最新刊期
卷 12 ， 期 8 ， 2007
- 摘要：Since more and more 3D models are developed for applications, the technique for content-based 3D model shape matching become more and more important, and researches have presented kinds of 3D model shape matching algorithms. In this paper, a comprehensive survey of the up-to-date methods and technologies for content-based 3D model shape matching algorithms is presented. The system framework of 3D model retrieval system is first introduced. Then the primary key techniques of 3D model shape matching, including anisotropy transform, coordinate normalization, online-based shape matching, topological-based shape matching, visual-based shape matching, and some. At experimental results with a 3D model database that contains 2 533 3D models, are analyzed the studying progress in this field, proposes a few weaknesses in 3D model shape similarity matching research field, and future areas of research are also put forward.关键词：3D model retrieval;anisotropy transform;shape matching;rotation invariant3947|244|0更新时间：2024-05-07
- 关键词：GIS;map symbol;sharing;symbol schema3077|212|0更新时间：2024-05-07
-
- 关键词：Fuzzy image enhancement;smoothing;sharpening;noise filtering;adaptive2670|235|0更新时间：2024-05-07
- 摘要：Sensor calibration is a necessary and key step before applying photics sensor to measurement. While applying template in calibration, the first task is to detect and locate the template in complex background. At present, manual detection is used widely, whose efficiency is very low. To solve this problem, a new method for template detection and location under complex background is provided in this paper, which consists of two steps, template detection and precise location. The former implements the template detection using image segmentation and Hough transformation, and the later locates the four key corners on template using SUSAN technique. The experiment result shows that the proposed method is simple and reliable and it can be applied in any complex scene.关键词：template detection;precise location;calibration;visual measurement2472|186|0更新时间：2024-05-07
- 关键词：block adaptive quantization;synthetic aperture radar;data compression;vector quantization2977|193|0更新时间：2024-05-07
- 摘要：The image registration of the global motion model is used successfully to the image super-resolution reconstruction. It can estimate motion parameters more accurately than the optimized registration algorithm in the frequency domain if the motion model is a good approximation to the motion between images, therefore, can insure that the reconstructed high resolution image possesses more details. At the same time, it is expounded that the larger the frame number of the low resolution images is, the more accurate the reconstructed image will be. But with the increasement of the frame number of the LR images, the diversification of the mean square error between the reconstructed image and the real image diminishes, and cost of the algorithm would be increased greatly. So, the frame number of the LR images should be determined according to the precision of the reconstructed image.关键词：image;super-resolution;motion model;registration;error2633|217|0更新时间：2024-05-07
- 摘要：The paper presents a novel approach to extract a semantic image object based on an optimized Harmonious Adaboost algorithm, shortly HAB, which produces less generalization error and high performance compared to the Gentle Adaboost Algorithm. Some key techniques in the proposed schema, including the pre-processing of image character, the training of object detector and the extracting of semantic image object, are discussed. The experiment shows that the recurrent training process improves the performance of the object detector, and the extracting results demonstrate the availability of the work.关键词：semantic object extraction;optimized HAB algorithm;image analysis;image semantic2680|208|0更新时间：2024-05-07
- 摘要：The present real-time tracking algorithm can perform well in term of translation tracking but can seldom do so in rotation tracking. A rotation tracking algorithm was proposed, which utilized the gray gradient direction distribution of the target region as the feature and constructed a similarity function that can be optimized by Mean Shift method. Therefore the rotation tracking was transformed into an optimization problem. Due to the fast convergence of the Mean Shift, this algorithm can be run in real-time. Combining the rotation tracking with the translation tracking algorithm proposed by Meer, a whole algorithm was obtained by alternate iteration, which can track both translation and rotation of the targets.2885|220|0更新时间：2024-05-07
- 摘要：This paper proposes a method of detecting moving objects against changing background based on correlative feature matching. The result of the mean of pixel value minus the variance of pixel value is used as the adaptive threshold to separate the object from the background; the features are extracted and parameterized from the image; using the Euclidean distance between the feature to detect objects; Filtering the static object through three continuous frame. This method reduce the calculation greatly compare to the method using correlative parameter, and the method is not subject to the same background between the neighbouring frames. The validity of the method is proved by experiment.关键词：adaptive threshold;feature extraction;moving object detection3082|215|0更新时间：2024-05-07
- 摘要：This paper proposes the weighted Gabor gradient algorithm based on the analysis of the characters of Gabor wavelet. The new method can obtain the more accurate direction of the gradient than the traditional gradient operators. And a new comer detecting algorithm based on the multi-scale weighted Gabor gradient is proposed. Experimental results with some synthetic and real images show that this new algorithm detects the comer more efficiently, locates the comer more accurately, and restrains the noise more effectively than the two classical comer detecting algorithms.关键词：multi-scale;weighted Gabor gradient;comer detection2640|203|0更新时间：2024-05-07
- 摘要：A novel gait recognition method based on periodic sequence width images is proposed in order to gain gait quickly and correctly. This method transforms the 2D silhouette contours sequences to width vector sequences according to the gait cycle. The vector sequences are turned into the periodic sequence width images, presented by grey values. These grey values can exactly depict the gait motion. The periodic sequence width images contain both the static and dynamic gait characteristics, which not only keep the shape structure information of each frame, but also represent the variant movement information of gait sequence excellently. Furthermore, the new method greatly reduces the image dimension by discrete cosine transforms and adopts the radial basis function neural networks to identify the gait. Experiments prove this method is simple and effective in theory and application.2972|195|0更新时间：2024-05-07
- 关键词：human head detection;mask matching;accurately location;real-time;integral image2455|203|0更新时间：2024-05-07
- 关键词：face recognition;Fisher nonlinear discriminant analysis;kernel method;small sample size problem;ill-pose problem2673|217|0更新时间：2024-05-07
- 关键词：fragmentation test;safety glass fragmentation particles;crack lines;edge detection;image segmentation3319|208|0更新时间：2024-05-07
- 关键词：stereoscopic display;sub-screen;brightness;stereo degree2786|190|0更新时间：2024-05-07
- 摘要：It is important to properly organize the unstructured video data for content-based video analysis and retrieval. In this paper, we propose a unified approach for film video summarization based on the analysis of video structure and motion attention model. Video shots are firstly grouped into shot clusters. Afterwards, according to the characterization of film video scene, a temporally and spatially integrated strategy is presented to parse shot clusters into semantic scenes in terms of the definition of temporal relationships between two shot clusters. Finally, representative frames and highlight shots are selected from scenes by using motion attention model. The scheme offers an efficient mean for browsing and effectively retrieving film video.关键词：film video;scene detection;summarization generation;motion attention model2982|232|0更新时间：2024-05-07
- 关键词：volume rendering;ray casting;segment composition;GPU3492|216|0更新时间：2024-05-07
- 关键词：pencil sketching;line integral convolution;non-photo-realistic rendering;neon processing4112|266|0更新时间：2024-05-07
- 摘要：3D Spatial Modeling is the key to 3D GIS, and is the basis of3D GIS. All kinds of 3D spatial modeling methods are different according to the differences of modeling objects. Based on the difference of spatial modeling objects, 3D spatial modeling methods are divided into two kinds. One is Geographical Spatial Modeling, and the other is Geological Spatial Modeling. Based on the comparision and contrast of all the 3D spatial modeling methods, this paper also presents some key issues on 3D spatial data modeling.关键词：3D modeling;geographical space;geological sapce5618|239|0更新时间：2024-05-07
- 摘要：3D Geological Model is the key and focus to learning, geological engineering, early warning and prevention of geological disasters, mine management, and other aspects that have been widely applied. 3D Geological Model involves modeling methods, data model, data structure and other aspects. Based on the comparative study on the research results of three-dimensional geological model in the domestic, it expounds the research progress in the three-dimensional model of geological field. The related modeling methods, data structure and practical application are comparative analyzed and classified, accovding to the three-dimensional geological model of the principles. The comprehensive analysis of threedimensional geological model progress is given in the article, and modeling methods, data structure, spatial analysis has done an in-depth analysis expounded. Based on a comprehensive study on the previous results, a multi-TIN and TEN mixed 3D geological model was proposed and an experiment was carried out to prove the availability of this method.关键词：geological volume;3D model;3D data structure4702|265|0更新时间：2024-05-07
- 关键词：three-dimension data;distributed environment;dynamic attemperation4382|214|0更新时间：2024-05-07
- 摘要：Raster is used widely as a basic object in the geography information science, because products producted by raster have real spatial size and many math models are more easily built based on raster. Fuzzy comprehensive assessment is applied widely in the field of multi-factors evaluation application. Sometimes spatial data and spatial concept are fuzzy in geography information science, so fuzzy spatial analysis has gained more and more attention from researchers during the recent years, but fuzzy comprehensive assessment method is used rarely in multl-raster data. The theory of fuzzy comprehensive assessment is described in detail firstly. Then the GIS model about fuzzy comprehensive assessment is built based on multiraster data and spatial overlay analysis. The GIS model has been used in the urban air quality assessment successfully. The result of the instance shows that this model can well conduct fuzzy comprehensive assessment based multl-raster data.关键词：geography information system;multi-raster data;fuzzy comprehensive assessment4579|243|0更新时间：2024-05-07
- 摘要：Multi-scale representations for geographical entities is one of the research focuses in the field of multi-scale spatial database. Compared with the traditional GIS model, the essential modeling mechanism and strategies for building a multi-scale data model are explored. Taken the road feature as an example, a detailed description of multi-representatlon elements in the model are provided. This model includes abstract data types and attribute-value domains for geographical features at different scales, as well as the scale, semantic, and mapping hierarchical relations among features. An appropriate multi-scale conceptual model is given in detail with the multi-scale extended E-R method.关键词：multi-scale representation;multi-scale modeling;hierarchical semantic relation;multi-scale extended EntityRelation method4246|220|0更新时间：2024-05-07
- 关键词：large-scale landscape;geomorphologic data;quadtree;LOD algorithm;visualization4604|232|0更新时间：2024-05-07
- 关键词：ground water;virtual reality;spatial analysis;visualization4511|251|0更新时间：2024-05-07
- 关键词：probability index model;region landlside susceptibility assessment;cameron highlands;GIS4852|229|0更新时间：2024-05-07
-
- 关键词：urbanization;population density;employment structures;cellular automata model5903|244|0更新时间：2024-05-07
- 摘要：Based on the characteristics of the groundwater table raster model, this paper firstly builds up the mathematical models about the groundwater flow direction, the cone of the depression and groundwater divides according to their hydrogeological definition. And then, seed algorithm and mathematical morphology are used to extract these spatial characteristics, and also the extracted information is visualized. In the end, this paper takes Su-Xi-Chang area as a study site, analyzes the extracted and visualized spatial characteristics, and gives some suggestion on the rational groundwater exploiting. These automated extraction results could facilitate the analysis of temporal and spatial dynamics of groundwater, provides support for groundwater management, and it also could be the useful exploring for digital groundwater study.关键词：groundwater;spatial characteristics;seed algorithm;mathematical morphology;visualization4665|234|0更新时间：2024-05-07
- 摘要：The Great Wall has been in the severe danger of the World Culture Heritages list. it is difficult to investigate the situation, because the Great Wall stretches too long and we do not know the exact layout of the Great Wall. The protection and management of the Great Wall is a hard work. In this paper, there is a new method to extract the information of the Great Wall from the satellite images. The research area BaDaLing is one of the typical stone Great Wall. Firstly we obtain the NDVI value from a SPOT5 image after fusion and orthorectification. Then use the DEM hydrology function to extract the ridge of the watershed, and buffer it. At last we put the NDVI and the buffered data together to make an overlay, then the Great Wall information is extracted. We apply the shape index to the overlay to get rid of other spots. The result is confirmed through the field survey. The method can provide reference to the Great Wall survey.关键词：Great Wall of BaDaLing;remote sensing;DEM;hydrology analysis;information extraction4619|302|0更新时间：2024-05-07
- 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