on plain-images. Several merits of the proposed image encryption...

An Interactive Control System for 3D Display Using Hidden Markov Model

Xu Liujing, Cao Xun, Deng Xiangdong, Wang Yuanqing, Jin Jing
This paper describes a system fulfilling interactive 3D-TV control. The system captures the position of the users’ right hand, and then records and feature-extracts the trajectory of the gestures. After that, the movement of the users’ input gestures can be recognized for interactive 3D-TV operations...

Improved Image Resizing using Seam Carving and scaling

Zhang Yan, Sun Jonathan Z., Peng Jingliang
Seam Carving, the popular content-aware image resizing technique, removes or inserts seams of low energy iteratively without sufficiently considering their impact on the global visual quality of the image. However, sometimes seams pass through the regions of interest (ROIs) with low energy and distort...

The Detection of Container Body Base on Multiple Features

Ziyi Chen, Yinxi Zheng, Junhao Wang, Lisheng Wang
Since the 20th century, the global container transportation is developing very quickly. Unfortunately, although many container terminals have adopted modern management, the character recognition of containers still need the operation of manual read and manual record, which will not only cause the operation...

An Adapted Multi-way Tree with Holder-chain for Large Scale P2P VoD System

Liu Pingshan, Huang Guimin, Zhou Ya, Zhang Huibing, Liu Siyun
Peer-to-Peer Video-on-demand (P2P VoD) systems have attracted great interest in research community. Many hybrid methods have been proposed to provide high-quality video-on-demand services to support VCR-like operations, which can scale to large population of users. In this paper, we propose a hybrid...

K - means multi-threshold image segmentation based on firefly algorithm

Yang Jie, Yang Yang, Yu Weiyu, Feng Jiuchao
This paper presents multi-threshold image segmentation approach based on K-means and firefly algorithm. This approach first use the firefly algorithm based on the characteristics of the groups search for optimization to obtain threshold as K-means initial clustering center. It could effectively overcome...

An Improved Method of Crowd Counting Based on Regression

Jiang Mei, Zhao Yanyun
An improved method of crowd counting based on regression is proposed to support intelligent management over crowd in video surveillance systems. According to the fact that human body has an articulate structure and complicated contours of shape, we propose a new low-level feature, the number of corner...

An Image Edge Detection Method Based on Mathematical Morphology

Xiaoping Ji, Haibin Zhang, Dazhi Zhang, Boying Wu
We present two kinds of improved morphological edge detectors according to: the characteristics of the classical morphological operators and the disadvantages of the single structural elements selected. The structure of the first improved operator considers multi-structural elements and omni-directional...

A new public key cryptograhpy system based on hyperbolic curve over finite field

Liu Xiaoqin, Zheng Qi, Yang Jianhua, Wang Lu, Zhang Tong, Li Tao, Wang Rui
In this paper, we propose a new technology that improves Diffie-Hellman’s safeness and keeps its good property.The technology is called “Hyperbolic Curve Cryptography System” (HCCS) which is designed on hyperbolic curve over finite filed. HCCS has a solid Abel group structure whose order is diverse over...

Adaptive Fusion Color and Haar-like Feature Object Tracking Based on Particle Filter

Xian-Bing Ma, Shui-Fa Sun, Yin-Shi Qin, Song Hu, Bang-Jun Lei
The conventional kernel color histogram based particle filter (CHGPF) object tracking algorithm suffers from cluttered backgrounds and illumination changes and results in tracking lost easily. In this paper, a particle filter based object tracking algorithm fusing color and haar-like feature (CHAPF)...

A method of TV Logo Recognition based on SIFT

Pan Da, Shi Ping
TV logo is an important symbol of TV station. Automatic identification of TV logo can be used in television monitoring and media assets management. By analyzing the characteristics of TV logos, a new algorithm for TV logo recognition is proposed in this paper. First of all, the TV logo information is...

Design and Storage Optimization of GPU-based Parallel Program of Image Registration for Remote Sensing

Zhou Haifang, Xu Rulin, Jiang Jingfei
Image registration is a crucial step of many remote sensing related applications. As the scale of data and complexity of algorithm keep growing, image registration faces great challenges of its processing speed. In recent years, the computing capacity of GPU improves greatly. Taking the benefits of using...

Fast Abdominal Medical Image Registration Based on Modified SIFT

Beilei Wang, Lu Meng, Jie Xu, Ye Shao
SIFT is an excellent descriptor to features in medical images. However, the algorithm to achieve SIFT is tedious and takes a long time. To cope with this, we combined image integration and image region partition and proposed a modified SIFT descriptor capable of describing the global energy information...

Effect of the Number of Codebook and MFCC on Chinese Isolated Words Recognition

De Liu, Mingjiang Wang, Zejun Wu
This paper aims to design and optimize the algorithm of Chinese isolated words speech recognition, to improve the recognition accuracy and robustness. Mel-Frequency Cepstral Coefficient (MFCC) has been widely used in the art-of-state speech recognition since it considers the characteristics of human...

Objective No-reference Stereo Video Quality Assessment Research

Li Yan, Yang Yu
With the development of the 3d industry, 3d video quality assessment method has become one of the hot spots. But now the main research directions are concentrated in reference stereoscopic video evaluation method and subjective evaluation method, which also have made some progress. Objective no-reference...

Random Multiple Access Protocol combined Binary Tree Conflict-resolving Algorithm and the 1-persistent CSMA Protocol

Zhao Yifan, Ding Hongwei, Gao Yangshui, Guo Yingying, Nan Jing, Yu Pingping
This paper presents a new random multiple access control protocol – 1-persistent CSMA control protocol based on improved binary tree conflict resolution algorithm. First, the paper gives an outline of 1-persistent CSMA and the binary tree conflict-resolving algorithm by building a mathematical model...

Image Mosaic Algorithm Based on Vertical Distance of Edges

Wu Yongqi, Hu Xizhi, Jiang Libiao, Chen Zemao
This paper presents a new algorithm of automatic image mosaic, which generate mosaic image by comparing the vertical distance of edges in two neighboring images. This algorithm selects points to be matched by statistical features of the images before the actual matching stage, reducing the amount of...

Spatial-temporal features for smoke detection on video images

Ma Li
Three temporal-space features are proposed in this paper on video images for smoke detections on the issue of dynamic textures, motion patterns and contour variations. Considering that the previous methods for smoke detection provides global descriptions on dynamic features, but its illustrations do...

Study on the Separation Technology of Temperature and Emissivity Data Based on the Airborne Thermal Infrared Image

Wang Junhu
Since the high-resolution airborne thermal infrared imaging spectrometer is used to civilian field, it shows attractive application prospect in the field of objects recognition. Taking an area for example, the paper carries out the technology research for temperature and emissivity separation, based...

An Audio Blind Watermarking Algorithm by Modifying the DWT Low-frequency Coefficients

Chen Xuesong, Li Haotian, Bu Guanglong, Bi Hongbo
An audio watermarking algorithm by modifying the low-frequency coefficients of DWT is discussed in this paper. Audio signal is divided into many sections, whose quantity is equal to the size of the watermark. The maximal value and the second maximal value of DWT low frequency coefficient can be found...

A Method of Caption Detection in News Video

Huang He, Shi Ping
News video is one of the most important media for people to get information. However, it is an urgent problem to find the useful information from a huge amount of news video efficiently and correctly. The caption in news video highly summarizes the related news story and can be used for effective retrieval....

Gesture browsing method for geological data

Chen Huang, Jianhua Li, Hanchao Yu, Junfa Hanchao, Jianghai Shen
In big screen environment,careful observationof geological data is significant forgeological workers. However,traditional mouse is not suitable for free operation in big screen environment.Influenced by illumination, background and some other things, gesture recognition based on ordinary camera isneither...

Research of new 3D resistivity prospecting system electrical measuring device

Xu Haning, Xiao Hui, Li Zhenggen, Zeng Zhengjun, Deng Juzhi
In the exploration area, traditional high-density electrical prospecting was designed for 2D resistivity acquisition, the accuracy and sampling rate was low. A new type 3D resistivity acquisition system was designed in this thesis. Apparent resistivity data can be acquired by the new substation System...

Using Edge SIFT Points for Simple Shape Object Matching

Fang Han, Yuan Yule, Shen Ling, Zhao Yong
SIFT the well-known image recognition algorithm performs reliable matching between different views of an object even it is rotated, in different scales, or has different brightness than of the original image. But in our button match works, the SIFT points detected in simple object may be few, and the...

A Vehicle Counting Algorithm Using Foreground Detection in Traffic Videos

Zhang Linbo, Wang Feng, Hu Ming, Shi Lei, Liang Long
Vehicle counting in traffic videos plays an essential role in traffic surveillance system. It can provide some important traffic information such as congestion level and statistical analysis of traffic flow. In this paper, a novel vehicle counting strategy, which is based on foreground detection algorithm...

Blood Pressure and Heart Rate Changes in Different Body Figures during Submaximal Exercise

Yi Rujia, Zhang Jianan, Ye Xiaolu, Xie Yong, Zou Fengyuan
In order to analyze blood pressure and heart rate changes during submaximal exercise in different body figures, 36 female college students underwent treadmill exercise with heart rate being monitored and blood pressure measured before, immediately after and 10 minutes after exercise. Correlation analysis...

Reference-Driven Compressed Sensing MR Image Reconstruction with Partially Known Support and Group Sparsity Constraints

Dong Yize, Du Huiqian, Zhao Di, Han Yu, Mei Wenbo
Applying compressed sensing (CS) to magnetic resonance imaging (MRI) makes it possible to reconstruct a MR image from undersampled data. Traditional CS based MR image reconstruction schemes only use the signals’ sparsity in an appropriate transform domain to reduce sampling rate. This paper proposes...

Research on the realization of 3D urban traffic simulation system

Cao ZhongHua, Tang QuanHua, Liu YuangChun
This paper makes an intensive study of the realizations and related key technologies in the 3D urban traffic simulation system. First, the system can quickly edit the scenes of the 3D urban, including buildings, roads, etc. It describes the roads using the graph structure, then, the constrained Delaunay...

NMF based speech and music separation in monaural speech recordings with sparseness and temporal continuity constraints

Tu Ming, Xie Xiang, Jiao Yishan
This paper proposes a semi-supervised approach of speech and music separation in monaural speech recordings based on non-negative matrix factorization (NMF). Considering the scenario that the genre of background music is known, music basis vectors are randomly picked from the magnitude of short time...

Integrating Multiagent Systems into Virtual Worlds

McClure Grant, Virwaney Sandeep, Lin Fuhua
Incorporating autonomy and intelligence into virtual worlds to build an engaging virtual environment for applications such as serious games is becoming more desirable. There are challenges in integrating these systems including concerns with synchronization, communication, monitoring, efficiency, and...

2D to 3D Conversion in 3DTV Using Depth Map Generation and Virtual View Synthesis

Jung Cheolkon, Zhu Xiaohua, Wang Lei, Sun Tian, Han Mingchen, Hou Biao, Jiao Licheng
2D to 3D conversion is an important task in 3DTV due to the lack of 3D contents. In this paper, we propose a novel framework of the 2D to 3D video conversion. The proposed framework consists of two main stages: depth map generation and virtual view synthesis. In the depth map generation, motion and relative-height...

Electronic Image Stabilization based on Motion Classification

Juanjuan Zhu, Baolong Guo
A novel electronic image stabilization based on motion classification is presented. It achieves image stabilization with high accuracy in complicated camera motion. Firstly, the feature points are selected evenly using the Harris operator and then matched based on the feature window. Hence, the corresponding...

Object-oriented Classification Technique for Extracting Abandoned Farmlands by Using Remote Sensing Images

Wang Shixin, Li Wenjun, Zhou Yi, Wang Futao, Xu Qilong
The abandonment phenomenon has become one of the most serious problems in China in the last 20 years. Preventing the farmland from abandonment is an urgent issue for authority. Thus, abandoned farmland monitoring is very important. The conventional field investigation approach of abandonment status cannot...

An enhancement of ladar image based on SFLA algorithm

Zhen Zeng, Lin Lu, Yuanqin Wang
Because resulting image of laser radar echo signal is weak, it is necessary to improve the relative gray scale of each point. This article proposed an adaptive image enhancement algorithm based on FSFLA (A Fast Shuffled Frog Leaping Algorithm). This algorithm is based on a fast shuffled frog leaping...

The Implementation of Fractional Pixel ME in H.264 Video Encoder

Zuo Shikai, Wang Mingjiang, Wu Zejun, Xiao Liyi
This paper first introduce the H.264 video codec standard briefly, then analyze the inter-frame motion estimation in H.264. After that we propose an optimaized algorithm and the corresponding architecture. A pipeline-architecture was proposed with scaled searching algorithm based on the analysis to the...

Fast Adaptive Depth Estimation Algorithm Based on K-means Segmentation

Dong Xin, Wang Guozhong, Fan Tao, Li Guoping, Zhao Haiwu, Teng Guowei
A fast depth estimation algorithm based on the K-means image segmentation is proposed in this paper. Traditional global-based depth estimation methods using graph-cuts made good performance on the depth map estimation, however, the time cost is a big problem for real time application. A fast segment-based...

The Design of a Hardware Thread Manager for a Polymorphic Multimedia Processor

Qian Bowen, Li Tao, Yang Ting
This paper proposes a hardware thread manager for the polymorphic parallel processor. The thread manager supports the MIMD mode with 8 threads and SIMD mode with multiple threads using the SIMD controllers in a unified approach to manage two operating modes to achieve a mixture of three types of parallel...

Road Network Extraction and Recognition Using Color Clustering From Color Map Images

Lulu Zhang, Ning He, Cheng Xu
This paper use a color image digital map of Beijing area to do road feature extraction.It takes full advantage of color map by using clustering to get road network highlighted first, and then picks road network out through denoising, and does post processing works by using mathematical morphology algorithms...

A fast on-line boosting tracking algorithm based on cascade filter of multi-features

Song Hu, Shui-Fa Sun, Xian-Bing Ma, Yin-Shi Qin, Bang-Jun Lei
Exhaustive search in local area around the object is used for tracking in the conventional Haar-like feature based on-line boosting tracking methods (HBT). Tracking is frequently failed and can hardly find the object again when the object moves fast or occluded completely. In addition, on-line tracking...

Study on new gray transformation of infrared image based on visual property

Dai Shaosheng, Li Xingfu, Du Zhihui, Zhang Bin, Huang Xinlin
Since the infrared image has disadvantages such as narrow gray distribution, low contrast and blurred vision effects, a new method of gray transformation of infrared image based on human visual property is proposed. The method aims to transform the gray distribution of infrared object to the sensitive...

A Dynamic Transmission Method for Scalable Video with Unequal Error Protection

Zheng Xi, Xue Yonglin
In this paper, we propose a dynamic transmission method for scalable video with unequal error protection (UEP). Forward error correction (FEC) is used in the UEP scheme. FEC codes, such as Reed-Solomon (RS) codes, are allocated to different layers of scalable video according to their importance. The...

Attractive Events Detection in Soccer Videos Based on Identification of Shots

Tian Fang, Shi Ping
The necessity of efficient identification and classification of shots in a soccer game ascends with the increasing popularity and quantity of soccer videos. This paper proposes an effective and real-time identifying system for attractive events, namely shooting shots in soccer video clips. Instead of...

A Novel Approach for Region-of-Interest Detection in Pornographic Images

Liu Yizhi, Zhou Dong, Liu Jianxun, Xie Hongtao, Yang Ying
Region-of-interest (ROI) detection plays an important role in filtering out pornographic images. Skin-color models, as a traditional approach, extract skin-color regions as ROI. However, the approach is difficult to differentiate between human skins and other objects with the skin-color. Furthermore,...

Separable Reversible Data hiding in Encrypted Images by n-nary Histogram Modification

Qian Zhenxing, Han Xiyu, Zhang Xinpeng
This work proposes a novel scheme of separable reversible data hiding for encrypted image using histogram modification. After the original image is en-crypted by the sender, the data-hider embeds the secret message into the encrypted image by a histogram modification and n-nary data hiding scheme. On...