Showing papers by "Xiangjian He published in 2013"

Energy Evaluation Model for an Improved Centralized Clustering Hierarchical Algorithm in WSN

Abstract: Wireless Sensor Networks (WSN) consists of battery-powered sensor nodes which collect data and route the data to the Base Station. Centralized Cluster-based routing protocols efficiently utilize limited energy of the nodes by selecting Cluster Heads (CHs) in each round. Selection of CHs and Cluster formation is performed by the Base Station. In each round, nodes transmit their location information and their residual energy to the Base Station. This operation is a considerable burden on these resource hungry sensor nodes. In this paper we propose a scheme whereby a small number of High-Energy nodes gather location information and residual energy status of the sensing nodes and transmit to the Base Station. This scheme eliminates CH advertisement phase in order to conserve energy. Based on the energy consumption by various types of nodes, we have derived an energy model for our algorithm which depicts the total energy consumption in the network.

Enhancing Lifetime and Quality of Data in Cluster-Based Hierarchical Routing Protocol for Wireless Sensor Network

Abstract: Wireless Sensor Network (WSN) performs energy extensive tasks and it is essential to rotate sensor nodes frequently so that Cluster Head selections can be made efficiently. In this paper, we aim to improve the lifetime of sensor network by using LEACH based protocols and efficiently utilizing the limited energy available in these sensor nodes. In sensor network, the amount of data delivered at the base station is not important but it is the quality of the data which is of utmost importance. Our proposed approach significantly improves the life time and quality of data being delivered at the base station in sensor network. We evaluate our proposed approach using different sets of node energy levels and in each case our approach shows significant improvement over existing cluster-based hierarchical routing protocols. We evaluate our scheme in terms of energy consumption, life time and quality of data delivered at the base station.

Text detection in born-digital images using multiple layer images

Abstract: In this paper, a new framework for detecting text from webpage and email images is presented. The original image is split into multiple layer images based on the maximum gradient difference (MGD) values to detect text with both strong and weak contrasts. Connected component processing and text detection are performed in each layer image. A novel texture descriptor named T-LBP, is proposed to further filter out non-text candidates with a trained SVM classifier. The ICDAR 2011 born-digital image dataset is used to evaluate and demonstrate the performance of the proposed method. Following the same performance evaluation criteria, the proposed method outperforms the winner algorithm of the ICDAR 2011 Robust Reading Competition Challenge 1.

Using swarm intelligence to optimize the energy consumption for distributed systems

Abstract: Large, distributed, network-based computing systems (also known as Cloud Computing) have recently gained significant interest. We expect significantly more applications or web services will be relying on network-based servers, therefore reducing the energy consumption of these systems would be beneficial for companies to save their budgets on running their machines as well as cooling down their infrastructures. Dynamic Voltage Scaling can save significant energy for these systems, but it faces the challenge of efficient and balanced parallelization of tasks in order to maximize energy savings while maintaining desired performance levels. This paper proposes our Simplified Swarm Optimization (SSO) method to reduce the energy consumption for distributed systems with Dynamic Voltage Scaling. The results of SSO have been compared to the most popular evolutionary Particle Swarm Optimization (PSO) algorithm and have shown to be more efficient and effective, reducing both the execution time for scheduling and makespan.

Robust object tracking using linear neighborhood propagation

Abstract: Object tracking is widely used in many applications such as intelligent surveillance, scene understanding, and behavior analysis. Graph-based semisupervised learning has been introduced to deal with specific tracking problems. However, existing algorithms follow- ing this idea solely focus on the pairwise relationship between samples and hence could decrease the classification accuracy for unlabeled samples. On the contrary, we regard tracking as a one- class classification issue and present a novel graph-based semi- supervised tracker. The proposed tracker uses linear neighborhood propagation, which aims to exploit the local information around each data point. Moreover, the manifold structure embedded in the whole sample set is discovered to allow the tracker to better model the target appearance, which is crucial to resisting the appearance variations of the object. Experiments on some public-domain sequen- ces show that the proposed tracker can exhibit reliable tracking performance in the presence of partial occlusions, complicated back- ground, and appearance changes, etc. © 2013 SPIE and IS&T (DOI:

Recent Advances on Graph-Based Image Segmentation Techniques

Abstract: Image segmentation techniques using graph theory has become a thriving research area in computer vision community in recent years. This chapter mainly focuses on the most up-to-date research achievements in graph-based image segmentation published in top journals and conferences in computer vision community. The representative graph-based image segmentation methods included in this chapter are classified into six categories: minimum-cut/maximum-flow model (called graph-cut in some literatures), random walk model, minimum spanning tree model, normalized cut model and isoperimetric graph partitioning. The basic rationales of these models are presented, and the image segmentation methods based on these graph-based models are discussed as the main concern of this chapter. Several performance evaluation methods for image segmentation are given. Some public databases for testing image segmentation algorithms are introduced and the future work on graph-based image segmentation is discussed at the end of this chapter. DOI: 10.4018/978-1-4666-1891-6.ch007

Generalized local N-ary patterns for texture classification

Abstract: Local Binary Pattern (LBP) has been well recognised and widely used in various texture analysis applications of computer vision and image processing. It integrates properties of texture structural and statistical texture analysis. LBP is invariant to monotonic gray-scale variations and has also extensions to rotation invariant texture analysis. In recent years, various improvements have been achieved based on LBP. One of extensive developments was replacing binary representation with ternary representation and proposed Local Ternary Pattern (LTP). This paper further generalises the local pattern representation by formulating it as a generalised weight problem of Bachet de Meziriac and proposes Local N-ary Pattern (LNP). The encouraging performance is achieved based on three benchmark datasets when compared with its predecessors.

TCTM: an evaluation framework for architecture design on wireless sensor networks

Abstract: This paper presents an evaluation framework for architecture designs on wireless sensor networks WSNs. We introduce a simple evaluation model: triangular constraint tradeoffs model TCTM to grasp the essence of the architecture design consideration under transient wireless media characteristic and stringent limitation on energy and computing resource of WSNs. Based on this evaluation framework, we investigate the existing architectures proposed in literature from three main competing constraint aspects, namely generality, cost, and performance. Two important concepts: performance efficiency and deployment efficiency are identified and distinguished in overall architecture efficiency. With this powerful abstract and simple model, we describe the motivations of major body of WSNs architectures proposed in current literature. We also analyse the fundamental advantage and limitations of each class of architectures from TCTM perspective. We foresee the influence of evolving technology to futuristic architecture design. We believe our efforts will serve as a reference to orient researchers and system designers in this area.

A Comprehensive Approach to Automatic Image Browsing for Small Display Devices

Abstract: Recently, small displays are widely used to browse digital images. While using a small display device, the content of the image appears very small. Users have to use manual zooming and panning in order to see the detail of the image on a small display. Hence, an automatic image browsing solution is desired for user convenience. In this chapter, a novel comprehensive and efficient system is proposed to browse high resolution images using small display devices by automatically panning and zooming on Region-of-Interests (ROIs). The challenge is to provide a better user experience on heterogeneous small display sizes. First of all, an input image is classified into one of the three different classes: close-up, landscape and other. Then the ROIs of image are extracted. Finally, ROIs are browsed based on different intuitive and study based strategies. Our proposed system is evaluated by subjective test. Experimental results indicate that the proposed system is an effective large image displaying technique on small display devices.