最新刊期
卷 5 ， 期 1 ， 2000
-
- 摘要：Topographic effects are the main obstacles to further application of remotely sensed images. Due to the fact of that different slopes and aspects show very different brightness in images even if the ground cover is the same type, the general classification methods may give wrong results. How to remove the topographic effects is a necessary step in quantitative remote sensing. However, topographic effects are very complex and difficult to be removed successfully. Based on detailed analysis of illumination sources that include solar direct irradiance, sky diffuse irradiance and adjacent reflectance, this paper presents a reflectance retrieval model to remove the topographic effects in satellite images and retrieve the information contained in shadow areas. From the corrected TM images, it is found that the topographic effects are removed effectively. This just illustrates that this method can provide more information for post processing of the remotely sensed images.关键词：model;Reflectance;topographic correction;Atmospheric parameters;Inversion2549|182|0更新时间：2024-05-08
- 摘要：Quality and interpretability of airborne imaging spectrometer data generally are degraded by radiometricdistortions which are related to the larger viewing field of remote sensor. During the period of data acquisition, some parameters, such as path radiance, atmospheric attenuation and the sun-object-sensor geometry, continuously change with viewing angle, which causes a severe radiometric distortion on airborne imaging spectrometer data in scanning direction. Additionally, non-Lambertin reflection of ground objects and relief of terrain strongly complicate the radionetric distortion. It is impossible to do data processing and quantitative analysis if radiometric distortions of data are not corrected properly. In this paper, a new method based on image itself is developed to correct edge radiometric distortion of airborne imaging spectroneter data. Experimental results presented in the paper illustrate that the proposed method is more practical, effective and efficient for radiometric restoration of airborne imaging spectrometer data.关键词：Imaging spectrometer;radiometric correction2804|176|0更新时间：2024-05-08
- 摘要：This article presents an adaptive min-distance algorithm to classify multi-spectral remote-sensing images. This method approximates the distribution of the classes by dividing the sample sets, and adjusts the parameters of the min-distance classifier adaptively. Experiments with TM remote-sensing images demonstrate that this approach achieves an accuracy of 92.9% in the supervised classification of 16 classes. The experimental results verify the applicability of this approach in classifying of multicategory remote-sensing images.关键词：Computer image processing;Remote-sensing;min-distance classification2421|161|0更新时间：2024-05-08
- 摘要：A new method of principal component extraction for remote sensing image based on auto-association\nneural network is presented in this paper. The proposed method is applied to the image data compression, feature\nextraction and filtering. Experiments show that auto-association neural network for extracting the principal\ncomponents of the image is as good as the conventional K-L transform.2420|154|0更新时间：2024-05-08
- 摘要：The paper presents the results of discrimination and classification of Three North shelter forests using shuttle imaging radar (SIR-C/X-SAR) data in Yichuan count, Shannxi province. The forest is divided into three types: coniferous, deciduous and mixed forest. The backscatter coefficients of three forest types are extracted from\nthe SIR-C/X-SAR data, and the effect of the forest types discrimination is analyzed using multifrequency and multipolarization.关键词：Imaging radar image;Forest type;Discrimination effect2405|148|0更新时间：2024-05-08
- 摘要：Image fractal dimension is a useful measure which can be used to characterize features of images. In this paper, three new methods—gray scale surface fractal, curse fractal, pixel fractal to estimate the fractal dimension of thermal image are proposed. The practices indicate that gray scale surface fractal can open out the unitary fractal character of thermal image, curse fractal can contrast and research the thermal radiation character of typical area and pixel fractal can give a quantitative description of variety grades of thermal radiation. After the researching of general fractal theory, the related characters of those methods are discussed. As an example, Shanghai City thermal image is given and the signification of experimental result is analyzed lastly.关键词：Thermal image;fractal geometry;Fractal dimension;Shanghai2603|156|0更新时间：2024-05-08
- 摘要：Since different segmentation algorithms works well for different applications, quality evaluation of image segmentation is indispensable, and thus we introduce fuzzy measure into quality evaluation algorithm of image segmentation and propose a function that could change an image to the field of fuzzy property effectively. Moreover, a composite evaluation function that includes region uniformity, gray contrast, shape parameter and fuzzy measure is presented. The experiment results indicate that fuzzy measure can evaluate image segmentation quality correctly.关键词：Image segmentation;Fuzzy sets;Quality evaluation3073|165|0更新时间：2024-05-08
- 摘要：In this paper, a new approach for multilevel thresholding based on genetic algorithm and fuzzy C-means algorithm has been proposed and implemented. Owing to the characteristics of genetic algorithm, the new approach has good robustness and global optimum. The approach has also been advanced to speed convergence and avoid local optimum. Experimental results are satisfied.关键词：Image segmentation;genetic algorithm;Fuzzy C-means algorithm2184|190|0更新时间：2024-05-08
- 摘要：Codebooks are crucial to vector quantizations (VQs), which determine their performance. LBG algorithm is often used to generate codebooks, where choice of original codebooks is a key technique, and the splitting algorithm is generally considered effective. In this paper, the greedy tree growing algorithm is introduced to design original codebooks, and two better algorithms are derived. Compared to the classical splitting algorithm, the total run time with the proposed algerithm is reduced, and the codebook performance is improved.关键词：vector quantization;Greedy tree growing algorithm;Splitting algorithm2105|155|0更新时间：2024-05-08
- 摘要：This paper mainly studied the problem of the noise suppression for images corrupted by different kinds of noises. A weighted average filter based on the fuzzy theory is presented. The algorithm first looks on the pixels in the filter window as elements of a fuzzy set, and then optimizes the membership of each element of the fuzzy set by iteration ways. In the end, the filter gets its weights of the pixels in the window from the memberships of the fuzzy set. Computer simulations show that the presented filter is not only better than average filter in the field of suppression of Gaussian noise, but also good at the suppression of impulse noise. So it has good performance to image corrupted by mixture noise.关键词：Fuzzy membership function;Average filter;median filter3208|160|0更新时间：2024-05-08
- 摘要：Image metamorphosis or image morphing, used for creating a smooth transition between two images, is a hotspot in the field of image processing. At present, the morphing processing focuses on two-dimensional images. With more and more images generated from three-dimensional models, extending the morphing techniques to three dimensional models is attracting more attention. In this paper, based on the analyses of feature-based metamorphosis, considering three dimensional data model, we put forward an algorithm on feature-based three dimensional morphing to deal with scatting data. In the algorithm, firstly shifting smooth interpolation is used to simulate the warp, then blending method is used to improve the precision and effect of morphing. The implementation shows that the method is reliable. The method is available for not only three dimensional, but also two dimensional image morphing.关键词：Feature-based morphing;Three dimensional metamorphosis;Shifting smooth interpolation;Blending2332|168|0更新时间：2024-05-08
- 摘要：This paper presents a new curve reconstruction method based on orthogonal neural network. The orthogonal neural network' s structure is the same as that of the three layered feedforward neural network. The difference is that the processing function of hidden unit of the orthogonal neural network is Tchebycheff orthogonal function instead of sigmoidial function and the calculation of Tchebycheff function is simpler than that of sigmoidial function. The new method uses less samples and reconstructs higher precision smooth curves than previous methods. By adopting a non-iterative Givens learning algorithm, the new network learning algorithm learns fast and can avoid false local minima and the initialization of weights and other parameters. Experiments show that the reconstructed curve using the orthogonal neural network method has high precision not only at learning sample points but also at the non-learning sample points.关键词：curve reconstruction;Orthogonal neural network;Givens learning algorithm2537|146|0更新时间：2024-05-08
- 摘要：The automatic vectorization about the engineering drawing is one of the urgent need solution key technology. This paper presents an automatic vector algorithm for converting rapidly a binary matrix image into the straight lines, circles and arcs, based on deeply study on the vectorization of the engineering drawing. Experimental\nresults of complex line drawing confirm performances of these algorithms.关键词：vectorization;Circular arc;Circle;Image2741|158|0更新时间：2024-05-08
- 摘要：The scanning input and recognition of engineering drawings is a key step in CAD, and is to reuse lots of engineering drawings. In study on recognition of scanned image of engineering drawings, the recognition for circular arcs is an important and difficult problem. Recent algorithms of recognizing arcs are mainly about approximation with lines. This paper presents an algorithm for recognizing arcs and circles using Primitive Regions Adjacent Graph, which can directly extract arcs. The binary image is encoded with black horizontal runlength. A stripe region consists of correlative runlengths with the same width and topology. The stripe regions then can be segmented as some primitive regions (line and arc). The graph is used to describe geometrical property and topological constraint. The primitive region supplies shape information (line, arc, arrow etc.) improving integrality of recognition. After extraction of the arc region from regions, the seed for an arc is obtained. By traversals for the graph, the seed arc grows by constrains for the same circle. Some applications to recognize arcs and circles are finally provided, which show that the algorithm is effective and robust, can solve well intersection and tangency of between an arc and a line or an arc.关键词：Engineering drawings;vectorization;Recognition for circular arc;Stripe region;Primitive Region Adjacency Graph2530|158|0更新时间：2024-05-08
- 摘要：The paper presents a visual modeling and parameter optimization approach using advanced simulation techniques and object oriented approach for complex nonlinear systems. By creating integrated simulation frame, a parameter optimization environment with graphical modeling and visual simulation is built for the complex nonlinear systems with SIMULINK 2.2. Compared to the parameter optimezation approach with conventional computer advanced programming language, this method is programming free and can be engaged in intelligent analysis and multiparameter auto-iteration optimization test.关键词：Nonlinear system;visualization;modeling;parameter optimization2174|142|0更新时间：2024-05-08
- Postal code：100190
- Tel：010-58887035/58887030/58887418 Email：jig@aircas.ac.cn
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05080539号-4
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0