|
Robust water hazard detection for autonomous off-road navigation
Tuo-zhong YAO, Zhi-yu XIANG, Ji-lin LIU
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 786-793.
https://doi.org/10.1631/jzus.A0820198
Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly detect different kinds of water hazards for autonomous navigation. Our algorithm combines traditional machine learning and image segmentation and uses only digital cameras, which are usually affordable, as the visual sensors. Active learning is used for automatically dealing with problems caused by the selection, labeling and classification of large numbers of training sets. Mean-shift based image segmentation is used to refine the final classification. Our experimental results show that our new algorithm can accurately detect not only ‘common’ water hazards, which usually have the features of both high brightness and low texture, but also ‘special’ water hazards that may have lots of ripples or low brightness.
|
|
Application of automated image analysis to the identification and extraction of recyclable plastic bottles
Edgar SCAVINO, Dzuraidah Abdul WAHAB, Aini HUSSAIN, Hassan BASRI, Mohd Marzuki MUSTAFA
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 794-799.
https://doi.org/10.1631/jzus.A0820788
An experimental machine vision apparatus was used to identify and extract recyclable plastic bottles out of a conveyor belt. Color images were taken with a commercially available Webcam, and the recognition was performed by our homemade software, based on the shape and dimensions of object images. The software was able to manage multiple bottles in a single image and was additionally extended to cases involving touching bottles. The identification was fulfilled by comparing the set of measured features with an existing database and meanwhile integrating various recognition techniques such as minimum distance in the feature space, self-organized maps, and neural networks. The recognition system was tested on a set of 50 different bottles and provided so far an accuracy of about 97% on bottle identification. The extraction of the bottles was performed by means of a pneumatic arm, which was activated according to the plastic type; polyethylene-terephthalate (PET) bottles were left on the conveyor belt, while non-PET bottles were extracted. The software was designed to provide the best compromise between reliability and speed for real-time applications in view of the commercialization of the system at existing recycling plants.
|
|
Efficient page layout analysis on small devices
Eun-jung HAN, Chee-onn WONG, Kee-chul JUNG, Kyung-ho LEE, Eun-yi KIM
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 800-804.
https://doi.org/10.1631/jzus.A0820842
Previously we have designed and implemented new image browsing facilities to support effective offline image contents on mobile devices with limited capabilities: low bandwidth, small display, and slow processing. In this letter, we fulfill the automatic production of cartoon contents fitting small-screen display, and introduce a clustering method useful for various types of cartoon images as a prerequisite stage for preserving semantic meaning. The usage of neural networks is to properly cut the various forms of pages. Texture information that is useful for grayscale image segmentation gives us a good clue for page layout analysis using the multilayer perceptron (MLP) based x-y recursive algorithm. We also automatically frame the segment MLP using agglomerative segmentation. Our experimental results show that the combined approaches yield good results of segmentation for several cartoons.
|
|
Bi-dimension decomposed hidden Markov models for multi-person activity recognition
Wei-dong ZHANG, Feng CHEN, Wen-li XU
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 810-819.
https://doi.org/10.1631/jzus.A0820388
We present a novel model for recognizing long-term complex activities involving multiple persons. The proposed model, named ‘decomposed hidden Markov model’ (DHMM), combines spatial decomposition and hierarchical abstraction to capture multi-modal, long-term dependent and multi-scale characteristics of activities. Decomposition in space and time offers conceptual advantages of compaction and clarity, and greatly reduces the size of state space as well as the number of parameters. DHMMs are efficient even when the number of persons is variable. We also introduce an efficient approximation algorithm for inference and parameter estimation. Experiments on multi-person activities and multi-modal individual activities demonstrate that DHMMs are more efficient and reliable than familiar models, such as coupled HMMs, hierarchical HMMs, and multi-observation HMMs.
|
|
Adaptive fractional window increment of TCP in multihop ad hoc networks
Liang-hui DING, Wen-jun ZHANG, Xin-bing WANG, Liang QIAN, You-yun XU
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 820-827.
https://doi.org/10.1631/jzus.A0820380
We propose an adaptive fractional window increasing algorithm (AFW) to improve the performance of the fractional window increment (FeW) in (Nahm et al., 2005). AFW fully utilizes the bandwidth when the network is idle, and limits the operating window when the network is congested. We evaluate AFW and compare the total throughput of AFW with that of FeW in different scenarios over chain, grid, random topologies and with hybrid traffics. Extensive simulation through ns2 shows that AFW obtains 5% higher throughput than FeW, whose throughput is significantly higher than that of TCP-Newreno, with limited modifications.
|
|
An XPath-based OWL storage model for effective ontology management in Semantic Web environment
Jinhyung KIM, Dongwon JEONG, Doo-kwon BAIK
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 843-857.
https://doi.org/10.1631/jzus.A0820355
With the rapid growth of the Web, the volume of information on the Web is increasing exponentially. However, information on the current Web is only understandable to humans, and this makes precise information retrieval difficult. To solve this problem, the Semantic Web was proposed. We must use ontology languages that can assign data the semantics for realizing the Semantic Web. One of the representative ontology languages is the Web ontology language OWL, adopted as a recommendation by the World-Wide Web Consortium (W3C). OWL includes hierarchical structural information between classes or properties. Therefore, an efficient OWL storage model that considers a hierarchical structure for effective information retrieval on the Semantic Web is required. In this paper we suggest an XPath-based OWL storage (XPOS) model, which includes hierarchical information between classes or properties in XPath form, and enables intuitive and effective information retrieval. Also, we show the comparative evaluation results for the performance of the XPOS model, Sesame, and the XML file system-based storage (XFSS) model, in terms of query processing and ontology updating.
|
|
Mixed nonlinear dynamic voltage phasor tracing method based on WAMS/SCADA
Xiao-gang CHEN, Yong-hui YI, Wei WANG, Quan-yuan JIANG, Chuang-xin GUO, Yi-jia CAO
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 868-876.
https://doi.org/10.1631/jzus.A0820150
By considering the static voltage characteristic of the load, we propose a WAMS/SCADA mixed nonlinear method to estimate the voltage of unobservable buses caused by topology change or phasor measurement unit (PMU) malfunction in a power system. By modeling the load characteristic with data from SCADA, we employed the Gauss-Seidel method to solve the nonlinear equations and estimate the voltage of unobservable buses with the high precision voltages of neighboring buses measured by a PMU. Simulations were carried out on the IEEE 39-bus system, and the results show that this novel method can dynamically and accurately trace the variation of the voltage phasor of the unobservable buses.
|
|
An immune-tabu hybrid algorithm for thermal unit commitment of electric power systems
Wei LI, Hao-yu PENG, Wei-hang ZHU, De-ren SHENG, Jian-hong CHEN
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 877-889.
https://doi.org/10.1631/jzus.A0820607
This paper presents a new method based on an immune-tabu hybrid algorithm to solve the thermal unit commitment (TUC) problem in power plant optimization. The mathematical model of the TUC problem is established by analyzing the generating units in modern power plants. A novel immune-tabu hybrid algorithm is proposed to solve this complex problem. In the algorithm, the objective function of the TUC problem is considered as an antigen and the solutions are considered as antibodies, which are determined by the affinity computation. The code length of an antibody is shortened by encoding the continuous operating time, and the optimum searching speed is improved. Each feasible individual in the immune algorithm (IA) is used as the initial solution of the tabu search (TS) algorithm after certain generations of IA iteration. As examples, the proposed method has been applied to several thermal unit systems for a period of 24 h. The computation results demonstrate the good global optimum searching performance of the proposed immune-tabu hybrid algorithm. The presented algorithm can also be used to solve other optimization problems in fields such as the chemical industry and the power industry.
|
|
Investigations on control algorithm of steady-state cornering and control strategy for dynamical correction in a steer-by-wire system
Ying XU, Chang-fu ZONG, Hsiao-hsiang NA, Lei LIU
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 900-908.
https://doi.org/10.1631/jzus.A0820173
To improve the handling performance of a steer-by-wire (SBW) vehicle, a series of control logics are proposed. Firstly, an algorithm for enhancing the maneuvering in steady-state cornering is presented. On this basis, two categories of control strategies are used to dynamically correct and compensate the transient state steering responses and vehicle behaviors. Simulator tests including subjective evaluations and virtual field tests are both conducted to make comprehensive investigations on the series of control logics. The subjective evaluations demonstrate that the SBW vehicle with a specifically selected value of steering sensitivity tends to be more desirable for driving than a conventional one in which a fixed steering ratio exists. The virtual field tests indicate that the control strategies for dynamical correction and compensation could effectively improve the handling performances of an SBW vehicle by reducing the work load of drivers, enhancing the track-holding performance, and improving steering response properties.
|
|
Low-cost fault tolerance in evolvable multiprocessor systems: a graceful degradation approach
Shervin VAKILI, Sied Mehdi FAKHRAIE, Siamak MOHAMMADI, Ali AHMADI
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(6): 922-926.
https://doi.org/10.1631/jzus.A0820803
The evolvable multiprocessor (EvoMP), as a novel multiprocessor system-on-chip (MPSoC) machine with evolvable task decomposition and scheduling, claims a major feature of low-cost and efficient fault tolerance. Non-centralized control and adaptive distribution of the program among the available processors are two major capabilities of this platform, which remarkably help to achieve an efficient fault tolerance scheme. This letter presents the operational as well as architectural details of this fault tolerance scheme. In this method, when a processor becomes faulty, it will be eliminated of contribution in program execution in remaining run-time. This method also utilizes dynamic rescheduling capability of the system to achieve the maximum possible efficiency after processor reduction. The results confirm the efficiency and remarkable advantages of the proposed approach over common redundancy based techniques in similar systems.
|
18 articles
|