中国科学院机构知识库网格系统: 检索

A shape context based Hausdorff similarity measure in image matching 会议论文 OAI收割
5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013
作者: Ma TL(马天磊); Liu YP(刘云鹏); Shi ZL(史泽林); Yin J(尹健)

收藏 | 浏览/下载：37/0 | 提交时间：2013/12/26

The traditional Hausdorff measure, which uses Euclidean distance metric (L2 norm) to define the distance between coordinates of any two points, has poor performance in the presence of the rotation and scale change although it is robust to the noise and occlusion. To address the problem, we define a novel similarity function including two parts in this paper. The first part is Hausdorff distance between shapes which is calculated by exploiting shape context that is rotation and scale invariant as the distance metric. The second part is the cost of matching between centroids. Unlike the traditional method, we use the centroid as reference point to obtain its shape context that embodies global information of the shape. Experiment results demonstrate that the function value between shapes is rotation and scale invariant and the matching accuracy of our algorithm is higher than that of previously proposed algorithm on the MEPG-7 database.

A line mapping based automatic registration algorithm of infrared and visible images 会议论文 OAI收割
5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013
作者: Ai R(艾锐); Shi ZL(史泽林); Xu DJ(徐德江); Zhang CS(张程硕)

收藏 | 浏览/下载：36/0 | 提交时间：2013/12/26

There exist complex gray mapping relationships among infrared and visible images because of the different imaging mechanisms. The difficulty of infrared and visible image registration is to find a reasonable similarity definition. In this paper, we develop a novel image similarity called implicit linesegment similarity(ILS) and a registration algorithm of infrared and visible images based on ILS. Essentially, the algorithm achieves image registration by aligning the corresponding line segment features in two images. First, we extract line segment features and record their coordinate positions in one of the images, and map these line segments into the second image based on the geometric transformation model. Then we iteratively maximize the degree of similarity between the line segment features and correspondence regions in the second image to obtain the model parameters. The advantage of doing this is no need directly measuring the gray similarity between the two images. We adopt a multi-resolution analysis method to calculate the model parameters from coarse to fine on Gaussian scale space. The geometric transformation parameters are finally obtained by the improved Powell algorithm. Comparative experiments demonstrate that the proposed algorithm can effectively achieve the automatic registration for infrared and visible images, and under considerable accuracy it makes a more significant improvement on computational efficiency and anti-noise ability than previously proposed algorithms.

A fast target recognition algorithm based on MSA and MSR (EI CONFERENCE) 会议论文 OAI收割
2012 International Conference on Industrial Control and Electronics Engineering, ICICEE 2012, August 23, 2012 - August 25, 2012, Xi'an, China
作者: Wang Y.; Liu G.; Wang Y.; Wang Y.; Wang Y.

收藏 | 浏览/下载：30/0 | 提交时间：2013/03/25

This paper presents a new fast target recognition algorithm the proposed method is based on Multi-scale Auto convolution(MSA) and Multi-scale Retinex(MSR). As shown by the comparison with original MSA it appears that this new technique solves the problem that MSA algorithm is sensitive to illumination and the computational load is significantly reduced to 1/8th of that of the original MSA algorithm it is also robust to affine transform light projective transform noise thin fog occlusion and illumination change. the performed experiments show that it has fast searching speed and can accurately recognize and locate target in real scenes. 2012 IEEE.

On hyperspectral remotely sensed image classification based on MNF and AdaBoosting (EI CONFERENCE) 会议论文 OAI收割
2012 3rd IEEE/IET International Conference on Audio, Language and Image Processing, ICALIP 2012, July 16, 2012 - July 18, 2012, Shanghai, China
作者: Yu P.; Yu P.; Gao X.

收藏 | 浏览/下载：23/0 | 提交时间：2013/03/25

As an effective statistical learning tool AdaBoosting has been widely used in the field of pattern recognition. In this paper a new method is proposed to improve the classification performance of hyperspectral images by combining the minimum noise fraction (MNF) and AdaBoosting. Because the hyperspectral imagery has many bands which have strong correlation and high redundancy the hyperspectral data are pre-processed by the minimum noise fraction to reduce the data's dimensionality whilst to remove noise bands simultaneously. Then we use an AdaBoost algorithm to conduct the classification of hyperspectral remotely sensed image. Experimental results show that the classification accuracy is improved and the time of calculation is reduced as well. 2012 IEEE.

Transitional compensation algorithm for correcting non-uniformity of LED display image (EI CONFERENCE) 会议论文 OAI收割
2012 2nd International Conference on Materials Science and Information Technology, MSIT 2012, August 24, 2012 - August 26, 2012, Xi'an, Shaan, China
Su W.-x.; Chen Y.-s.

收藏 | 浏览/下载：32/0 | 提交时间：2013/03/25

In order to solve the problem of high non-uniformity of LED display images which is caused by the edges of LED display panel during module splicing transitional compensation algorithm is proposed by improving the existed correction technique named the correction technique based on CCD. First introduce the three development stages of the LED display panel. Then the realization progress of the transitional compensation algorithm is described in detail after elaborating the principle of transitional compensation. Finally the algorithm is emplaned in a LED video control system to control the LED display panel whose display area is 1280960 and which is spliced by 3020 LED modules whose size are 6432. Experimental results show that this algorithm is able to reduce non-uniformity of LED display images from 29.3% before correcting to 0.95%. (2012) Trans Tech Publications Switzerland.

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.

Method of tacit knowledge discovery based on domain knowledge under driven of problems (EI CONFERENCE) 会议论文 OAI收割
2012 International Conference on Computer Science and Information Processing, CSIP 2012, August 24, 2012 - August 26, 2012, Xi'an, Shaanxi, China
作者: Wang Y.-C.; Wang Y.-C.

收藏 | 浏览/下载：18/0 | 提交时间：2013/03/25

Now most of the knowledge discoveries are using the data mining technology and driven by data. This kind of knowledge discovery can't finish the discovery exploration and applying of the tacit knowledge. According to the problem above this paper proposes a domain knowledge-based of problem driven tacit knowledge discovery method. This paper designs a S-K-T algorithm and the related problem-knowledge mining algorithm to get the domain knowledge semantic tree and the problem-domain knowledge tree and based on this through the spiral iteration to finish the discovery of the tacit knowledge under the driven of problems. 2012 IEEE.

The shape edge measure of automobile airbag based on image processing (EI CONFERENCE) 会议论文 OAI收割
2012 IEEE 5th International Conference on Advanced Computational Intelligence, ICACI 2012, October 18, 2012 - October 20, 2012, Nanjing, China
作者: Li Y.; Wang Z.; Wang Z.; Li Y.; Li Y.

收藏 | 浏览/下载：34/0 | 提交时间：2013/03/25

At present micrometer is used for measure the shape edge of automobile airbag. There are some shortcomings in this method. The number of test points is limited. Test data is not comprehensive. Detection speed is slow and a fixture can only test a kind of airbag. The method of airbag shape edge detection based on image processing is researched in this paper. The image of airbag is collected by CCD and then it is sent to the computer to be processed and segmented. The edge of image is extracted through Canny edge detection algorithm in order to acquire shape edge of airbag in this paper and the image similarity degree are calculated to provide the information of matching in the template matching process. Finally the comprehensive test shape edge of airbag is realized. The experimental results show that the detection method is effective feasible intuitive and clear. 2012 IEEE.

Image mosaic technique based on the information of edge (EI CONFERENCE) 会议论文 OAI收割
2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012, July 31, 2012 - August 2, 2012, Guilin, Guangxi, China
作者: Wang Y.-Q.

收藏 | 浏览/下载：35/0 | 提交时间：2013/03/25

Image mosaic is an important branch in the field of image processing. This paper designs and realizes an image mosaic technique based on the information of edge. The technology is suitable for engineering application. First of all two images of the adjoining frames are processed by convolution operation get the edge images. And then we cut edge image into pieces and compute their spatial frequency. According to the value of the spatial frequency select reasonable registration model group. We compute correlation strength and the value of movement offset which are the model group and the current frame edge image. We can complete image mosaic by them. We use video sequence which of the resolution is 1024 * 768 do the experiment. The results show that the method has good effect and strong adaptability. Algorithm is high efficiency which running time is 24 ms. It is suitable for real-time processing requirements of the application. This method is an effective mosaic technique which is suitable for engineering application. 2012 IEEE.

Trajectory tacking control of a quad-rotor based on active disturbance rejection control (EI CONFERENCE) 会议论文 OAI收割
2012 IEEE International Conference on Automation and Logistics, ICAL 2012, August 15, 2012 - August 17, 2012, Zhengzhou, China
Gong X.; Tian Y.; Bai Y.; Zhao C.

收藏 | 浏览/下载：31/0 | 提交时间：2013/03/25

The objective of this paper is to deal with a trajectory tracking of a Quad-rotor unmanned aerial vehicle (UAV). For the model uncertainty the external disturbance and the coupling factor are considered an active disturbance rejection control (ADRC) algorithm is introduced into the designing procedure. The aircraft dynamic model is proposed in this article based on which the closed-loop control system is divided into four independent channels with the coupling factor compensated by the extended state observer (ESO). The nonlinear state error feedback (NLSEF) algorithm is designed in each channel to improve the closed-loop dynamics. In this article the ADRC controller is expressed in the discrete form. And finally the simulation results show that the proposed control algorithm achieves a favourable tracking performance. 2012 IEEE.