中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共9条，第1-9条

帮助

条数/页：排序方式：
	An improved hyperspectral classification algorithm based on back-propagation neural networks (EI CONFERENCE) 会议论文 OAI收割 2012 2nd International Conference on Remote Sensing, Environment and Transportation Engineering, RSETE 2012, June 1, 2012 - June 3, 2012, Nanjing, China 作者: Yu P.; Yu P. 收藏 \| 浏览/下载：34/0 \| 提交时间：2013/03/25 In this paper a new method is proposed to improve the classification performance of hyperspectral images by combining the principal component analysis (PCA) genetic algorithm (GA) and artificial neural networks (ANNs). First some characteristics of the hyperspectral remotely sensed data such as high correlation high redundancy etc. are investigated. Based on the above analysis we propose to use the principal component analysis to capture the main information existing in the hyperspectral images and reduce its dimensionality consequently. Next we use neural networks to classify the reduced hyperspectral data. Since the back-propagation neural network we used is easy to suffer from the local minimum problem we adopt a genetic algorithm to optimize the BP network's weights and the threshold. Experimental results show that the classification accuracy is improved and the time of calculation is reduced as well. 2012 IEEE.
	Neural network based online traffic signal controller design with reinforcement training (EI CONFERENCE) 会议论文 OAI收割 14th IEEE International Intelligent Transportation Systems Conference, ITSC 2011, October 5, 2011 - October 7, 2011, Washington, DC, United states Dai Y.; Hu J.; Zhao D.; Zhu F. 收藏 \| 浏览/下载：29/0 \| 提交时间：2013/03/25 Traffic congestion leads to problems like delays decreasing flow rate and higher fuel consumption. Consequently keeping traffic moving as efficiently as possible is not only important to economy but also important to environment. Traffic system is a large complex nonlinear stochastic system. Traditional mathematical methods have some limitations when they are applied in traffic control. Thus computational intelligence (CI) technologies gain more and more attentions. Neural Networks (NNs) is a well developed CI technology with lots of promising applications in traffic signal control (TSC). In this paper a neural network (NN) based signal controller is designed to control the traffic lights in an urban traffic road network. Scenarios of simulation are conducted under a microscopic traffic simulation software. Several criterions are collected. Results demonstrate that through online reinforcement training the controllers obtain better control effects than the widely used pre-time and actuated methods under various traffic conditions. 2011 IEEE.
	Study on medical X-ray coherent scatter imaging and processing based digital flat detector (EI CONFERENCE) 会议论文 OAI收割 3rd International Conference on BioMedical Engineering and Informatics, BMEI 2010, October 16, 2010 - October 18, 2010, Yantai, China 作者: Li B.; Zhao J.; Li B.; Li B.; Liu J. 收藏 \| 浏览/下载：31/0 \| 提交时间：2013/03/25 It is introduced a novel imaging technique for medical diagnostic X-ray coherent scatter in this paper. A set of experimental equipment for X-ray coherent scatter imaging was set up with X-ray digital flat detector and medical diagnostic X-ray source. According to this equipment the scatter images obtained are made of some circles with the same center. It is vital to calculate the energy template to classify the different samples. It is difficult to separate them using the traditional threshold method due to noise and overlapped shadow. In this paper the image was transformed a binary image by using K-Means algorithm and Mathematical Morphology Methods. The effective region was extracted from the binary image inside the orthogonal energy projection space then to calculate the centroid of rings. Consequently the curve of the energy distribution was built. The experiment results show that our method is reasonable and feasible. The technique will have wide foreground of application .Besides the imaging of human bone content it can be used for various imaging of tissue and organs in biology. 2010 IEEE.
	Kalman filter for pointing deviation delay compensation in a TV tracker (EI CONFERENCE) 会议论文 OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China Juan C.; Wang Q.-P.; Jian C. 收藏 \| 浏览/下载：22/0 \| 提交时间：2013/03/25 Considering the pointing deviation delay in the TV tracker which heavily worsens the tracking precision here we offer an improved Kalman filter algorithm to compensate the delay. The output speed from the filter is fed forward to the speed loop for the compound control to increase the speed constant. The simulation results based on the experiment data show that the method can effectively estimate the position consequently the speed and accelerate and the tracking precision is improved. The estimation precision of the speed and accelerate depend on that if the state model is coherent with the movement of the real target. 2010 IEEE.
	Shape and alignment measurement of the heliostat by laser deflectometry (EI CONFERENCE) 会议论文 OAI收割 Optical Modeling and Measurements for Solar Energy Systems II, August 13, 2008 - August 14, 2008, San Diego, CA, United states 作者: Liu H.; Zhang H.; Zhang H.; Liu H.; Liu H. 收藏 \| 浏览/下载：16/0 \| 提交时间：2013/03/25 In the solar tower thermal power generation system such apparatus and corresponding software packages are developed. With the help of these two apparatus (hexagon) the precision of the slope angle of the heliostat is the major factor the heliostat of 1002 for the 1MWe solar tower power plant in Beijing are measured and connected successfully. which influences the efficiency of the system consisting of 55 mirror facets of 1.8182 m2 consequently this angle should be tested accurately. In this paper the methods based on laser deflectometry are proposed to measure the shape error of the mirror facet and the connected error of the facets
	Research on 10.6 m laser beam monitoring in CO2 laser processing system (EI CONFERENCE) 会议论文 OAI收割 Infrared Materials, Devices, and Applications, November 12, 2007 - November 15, 2007, Beijing, China 作者: Gao Y.; Shao S. 收藏 \| 浏览/下载：25/0 \| 提交时间：2013/03/25 It is a key point of CO2 laser beam monitoring in the CO 2 laser processing system to achieve alignment between CO2 laser and PL (pointing and launching) system. By monitoring the angle offset of CO2 laser beam the compensation can be gotten witch is given to fast-steering mirror to rectify the direction of laser beam. But the normal photoelectric detector can not get the laser signal because of CO2 laser's high energy and long wavelength. Its wavelength is 10.6m and its power can reach kW level. Consequently it is difficult to detect the high-energy 10.6m laser beam directly. So we monitored the output mirror of laser resonator superseded the laser beam indirectly. The laser beam monitoring system could be designed based on CCD laser auto-collimation angular measurement principle and image processing method. In this paper application of CCD laser auto-collimation angular measurement principle and image processing method for CO2 laser beam monitoring system is introduced particularly After design fabrication and alignment the monitoring system can be used for experimental study that including angular measurement accuracy and angle offset measurement of CO2 laser beam. Angle offset range and angle variation rule of CO2 laser beam is also can be acquired for further research.
	A new algorithm of image segmentation for overlapping grain image (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Zhang X.; Zhang X.; Zhang X. 收藏 \| 浏览/下载：17/0 \| 提交时间：2013/03/25 Image segmentation is primary issue in image processing at the same time it is principal problem in low level vision in computer vision field. It is the key technology to process image analysis image comprehend and image depict successfully. Aim at measurement of granularity size of nonmetal grain a new algorithm of image segmentation and parameters calculation for overlapping grain image is studied. The hypostasis of this algorithm is present some new attributes of graph sequence from discrete attribute of graph consequently achieve that pick up the geometrical characteristics from input graph and new graph sequence which in favor of image segmentation is recombined. The conception that image edge denoted with "twin-point" is put forward base on geometrical characters of point image edge is transformed into serial edge and on recombined serial image edge based on direction vector definition of line and some additional restricted conditions the segmentation twin-points are searched with thus image segmentation is accomplished. Serial image edge is transformed into twin-point pattern to realize calculation of area and granularity size of nonmetal grain. The inkling and uncertainty on selection of structure element which base on mathematical morphology are avoided in this algorithm and image segmentation and parameters calculation are realized without changing grain's self statistical characters.
	A new spaceborne compression approach for remote sensing imagery (EI CONFERENCE) 会议论文 OAI收割 ICO20: Remote Sensing and Infrared Devices and Systems, August 21, 2005 - August 26, 2005, Changchun, China 作者: Xu S. 收藏 \| 浏览/下载：27/0 \| 提交时间：2013/03/25 After analyzing advantages and disadvantages of these typical encoding methods: SPIHT and VQ a "DWT+MRLE" approach for spaceborne data compression was proposed in this paper. This approach includes two steps: Discrete Wavelet Transform (DWT) and Modified Run Length Encoding (MRLE). The former used CDF9/7 biorthogonal wavelet filters to powerfully get rid of correlation between pixels in imagery. The later put enlightening information into the lowest bit of some key-position transform coefficients. Consequently CDF9/7 and MRLE together make hardware platform remain high real-time capability and help reconstructed images keep good fidelity with PSNR being about 40dB compared with the original ones. Comparison between experimentations on SPOT4's low-spatial-resolution (10m) imagery and Ikonos2's high-spatial-resolution (1m) imagery shows this "DWT+MRLE" method having better performance for remote-sensed imagery especially those of higher resolution. Although inferior to 8:1 Compression Ration (CR) here near 5:1 is greater than France SPOT5's 3:1 and American Ikonos2's 11:2.6 on-board data compression. More important this method having less computational amount is good for spaceborne capability of real time. The consumed time of different image size is also presented in this paper based on TI TMSC6416 DSP chip with 600MHz CPU cycle clock.
	Design of GPS/INS integrated navigation system based on multisensor information fusion (EI CONFERENCE) 会议论文 OAI收割 6th World Congress on Intelligent Control and Automation, WCICA 2006, June 21, 2006 - June 23, 2006, Dalian, China Chunmei H.; Yantao T.; Wanxin S.; Mao L. 收藏 \| 浏览/下载：38/0 \| 提交时间：2013/03/25 Two kinds of design methods of GPS/INS integrated navigation system are presented that is GPS/INS integrative system and integrated navigation system based on information fusion. By analyzing mathematics model of the first system error we found that inertia velocity error would cause code loop track error. Consequently the pseudo range meterage error is interrelated with inertia velocity error which is complex to calculate. If this relativity is ignored in the state equation and observation equation of this system it must affect the estimated precision of the kalman filter and maybe the system is unstable. Therefore the second integrated navigation method is introduced. It adopts information fusion federal kalman filter and covariance. And consider the above pertinence to analyze the navigation performance of the integration system. Then it gives the flow of federal kalman filter algorithm. By analyzing the conclusion is that velocity error of integrated navigation system drops from 0.5m/s to below 0.05m/s and improves the precision and reliability of the navigation system effectively well continuity and real-time capability. It provides an effective way for data analysis and process of fusion navigation system. 2006 IEEE.