Search

Your search keyword '"Yang, Jianzhong"' showing total 19 results
Start Over Author "Yang, Jianzhong" Publisher ieee
19 results on '"Yang, Jianzhong"'

6. Track 3D Coordinate Fast Measurement Algorithm Based on Trajectory Method

Author

Zhao Yufei, Zhang Hang, Shao Yinxu, and Yang Jianzhong

Subjects
Measure (data warehouse), Smart grid, Computer science, business.industry, Trajectory method, Rail inspection, ComputerApplications_COMPUTERSINOTHERSYSTEMS, Control engineering, State (computer science), Track (rail transport), business, Automation, Fast measurement
Abstract

With its fast, smooth and comfortable riding environment, high-speed rail has become the preferred travel tool for people. In order to guarantee the safe operation of high-speed railway, the geometrical state of high-speed railway must be tested. However, the existing detection methods and equipment are slow to measure, which can not meet the requirements of daily operation or maintenance of high-speed railway. For this purpose, this paper proposes a fast measurement method based on relative measurement and absolute measurement, which solves the problem of slow speed of external geometry parameters of the existing rail inspection equipment.

Published
2018

11. Safety Assessment Research of Wheel Brake System Based on CPN

Author

Duan Xiaojing, Yang Jianzhong, and Luo Yunlin

Subjects
Engineering, business.industry, Airworthiness, Brake, Static analysis, Petri net, business, Automotive engineering, Reliability engineering
Abstract

Safety analysis is an important method of compliance demonstration for airworthiness regulation. It describes the foundation and application of CPN. Some features of CPN model are introduced and the future of CPN is predicted. The article sets up a CPN model based on WBS(Wheel Brake System), and make a contrast of CPN and FTA. It uses CPN model in the safety analysis process, which overcomes the shortcomings of the static analysis features of the FTA.

Published
2010

12. The noise elimination of the image based on otsu

Author

Dai Xuan, Yang Jianzhong, Liang Tao, and Zhang Xian-quan

Subjects
Difference of Gaussians, business.industry, Denoising algorithm, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Normalization (image processing), Pattern recognition, Image processing, Noise elimination, Data_CODINGANDINFORMATIONTHEORY, Image segmentation, Grayscale, Computer Science::Graphics, Computer Science::Computer Vision and Pattern Recognition, Computer Science::Multimedia, Computer vision, Artificial intelligence, business, Image based, ComputingMethodologies_COMPUTERGRAPHICS, Mathematics
Abstract

In the image processing, this paper proposed a new denoising algorithm for scanning images. The basic idea was that each grayscale probability was computed. In order to prevent the probability is too small, using 1 minus the grayscale probability, and with each grayscale corresponding between-cluster variance to multiply. Finally, let the gray value that made the result was the biggest grayscale as optimal threshold. Using optimal threshold to discriminate the foreground and background shadow, removed scanning images from the shadows. Experiments showed that the denoising algorithm had good effect, but also it was very well to protect the details.

Published
2010

13. Nonlinear predictive control for SRM based on TSE

Author

Yang Jianzhong and Huo Lihua

Subjects
Engineering, Model predictive control, Hardware_MEMORYSTRUCTURES, Artificial neural network, business.industry, Control theory, Control system, Torque, Angular velocity, Control engineering, Nonlinear control, business, Switched reluctance motor
Abstract

A novel scheme for nonlinear predictive control of Switched Reluctance Motor(SRM) based on Target State Equations (TSEs) is proposed in this paper. According to the nonlinear model of SRM, the offsets of the torque and angular speed of SRM is defined as TSEs by applying the nonlinear control theory. Based on TSEs and predictive control theory, a nonlinear predictive control for SRM control system is designed. Using the torque and angular speed as feedback variables, a nonlinear predictive control law is got. The designed controller is validated by software simulation and hardware experiment.The results of simulation and experiment show that the scheme has excellent dynamic and static performances, and good effects for restraining the ripple of torque of SRM simultaneously.

Published
2009

18. Efficient BOF Generation and Compression for On-Device Mobile Visual Location Recognition.

Author

Guan, Tao, He, Yunfeng, Duan, Liya, Yang, Jianzhong, Gao, Juan, and Yu, Junqing

Subjects
MOBILE geographic information systems, ACCURACY of information, INFORMATION retrieval, SEARCH algorithms, VECTOR quantization
Abstract

Existing mobile visual location recognition (MVLR) applications typically rely on bag-of-features (BOF) representation, which shows superior performance in retrieval accuracy. However, although the BOF framework is promising, it is not compact enough for on-device MVLR. The authors have made two contributions to the design of a BOF-based on-device MVLR system. First, to generate BOF descriptors, they propose a memory-efficient approximate nearest-neighbor search algorithm by combining residual vector quantization (RVQ) and tree-structured RVQ (TSRVQ). Second, they implemented a GPS-based and heading-aware RankBoost algorithm to reduce the dimensionality of the BOF descriptors. The authors evaluate the effectiveness of the proposed algorithms on an HTC mobile phone. Their work applies to on-device MVLR in city-scale workspaces. [ABSTRACT FROM AUTHOR]

Published
2014
Full Text
View/download PDF

19. On-Device Mobile Visual Location Recognition by Integrating Vision and Inertial Sensors.

Author

Guan, Tao, He, Yunfeng, Gao, Juan, Yang, Jianzhong, and Yu, Junqing

Abstract

This paper deals with the problem of city scale on-device mobile visual location recognition by fusing the inertial sensors and computer vision techniques. The main contributions are as follows: Firstly, we design an efficient vector quantization strategy by combining the Transform Coding (TC) and Residual Vector Quantization (RVQ). Our method can compress a visual descriptor into only several bytes while providing reasonable searching accuracy, which makes the managing of city scale image database directly on mobile devices come true. Secondly, we integrate the information from inertial sensors into the Vector of Locally Aggregated Descriptors (VLAD) generation and image similarity evaluation processes. Our method is not only fast enough for on-device implementation, but it also can improve the location recognition accuracy obviously. Thirdly, we also release a set of 1.295 million geo-tagged street view images with the information from inertial sensors, as well as a difficult set of query images. These resources can be used as a new benchmark to facilitate further research in the area. Experimental results prove the validity of the proposed methods for on-device mobile visual location recognition applications. [ABSTRACT FROM PUBLISHER]

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results