最新刊期
卷 12 ， 期 9 ， 2007
- 摘要：The research on new generation of Intelligent Visual Surveillance is a new arising font field with many challenges. It aims to endow surveillance systems with the ability of analyzing scene contents, make surveillance tasks fulfilled automatically and intelligently, which has a large potential of application. There are four main issues in the process of intelligent analysis of typical visual surveillance system, detection, classification, tracking of objects and analysis of video contents. According to the real applications, video contents analysis can he abnormal detection, person recognition, understanding and description of video contents etc. In this paper, in addition to make a survey on the research progresses of the key technologies of visual surveillance, the concept of super resolution restoration is further introduced to this field to enhance the quality of the surveillance sequence. The main algorithms of super resolution restoration and its applications in visual surveillance are discussed in detail.关键词：intelligent visual surveillance;object detection;object tracking;gait recognition;video content understanding and description4455|279|0更新时间：2024-05-08
- 摘要：Binarization is an elementary step in the framework of context-based adaptive binary arithmetic coding. It is introduced to simplify the context modeling and the subsequent arithmetic coding process. In this paper, we propose a novel binarization scheme for arithmetic coding. Based on the observation that the numbers of nonzero coefficients in neighboring blocks are highly correlated, the number of nonzero coefficients of a block is specifically binarized according to the numbers of nonzero coefficients of its top and left neighbors. In addition, a novel mapping rule is designed to map a syntax element to a code number, according to the observed features of probability distribution. Experimental results show that compared to the conventional scheme, this scheme can reduce decoding complexity with comparable coding efficiency.关键词：arithmetic coding;adaptive;binarization;mapping rule3111|229|0更新时间：2024-05-08
- 摘要：AVS is a new audio and video coding standard in China, in which variable block sizes and quarter-pel motion compensation have been applied to improve coding efficiency. In this paper, an adaptive range fractional pel search algorithm is proposed to further speed up the encoding process and reduce the computation complexity. Small diamond search and threshold judgment are used to this algorithm. Compared with the half-pel full search algorithm, experiments show that the proposed algorithm can reduce the sub-pel search points by 30. 25% on average with the limited performance lost about 0. 009 3dB. And compared with the fast search algorithm in AVS reference software, experiments show that the proposed algorithm can reduce the sub-pel search point by 8.78% on average with the performance achieve a gain up to 0. 0221dB.关键词：AVS;video coding;sub-pel motion estimation3352|208|0更新时间：2024-05-08
- 摘要：Solar eclipse may cause a shadow on satellite visible imagery. So it would have impact on analyzing and applying the information of satellite image in practice. This paper gives an improved method to eliminating eclipse shadow, and has been evaluated through an actual data experiment with gray level concurrence matrix and image texture feature quantities. The results show that improved method is more effective.关键词：solar eclipse;radiation correction;satellite visible imagery;gray level coocurrence matrix;cloud texture feature quantities3119|204|0更新时间：2024-05-08
-
- 关键词：surface reconstruction;topology reconstruction;TIN;unorganized sampling points;2-dimensional manifold;3-dimensional surface model3121|209|0更新时间：2024-05-08
- 摘要：It is proved by experiments that the particle swarm optimization is superior to the genetic algorithm in solving the problems of real optimization. In order to enhance the efficiency of the color image quantification algorithm, in this paper, the corresponding fitness function is designed, and a kind of particle swarm optimization color image quantization method is provided on the basis of the genetic algorithm color image quantization method. The comparison of the performance of two kind of quantification method has been carried on through the examples. The experimental result shows that the particle swarm optimization color image quantization method is obviously superior to the genetic algorithm color image quantization method since it has higher convergence rate.关键词：particle swarm optimization;color quantization;K-means algorithm2787|195|0更新时间：2024-05-08
-
- 摘要：There are broken fibers which cause blind pixels in image-carrying fiber bundles due to limitations of manufacture technology. However, Mean filters and mid-value filters can not solve this problem. An algorithm based on double-module extremum is proposed in this paper, and it is effective to solve the problem. This algorithm is also effective in locating the barycenter of Fiber.关键词：image-carrying fiber bundles;blind pixels;double-module extremum filter2478|214|0更新时间：2024-05-08
- 关键词：singular value decomposition;digital image watermarking;arnold transformation;blind watermarking2777|207|0更新时间：2024-05-08
- 摘要：In order to realize lossless covert communication in image, a novel lossless covert communication method based on integer linear transform was proposed. The method uses integer linear transformed vector instead of original vector and need not to save the message of the revisable vector. Using the method the host data with large capacity secret information embedded can be transmitted in open channels. Host image can be recovered without any distortion from the marked image after the hidden data have been extracted. The scheme had been simulated and good experimental results were achieved. It can be applied to keeping case history in medical images and can also be used for covert communication in remote sensing images, military images and etc.2948|194|0更新时间：2024-05-08
- 关键词：information safety;remote sensing image;authorization;discrete wavelet transform3190|217|0更新时间：2024-05-08
-
- 关键词：intelligent video monitoring system;mixture Gaussian model;moving object detecting and recognition3280|200|0更新时间：2024-05-08
- 摘要：Moving object detection is a very significant and difficult problem in processing image sequence acquired by a mobile camera. The objective of this research is to present a novel method to resolve the moving target detection difficulties, which bring by several layers with different motion parameters of the sequence images. Considering a moving camera, it was hard to distinguish different motion layers led by 3D depth difference of immobile objects from those caused by target moving in scene. Firstly, a mixture model of image was proposed, and the method of motion segmentation based this model were suggested. Secondly, the reconstruction method of scene depth, which employed the motion parameters by EM, was presented. Finally, the detail theory and algorithm of new moving target detection approach, which were based on the scene 3D depth reconstruction, were described. The results indicate that the moving targets detected by the new technique are more accurate than those detected by traditional methods. In addition, the detection speed becomes more-much. The results seem to suggest that the new method be able to provide efficiency and accuracy advantages in computer version.关键词：motion segmentation;moving object detection;mixture model;affine motion model;dynamic scene3392|232|0更新时间：2024-05-08
-
- 摘要：A quick road-boundary detection algorithm using 2D laser rangefinder based on maximum entropy principle is proposed. By reclassifying observed measurements at different measure angle in limited continuous domain, we calculate fuzzy cluster centers directly and predict the states and predictable error simultaneously, and calculate membership values of current state based on the maximum entropy principle. The method eliminates the dependence of conventional methods on hnowledge of experts and prior information. The weighted factors are designed for calculating prediction results based on the fact that later states have more impacts on the prediction. In the process, the error of every step is also predicted to modify the prediction results of states, and the prediction error is determined by the selected states in the limit domain. Thus the accumulation error overtime is eliminated. The results of experiments indicate the effectiveness of the proposed algorithm.关键词：maximum entropy;two dimensional laser rangefinder;fuzzy prediction;road boundary detection3362|192|0更新时间：2024-05-08
- 摘要：The key to edge detection is to filter more noises while obtaining more edge details. A new multi-scale morphological method of edge detection based on contour structuring elements is proposed in this paper. This method realizes a modified morphological transform through regrouping the priorities of several morphological transforms based on contour structuring elements firstly. And then a new edge detector is defined by using the multi-scale operation of the modified morphological transform. Comparative study with other morphological methods reveals its superiority over de-noising capacity, edge detail protection and un-sensitivity to the shape of the structuring elements.关键词：edge detection;multi-scale;mathematic morphology3362|227|0更新时间：2024-05-08
- 摘要：This paper presents a texture segmentation algorithm based on self-supervised classification and multispace KL transform. It turns unsupervised clustering into self-supervlsed classification to decrease the ratio of misclassificatlon. Our algorithm adopts a multispace method for feature selection to avoid the limitations introduced by supposing that all samples obey a single Gauss distribution. Firstly multldirection and multiscale Gabor transforms are applied to target texture images ; then fuzzy C means clustering is acted on the results of above transforms to extract some typical training samples, which are requested to supervise later segmentation. Secondly a separate subspace for each class is initialized by training samples respectively. Lastly other samples are classified with multispace KL transforms through the iterative processes. Our algorithm is fully competent for various composite texture segmentations. And experimental results have proved that it can successfully reduce misclassification ratio in the same time improve the visual effects of texture segmentation.关键词：image segmentation;pixel feature;fuzzy C means;KL transform3229|210|0更新时间：2024-05-08
- 关键词：magnetic resonance;detail signal energy;geodesic active contour;left ventricle;tagged line2814|214|0更新时间：2024-05-08
- 关键词：contextual;forest fire;detection;remote sensing3223|206|0更新时间：2024-05-08
- 关键词：affine invariant feature;affine geometry;extended centroid;affine region cutting;target recognition3495|199|0更新时间：2024-05-08
- 关键词：subvoxel model;density field;subtraction image;membership degree3622|198|0更新时间：2024-05-08
- 关键词：image retrieval;robustness;significant bit-plane;color histogram;standard deviation2916|258|0更新时间：2024-05-08
- 摘要：In practical applications, many video sequences have moving background, and then the extraction of video object becomes complicated. An algorithm is proposed in the paper to extract video object from dynamic scene based on motion estimation and the graph pyramid. Phase correlation is first used to obtain the motion vector with high efficiency and robustness, and to weaken the impacts of illumination in the video sequence. Then global motion estimation with parameter-model is used to find the final motion template. Finally, to extract the semantic video object, spatial segmentation using the graph pyramid is applied to the image region in the current motion template. Compared with some prevailing methods, in the case of extraction of moving object from video sequences of dynamic scene, our algorithm avoids precise background compensation and is very computationally efficient, while the extracted semantic object is of high precision. The experimental results show that both rigid and non-rigid moving objects in dynamic scene are well extracted by this algorithm.关键词：dynamic scene;video object extraction;phase correlation;motion estimation;graph pyramid3333|210|0更新时间：2024-05-08
- 关键词：high accuracy surface modelling;spatial real-time simulation;dynamically adding information points;dynamically reducing information points;numerical test2707|188|0更新时间：2024-05-08
- 关键词：remote sensing image fusion;Contourlet transform;independent component analysis;support vector machines;feature extraction2964|222|0更新时间：2024-05-08
- 摘要：Image mosaic is the key step to panorama, while existing algorithms focus on scenes with the same illumination. This paper presents a novel method for image mosaics with notable illumination difference. First, feature points are extracted by ring projection, which overpass the local area limitation in tradition methods and gains exactly matching result for image under vary illumination conditions. Then mean and covariance are used to adjust the global brightness of the images to solve the problem of different illumination. While blending factors are gained using the energy function that contains image gradient, which conquers the blur and mackle problems in the overlap area if using the tradition linear weight function. Experiment results show that we can gain satisfying visual effect using this method in image mosaics with notable illumination difference.关键词：image based rendering;image mosaic;ring projection;image blending;vary illumination4224|228|0更新时间：2024-05-08
- 摘要：Based on the analysis of traditional simulation methods, this paper presents a new approach for simulation of snow falling and accumulating in large-scale terrain. The snow simulation is divided into two stages-falling and accumulating. In the former stage, rotation, dynamic texture, and dynamic color of particles are taken into account, which greatly improves the reality of simulation. In the later stage, image noise is introduced to a large-scale terrain, which solves the problem that the traditional methods cannot be scaled up to the large-scale terrain. Experiment shows this method improves the in snow simulation, keeps real-time, and adapts to the large-scale terrain, especially for the scene with flight simulation.关键词：particle system;falling snow;accumulating snow;image noise2982|198|0更新时间：2024-05-08
- 关键词：video watermarking;motion vector;geometric attack2964|186|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