最新刊期
卷 14 ， 期 10 ， 2009
- 摘要：Multi-view video coding has higher demands on power consumption, complexity, storage capacity, and transmission capacity of the encoder, whereas the distributed source coding theory adapts to the needs. The basic theory and the key technology for distributed video coding are summarized firstly as the background information. Second, the expansion from single view to multi-view for distributed source coding theory is introduced. Then, the research status of distributed multi-view video coding is exposited. Finally, the development prospect for distributed source coding in the field of multi-view video coding is analyzed.3395|243|0更新时间：2024-05-07
- 摘要：Autostereoscopic display is a kind of three-dimensional technique which need not wear 3D goggles or other equipments. It can be classified into four groups: holography display techniques, integral photography display techniques, volumetric display techniques and horizontal parallax-based autostereoscopic display techniques. In these years, volumetric display techniques and horizontal parallax-based autostereoscopic display techniques develop rapidly. In this paper, we first overview developments in two kinds of volumetric display techniques, which are static volumetric display technique and volumetric display technique based on swept screen, during recent years. Then, make a survey of horizontal parallax-based autostereoscopic display on two ways, the optical sheets used and the multiplex methods. Last, summarize the advantages and disadvantages of volumetric display and autostereoscopic display based on parallax.关键词：volumetric display techniques;horizontal parallax-based autostereoscopic display techniques;holography techniques;integral photography techniques3912|280|0更新时间：2024-05-07
- 摘要：In this work, a 2D overlapped sub-aperture polar format algorithm (PFA) based on stepped-chirp signal is proposed. In synthetic aperture radar (SAR) with stepped-chirp signals, instead of using traditional pulse synthesis to conduct preprocess, the presented method integrates the pulse synthesis process into the range sub-aperture processing. Meanwhile, due to the multi-resolution characteristics of sub-aperture processing, this algorithm is able to compensate the space-variant phase error caused by the radar motion during the period of a pulse cluster. Finally, experiments carried out on simulated and measured data confirm the validity of the algorithm.关键词：synthetic aperture radar (SAR);polar format algorithm (PFA);2D sub-aperture processing;stepped-chirp signal;bandwidth synthesis;space-variant phase compensation3017|254|0更新时间：2024-05-07
- 摘要：Stanley Osher and Martin Burger introduced an iterative regularization method for image de-nosing based on the Bregman distance. The approach can improve the general procedure and save the execution time. However, important information, such as texture is often compromised in the process of de-noising. The reason is that the proposed approach ignored the gradient information of each pixel. In order to avoid the above phenomenon, a novel texture preserving variational de-noising method based on the use of adaptive regularization is proposed in this paper . The new adaptive regularization method based total variational de-noising algorithm uses an adaptive fidelity term which locally controls the extent of de-nosing over image regions according to the gradient information of each pixel. So important information, such as edge and texture is preserved. The numerical results for de-nosing show the improvement in the signal-to-noise ratio (SNR) over standard model processes, and they are visually more appealing.关键词：image denoising;total variation;Bregman distance;adaptive denoising4197|282|0更新时间：2024-05-07
- 摘要：For the lack of rate control model in H.264, a new macro-block layer rate control algorithm for H.264 is proposed. The algorithm uses the spatio-temporal relevancy of frames estimated mean absolute difference(MAD).Then a fuzzy controller is applied, making rate control no longer rely on the various statistical models. By leaving out the updated of the model parameter, the computational complexity of the algorithm is decreased to some extent. The experimental results show that compared to JM8.6 original algorithm, the new algorithm can increase the accuracy of rate control and the image quality of the restoration at the same time.关键词：H.264;rate control;the spatio-temporal relevancy;fuzzy control3133|224|0更新时间：2024-05-07
- 摘要：To solve the problem of slow reconstruction speed of algebraic reconstruction technique, this paper presents a fast traversal and intersection algorithm of ray beam-pixels. The algorithm determines the pixel index traversed by ray beam and calculates area overlapped by the ray beam through a distance parameter. The distance parameter can be calculated with an incremental method, thus the operation is of high efficiency. Applying this algorithm to calculate the weight coefficients on real-time during the process of reconstruction, not only large amount of memory is saved, but also the speed of image reconstruction is improved greatly. The experimental result shows that the algorithm is very effective and the reconstruction speed is improved about 17 times compared with the conventional method.关键词：image reconstruction;algebraic reconstruction technique(ART);traversal;intersection;weight coefficient3167|202|0更新时间：2024-05-07
- 摘要：Semi-fragile video watermarking is an important technology of videos’ content authentication. A novel semi-fragile watermarking scheme is proposed in this paper in order to improve authentication abilities. The scheme obtained the watermarking information by adopting double-feature extraction which was a combination of DCT blocks’ relation and grayscale blocks’ relation. The watermark was embedded into the host video with an improved DEW algorithm after it had been Turbo coded. The double-feature extraction algorithm can conquer single-feature’s imperfection to improve the abilities of tamper estimation and orientation. Turbo code can improve the robustness of watermark and decrease the probability of false positive. Experimental results demonstrate that it will not degrade the visual quality of original videos, and it can authenticate normal tamper operations. Besides the scheme have little probability of false positive.关键词：video watermark;semi-fragile;feature extraction;Turbo code3040|240|0更新时间：2024-05-07
- 摘要：A new method which is based on bidimensional empirical mode decomposition（BEMD） and wavelet thresholding was proposed for the noise removal in medical image of magnetic resonance image（MRI）. Namely the image was decomposed into the intrinsic mode function (IMF) domain. Then the wavelet thresholding was used to remove the noise in the IMF. After the characteristic of the wavelet hard thresholding and the wavelet soft thresholding was analyzed, an improved wavelet thresholding which overcomes the shortcoming of the custom wavelet thresholding for denoising was introduced. In addition to remove the noise in MRI image, the experimental results show that our method had preserved the details of MRI image. It was propitious to medical diagnoses.关键词：magnetic resonance image;bidimensional empirical mode decomposition;intrinsic mode function;wavelet thresholding denoising3445|259|0更新时间：2024-05-07
- 摘要：An adaptive algorithm for license plate(LP) orientation was proposed. Based on the common features of LP, the vertical edge was first detected. Then, some approaches were adopted to remove adaptively the invalid edge due to the characteristics of vertical texture and edge density, so that the regions with features of LP were preserved. Next, horizontal morphologic operation was conducted to close the candidate regions, and the above method overcomes the problem how the morphologic structure element was adjusted adaptively to the size change of LP. A viewpoint then proposed was that the gray adjustment and color recognition modules could be employed according to actual scene conditions. With abundant samples verified in dark hours and daytime in real conditions, the experiment indicates that it is feasible to adopt this algorithm in LP recognition system to achieve both accuracy and adaptability.关键词：license plate recognition;license plate orientation;image processing;edge characteristic;adaptability3325|330|0更新时间：2024-05-07
- 摘要：To overcome the drawbacks of the models of line and parabola when there is an inflection point on the edge, a novel approach to edge locating to sub-pixel accuracy is proposed in this paper. The Levenberg-Marquardt iterative method is utilized to obtain the control points of the cubic Bézier curve. Simulation results illustrate that the determination of the edges is much more accurate than that of the existing approaches when the shape of the fitted edge is close to a cubic with an inflection point on it. The proposed model is based on an ideal step edge; therefore, it will be improved to fit other kinds of edges.关键词：sub-pixel edge location;spatial moment;cubic Bézier curve2732|258|0更新时间：2024-05-07
- 摘要：The characters of Bubble wavelet（Mexico hat wavelet) have been researched.We discussed the mistakes in some literatures that Mexico hat wavelet is applied to multi-resolution analysis, This paper point out that Mexico hat wavelet can only be applied to continuum wavelet transform(CWT) and its multi-resolution analysis does not exist. We suggest that it is applicable for bubble wavelet to detect image edge under continuum wavelet transform.The template for CWT is presented and is proved efficiency use for edge detection by experiment.关键词：multi-resolution analysis;bubble wavelet;edge detection3220|216|0更新时间：2024-05-07
- 摘要：Fabric defect detection and classification (FDDC) plays an important role in the automated inspection of fabric products. In this paper, a novel defect detection method based on texture watershed is proposed. The properties of texture defects are characterized using the wavelet method. Texture gradient can be acquired by calculating the sub-band wavelet. Texture gradient contains many texture features and the boundary of texture regions in fabric images can be enhanced. Combined with the watershed transform, the defective regions in fabric images can be detected accurately. The proposed method achieves efficient and accurate performance on the detection of 6 fabric images containing fabric defects.关键词：image segmentation;fabric defect;texture watershed;wavelet transform3192|292|0更新时间：2024-05-07
- 摘要：In this paper, a novel edge detection algorithm based on cellular neural networks (CNN) is proposed for nucleated cell detection. This new algorithm applies particle swarm optimization (PSO) to design the CNN templates to identify the edge of a nucleated cell. In order to overcome the premature phenomenon of PSO, the variance of populations fitness is calculated, and chaos optimization theory is applied to enhance the PSO’s global optimization. According to the characteristics of nucleated cell, a three-step study strategy is specially designed to obtain the best CNN templates. Experimental results show the new algorithm is effective; its edge fitness rates and checkout rates are better than former algorithms.关键词：cellular neural networks;nucleated cells;particle swarm optimization;chaos3280|290|0更新时间：2024-05-07
- 摘要：In independent component analysis (ICA), a statistical latent variables model is employed to assume that the obtained data is a linear mixture of signals. To deal with the detection error when the nonlinear mixing signals of functional magnetic resonance imaging (fMRI) data are decomposed by means of ICA, a novel ICA method based on the instantaneous power of fMRI data is developed. Firstly, fMRI data are converted into its energy signals according to the energy form of electricity. Secondly, according to the relationship between blood oxygenation level dependent (BOLD) and T*2 signal, two types of instantaneous power of fMRI signals which represent the energy fluctuations of BOLD are proposed. Finally, based on the instantaneous power of fMRI data, the components correlated with the energies of brain activations are obtained by using a spatial ICA method. The effectiveness and advantage are elucidated through theoretical analyses and simulation tests, and it is also applied to vivo experimental epileptic fMRI, the results show that our method can robustly detect abnormal brain activities at resting state compared with the traditional ICA methods.关键词：independent component analysis (ICA);functional magnetic resonance (fMRI);blood oxygenation level dependent (BOLD);instantaneous power3657|277|0更新时间：2024-05-07
- 摘要：Aiming at solving the segmentation problem caused by the connection of lung nodule and vessel, a new adaptive bandwidth selection method based on EM is proposed and we apply it into nodule segmentation. Compared it to the method of bandwidth chosen based on statistical analysis rule or optimized rule, it has some advantages such as low time complexity and correct bandwidth in accord with a real problem.The vertical orientation vectors of vessels gradient was constructed as to normal distribution and the vertical orientation vectors of nodules gradient as uniform distribution, we modeled the nodule connected vessel, estimated model parameters by EM, and extracted bandwidth values in Mean-shift based on the weight of uniform distribution and bandwidth selection theorem. The proposed method was tested on synthetic data and the clinical chest CT volumes, and all the results were correct. The results revealed that the proposed method is successful in segmentation lung nodules connected vessel.关键词：lung nodule;EM;Mean-shift;vertical orientation vectors of gradients distribution feature3265|238|0更新时间：2024-05-07
- 摘要：The background difference is important for segmenting mobile objects. But this method highly depends on background quality and easily regards moving shadows as objects. To cope with these problems, a novel segmentation method is proposed for intelligent transportation system. Firstly, the background image is extracted in the RGB space by improving pixel grayscale classification，and is updated real time with selective update and background adjustment. Then, the motion regions are detected by summarizing and thresholding the RGB values in the difference image. Finally, the hue, value and border intersection, which are judged from top to bottom, from left to the right and inverse directions in detected regions, are utilized to detect and eliminate shadows in the HSV space. The experimental results show that this new method can effectively reconstruct background, eliminate shadow (especially dark object shadow) and improve segmentation quality.关键词：pixel grayscale classification;background reconstruction;object segmentation;border intersection;shadow elimination3168|243|0更新时间：2024-05-07
- 摘要：To extract the brain from cerebral MR image automatically and stably, an improved BET (brain extraction tool) algorithm is proposed in this paper. The improved algorithm simplifies the smoothing force used in BET which makes the contour of edge smooth and modifies the expansionary force used in BET to evolve the edge of brain according to the intensity distribution and the gradient of images. The modified expansionary force puts the contour fast when the contour is in the brain and puts the contour slowly when the contour is close to the edge of brain. The experiment results of the MR images from 100 patients processed by the improved algorithm are satisfying, but BET leads to 8 unsatisfying results whatever the parameters are set as, which shows the improved algorithm is more robust than BET algorithm when processing real MR images.关键词：BET;cerebral MR image;extraction of brain3393|250|0更新时间：2024-05-07
- 摘要：We propose a road-surface abstraction algorithm which is suitable for structured or semi-structured road environment and extracts effectively a road-surface for ground robot navigation. A fuzzy cluster method based on maximum entropy theories was employed to cluster Lidar points. After fitting clustered data linearly, the algorithm extracts seams that belong to road-surface by their location and angle. Current referenced horizontal can be acquired by comparing several continuous Lidar frames and then the algorithm extracts the obstacles in road area. Experiments show the algorithm works well in spite of road-boundary has regular shape or not, and is free from the impact of complex texture or irregular illumination of the road.关键词：robot;LiDAR;road-surface abstraction;fuzzy cluster;maximum entropy encoding3739|243|0更新时间：2024-05-07
- 摘要：A new feature extraction method for remote sensing image was proposed based on a novel wavelet transform algorithm. Different from binary wavelet transform partition the frequency domain by constant Q criteria, the method can partition the frequency domain freely through setting the ratio of bandwidth of adjacent wavelet. Feature extraction based on discrete cosine transform of the wavelet energy was performed. The results of C-means clustering and RBF neural networks classification experiments show that, the proposed feature of wavelet transform can effectively describe spectral curve, and has better classification rate than the traditional wavelet transform algorithm.关键词：hyper spectrum image;spectrum feature;novel wavelet transform;Q criteria;feature extraction3318|271|0更新时间：2024-05-07
- 摘要：The constructure of nonsubsampled directional filter bank (NSDFB) which is a full shift invariant is introduced, and a novel image fusion scheme based on NSDFB combining àtrous wavelet transform for multispectral image(MS) and panchromatic image (PAN) is proposed. The intensity component I of MS obtained by intensity, hue and saturation (IHS) transform and the PAN are decomposed using àtrous wavelet, and the high pass-bands are decomposed in multi-directional high pass-bands respectively by NSDFB. Then the high pass-bands and low pass-bands are fused by different fusion rules, and the I′ component is reconstructed by taking inverse NSDFB decompose and inverse a-trous wavelet transform. Finally, the fusion image is obtained by inverse IHS transform of I′ and the H, S component of MS. The experimental results show that the performance of the novel algorithm is better than IHS,principal component analysis (PCA) and the traditional fusion algorithms based on wavelet transformation, and especially can effectively eliminate the spectral distortion caused by PCA and wavelet transform.关键词：image fusion;nonsubsampled directional filter bank;àtrous wavelet transform;spectral distortion3762|255|0更新时间：2024-05-07
- 摘要：It is usually difficult to extract feature regions from two successive frames of SAR imagery which lack overlapping portion, because the effects of different random noise during the flight when forming SAR images. A new mosaic method for this sort of SAR sequential imagery is presented. Firstly, the flight information of the plane and geographical coordinates of several feature points in SAR images are used to conduct a rough match. And then, a detailed approach based on remarkable linear features extracted in adjacent areas of two images is used to determine the corresponding positions of two images, which can subtly mosaic the sequential images. Finally, the gray levels between two stitched images are fused to eliminate the remarkable seam. Experimental results testify that this algorithm is able to seamlessly stitch two successive images automatically.关键词：SAR images;linear feature;speckle;image mosaic;airborne SAR3733|216|0更新时间：2024-05-07
- 摘要：At present, the multimodality medical image registration has been all confined in registering two images and rarely involved N-dimensional images (three and more than three dimensions). Using the expanded N-dimensional mutual information measure (E-NMIM) to register multiple images inefficient, and cannot meet the clinical requirement.In addition mutual information(MI) values are not necessarily nonnegative. In this paper, we introduce a new N-dimensional mutual information measure (N-NMIM), which can ensure MI values are nonnegative, bounded to range from 1 to 2. At the same time, the rate of the registration has moved up. Then this definition is tested and proved to be effective on registration of three lumbar vertebra images through simulation, including CT,T1 weighted MRI and T2 weighted MRI.关键词：multimodality image registration;N-dimensional mutual information;similarity measure;affine transformation3026|262|0更新时间：2024-05-07
- 摘要：The fundamental matrix is an effective tool to analyze epipolar geometry and plays an important role in computer vision. This paper analyzes the shortcoming of traditional robust methods in estimating the fundamental matrix, and proposes a novel technique for estimating the fundamental matrix using LQS and bucketing technique in robust regression, which eliminates the drawbacks of RANSAC and LMedS. Experimental results on synthetic data and real images show that the proposed algorithm achieves high accuracy and robustness.关键词：computer vision;fundamental matrix;robust estimate;LQS;bucketing technique3870|201|0更新时间：2024-05-07
- 摘要：The objective of recovering writing order is to extract dynamic handwriting information from static text images, which can be seen as to convert a 2-dimensional image into sequences of 1-dimensional vectors of pentip positions along the time axis. This paper proposes a model for recovering writing order from offline handwritten Chinese character. In this model, a 4-layer hierarchy is presented to model each Chinese character, where character, component, subcomponent and stroke are located at each layer, respectively. Characters are decomposed into components and each component is decomposed to subcomponents in turn by four decomposing operators. The totally-ordered relations between subcomponents are retrieved by defining the corresponding rules between decomposed relations and a poset of subcomponents. Subcomponents are the basic recovering primitives in this model, whose writing orders are recovered by classifying strokes and pairs of crossing strokes. Experimental results show that the proposed method is effective and accurate.关键词：writer identification;hierarchical model;temporal information;stroke recovery3130|234|0更新时间：2024-05-07
- 摘要：The reconstruction of the surface is a basic problem in CG field. And the current research focuses on the reconstruction surface and the mesh optimization. Most processes a continuous surface. In order to reconstruct the broken surface, a new method is presented in this paper to approach the object surface with the subdivision method first and then calculate the discontinuous mesh automatically. This algorithm has been used in the 3D seismic data scientific visualization.关键词：Loop subdivision;reconstruction of scattered points2746|214|0更新时间：2024-05-07
- 摘要：The classification and recognition of the coke optical texture is one of the key elements to determine the quality and guide the production of cokes. As the results of the traditional methods in spatial and frequency domain are not so ideal, a fusion algorithm, which is based on WBCT and LBP, is proposed. Firstly, the method decomposes the coke micrograph with WBCT for multi-scale and multi-direction, and extracts the statistical features from each sub-band. Then in spatial domain, the features of coke micrograph are calculated with uniform LBP operator. Finally, according to the fusion similarity measure criteria, the classes of optical texture in coke micrograph are identified. Comparing with other methods, the results of experiments show that the proposed algorithm not only obtain a high recognition accuracy, but also has strong anti-interference ability, especially for the Poisson distribution of noise. Therefore, it is suitable for micrograph analysis of coke.关键词：coke micrograph;optical texture;multiscale geometric analysisl（MGA）;wavelet-based contourlet transform(WBCT);local binary patterns(LBP)3394|239|0更新时间：2024-05-07
- 摘要：Graph cutting is a popular technique for image segmentation. However, it is invalid for images with texture or strong edge. In this paper, we propose a novel segmentation method that graph-based color-texture region segmentation, which overcomes the shortcoming of existing graph-based segmentation method. This method computed feature vector of blocks using color moment, wavelets energy histogram and distance of blocks. Then we segment the image based on a minimal spanning tree. The experimental results show that our method is robust and efficient for image segmentations.关键词：graph cuts;wavelet energy histogram;texture feature;graph partitioning3585|237|0更新时间：2024-05-07
- 摘要：Different understanding results in different scenarios even for the same person to conduet visual analysis. In order to determine whether the behavior is abnormal in different scenarios, a double-layer bag-of-words model is proposed to solve the problem in surveillance system. The video information is processed in the first layer of Bag-of-Words, and the information of scenario-action text words is included in the second one. A video sequence is represented as a collection of spatial-temporal codebook by extracting space-time interest points. A behavior characteristic is represented as a collection of behavior text words in special scenarios. Probabilistic latent semantic analysis(pLSA)model is adopted to automatically learn the probability distributions of spatial-temporal words and the topics correspond to human action categories. PLSA also can learn the probability distributions of the motion text words in a scenario with supervisor and the topics correspond to anomalous or normal actions. The algorithm can categorize the human anomalous or normal action contained in the special occasion to a novel video sequence after being trained.关键词：abnormal action;interest points;double-layer bag-of-words;probabilistic latent semantic analysis;variable scenarios4030|251|0更新时间：2024-05-07
- 摘要：Automatic age estimation based on facial images is an important research trend of face recognition. Here we proposed an independent component analysis method based on winner-take-all（WTA）rule to realize the age estimation task. Firstly, applying the PCA method to reduce the dimensions of original training data; then, using the proposed WTA-ICA coefficient sparse description method to extract the feature.Finally, the experimental results on the FG-NET Aging database indicate that the proposed method can estimate peoples age based on the face images well.关键词：age estimation;WTA-ICA;sparse description;facial image3243|243|0更新时间：2024-05-07
- 摘要：In this paper we proposed a method for determining the passenger flux based on SVM(support vector machine)detection and Mean Shift tracker. With adaptive detection window, the histogram of the gradient orientations is extracted through the detection region. After classification and clustering, the initial head hypotheses are obtained. Then, the Mean Shift tracker is used to track them, and image sequences of the head are achieved. By the whole decision on the consecutive head sequences using SVM, the number of people is obtained. Experimental results show that the adaptive sliding window method reduces the time consumption, and the accuracy of detection is improved by the combination with head tracking.3454|295|0更新时间：2024-05-07
- 摘要：This paper proposes a new approach to moving cast shadow removal based on chromaticity, intensity and the edge information. Based on kernel density estimation and edge information of the input frame, an initial moving object mask and the corresponding edge of moving objects are obtained. Then a potential shadow region is obtained by extracting chromaticity and intensity information from the input frame. Finally, the moving cast shadow region is detected and then removed using region growing method. Experimental results demonstrate the good performance of moving cast shadow removal of the proposed approach.关键词：moving cast shadow removal;region growing;video segmentation3232|229|0更新时间：2024-05-07
- 摘要：To compensate for the performance degradation induced by phase noise, a low-complexity phase noise cancellation algorithm for OFDM systems is developed in this paper. This method utilizes Transmission Parameter Signaling(TPS), which are inserted in frames and then are used for signaling parameters. Based on an assumption that finite-length TPS sub-carriers can cover most energy of phase noise, the proposed scheme can remove phase noise effectively and achieve satisfying results of low complexity as well.关键词：OFDM;phase noise;TPS;digital terrestrial broadcasting3887|215|0更新时间：2024-05-07
- 摘要：In the interactive graphics applications such as games and augmented reality which require high demanding real time performance, the adoption of complex environment lighting has been increasing to illuminate the synthetic objects naturally in the dynamic scenes and make them merge consistently.we propose the Cook Torrance illumination model to accomplish the illumination computing.Our method analyze spherical harmonics to determine the lighting coefficients of high dynamic range environment map in real time and use them to obtain a quadratic polynomial form of high dynamic range environment map.Then calculate the expression in the shader to obtain the diffuse component of the illumination model. And the specular component of it is approximated via the technology of environment maps.Finally all of them are computed in GPU. The experimental results show our algorithm renders the synthetic objects at rates of over 30 FPS under dynamic complex environment lighting and achieves photo-realistic visual effect.关键词：complex environment lighting;mix of virtual and actual reality;illumination consistent;real-time rendering3376|247|0更新时间：2024-05-07
- 摘要：On the basis of two-dimensional linear discriminant analysis(2DLDA), a novel discriminant analysis named two-dimensional heteroscedastic discriminant analysis(2DHDA)is introduced, and is used for face recognition. In 2DHDA, equal within-class covariance constraint is removed and “small sample size” problem of heteroscedastic discriminant analysis(HDA)is solved. Firstly, criterion of 2DHDA is defined according to that of 2DLDA. Secondly, criterion of 2DHDA, log term is taken, and then the optimal projection matrix is solved by gradient descent algorithm. Thirdly, facial images are projected onto the optimal projection matrix, then, 2DHDA features of face images are extracted. Finally, nearest neighbor classifier is selected to perform face recognition. Experimental results based on olivetti research laboratory(ORL)and Yale mixture face database show the validity of 2DHDA for face recognition.关键词：two-dimensional heteroscedastic discriminant analysis;two-dimensional linear discriminant analysis;face recognition3544|243|0更新时间：2024-05-07
- 摘要：For non-parametric kernel density estimation information redundancy and repetition computation in the training stage estimate error and large amount of calculation in the estimated phase,this paper proposed a method of clustering difference image kernel density estimation for foreground object detection.We first choose those samples that have higher frequency and diversity to contain important information based on max-min distance clustering in training sequence.A Gausisian KDE is built to estimatea motion object after adaptive threshold image difference calculation.Experimental results were given to demonstrate that the proposed algorithms are elimination of the typical non-movement noise point for estimated error and improving real-time capability.关键词：kernel density estimation(KDE);clustering;difference image;foreground object detection3929|247|0更新时间：2024-05-07
- 摘要：In recent years, the animal iris recognition tend to become a new animal identification technology, which has potential applications to control the safety of the meat products. This paper presents an approach to cattle iris segmentation. The inner and outer boundaries of cattle iris are fitted respectively as two ellipses which are detected by following the least square principle, according to the feature of cattle iris structure. The inner ellipse is fitted by the edge points on the boundary of pupil. The outer ellipse is fitted by the edge points which are selected randomly on the boundary of iris in order to reduce the influence of the noise on the outer edge. The distance between the outer edge points and the fitted ellipses is calculated to decide the best outer ellipse in the cattle iris image. Normalization is carried out using a geometric method. Experimental results indicate the efficiency of the proposed approach.关键词：biometrics;least square principle;animal identification;iris recognition3584|212|0更新时间：2024-05-07
- 摘要：A new method for undersized part surface defect detection is proposed. In order to meet workpieces with different sizes and different surface geometry characteristics, we use the rectangular LED array with variable incidence angle as the light source. The original facing image is captured with CCD and treated with a series of pre-processing procedures. Then optimized Hough transform is adopted to fit circle rapidly for end face detection. Radial offsets from pixel point to fitted standard circle are calculated to acquire defected pixel points and then realize the quantitative evaluation for the end face defect. Experimental results show that this method can realize on-line detection of undersized part surface quality promptly and accurately as to improve the efficiency of existing production lines.关键词：visual detection;hollow cylinder;Hough transform;top-surface defect;undersized3709|289|0更新时间：2024-05-07
- 摘要：Stereoscopic Television system demands view scalability as well as high compression rates, which enables the video to be applicable to various terminals. To achieve view scalability, firstly, it is necessary to achieve view scalability for the encoding part. Then, a view scalable transmission scheme is needed. In this paper, based on a scalable encoding scheme, the author proposed a scalable multi-view video transmission scheme that perfectly realizes the concept of view scalability by remarkably reducing bandwidth consumption while being applicable to various terminals. All views are divided into three groups in the proposed scheme: base view, second view and other view. Streams from those three types of views are transported with separate multicast groups. Also, a stream shaping and synchronizing scheme is proposed to tackle with the network problems that arise in the implementation of view scalability.关键词：stereoscopic television;multi-view;scalable;multicast3134|319|0更新时间：2024-05-07
- 摘要：In this paper, we propose a new method to segment video object. Firstly, we smooth each frame with the mean-shift and region-growing method. And then, the motion vectors which are released by video coding are used to extract a moving object. Finally, the object segmentation method proposed in this paper is used to extract the video attention object. Experimental results show that the proposed method can effectively separate the video object from the sequence and has the strong robustness in multi-targets tracking especially for switching targets and deformed objects.关键词：mean-shift;information entropy;motion vector;object extraction3070|304|0更新时间：2024-05-07
- 摘要：Sorting problem has an important role in the field of video stream transmission.A sorting algorithm for multi-channel video stream is proposed. It uses the method of look up table in the circular linear two-dimensional table to sort the video stream packets received from multi-channels which is different from a traditional sorting method. It efficiently solves the problems such as uncontrollable delay, high complexity both in sorting and in memory management, the result has been verified through PC simulation which indicates that there is a linear relationship between the increase of packet number and the increase of the time which consumed during the sorting, while in a traditional sorting algorithm, when the number of the packet increases the time consumption will experienced an exponential growth. The statistical datas between this algorithm and traditional algorithms have shown that it can reduce time consumption when the number of packet increases.关键词：video stream packet;datagram mode;linear table2726|254|0更新时间：2024-05-07
- 摘要：In this paper, we present a novel approach to segmenting moving objects from the H.264 compressed based on recursive shortest spanning tree(RSST). Firstly, the motion vector is obtained from the H.264 encoder and then a dense vector field is formed after the vector is unified and accumulated with a backward iterative projection process. Secondly, global motion compensation is used to eliminate the global motion. Thirdly, a modified RSST arithmetic is used to make the blocks clustered.Thus,with the proposed method we achieved moving object segmentation. Experimental results for several video sequences demonstrate the effectiveness of the proposed approach.关键词：H.264;compressed domain;moving object segmetation;recursive shortest spanning tree（RSST）2892|238|0更新时间：2024-05-07
- 摘要：Multimedia sensor nodes processing power, storage capacity and communication is relatively weak, which posed a great challenge on video coding and transmission. This article will improve SPIHT(set partitioning in hierarchical trees) algorithm and propose an improved three-dimensional set partitioning in hierarchical trees(3D-MSPIHT)video coding algorithm. This algorithm uses three-dimensional lifting wavelet decomposition, improved methods of the root and partition, to achieve the resorting of coefficients and ensure that more important information can be encoded earlier in the bit stream. At the same time, it adopted the listless coding structure, as well as no need for complex and heavy motion estimation and compensation, achieved less memory and energy consumption, and considerable QoS(quality of service).The experimental results show that this algorithm is better than 3D-SPIHT, particularly in low bit rate circumstances; and compared to coding schemes such as H.264, besides the all square image quality, encoding speed enhance 11.5～11.8 times.关键词：video coding;lifting wavelet;3D-MSPIHT;multimedia sensor networks3173|245|0更新时间：2024-05-07
- 摘要：The paper presents an new approach to video quality assessment based on human perception and fusion. In the proposed method, the SSIM values are calculated with the different weighted values fused visual characteristics including contrast sensitivity, multi-channel structure, visual masking and so on. The method has the same properties of simplicity and efficiency as that of the SSIM method. And it is more suitable for perceived characteristics due to fusing HVS. The experimental results show that the method can reflect people’s subjective feelings in a better way and is better than other traditional methods in fitting M2(correlation coefficient of Non-linear regression), M3(spearman rank), M4(outlier ratio)of VQEG Phase I MOS.3728|224|0更新时间：2024-05-07
- 摘要：Distributed video coding(DVC)is a new paradigm for video compression, based on Wyner-Ziv’s lossy source coding theory. DVC features low-complexity video encoding and is robust against transmission errors. Common DVC loses information during the side information(SI)interpolation at the decoder. In this paper, we extract features from the adjacent frames which are used to interpolate the SI so as to predict the next bit of the reconstructed frame. The predicted bit is used to modify the probability density function(PDF)of reconstruction. The experimental results show that our method achieves higher PSNR and better subjective effects than other methods even when fewer bit planes are transmitted.关键词：distributed video coding;Wyner-Ziv coding;bit plane;probability density function(PDF)3639|215|0更新时间：2024-05-07
- 摘要：The fish motion essentially reflects the current state of water quality, so it is necessary to study the methods of obtaining the real-time dynamic motion characters of fish body in the field of biological water monitoring. Based on the analysis of fish locomotion model, the paper presents a fish activity model using the frequency of tail swing, which acquires some kinematical parameters, i.e., tail frequency, swimming velocity, acceleration and so on. The results show that the model,which can be used as the theoretical basis of the application, represents the fish motion activity accurately and efficiently in the biological water monitoring.关键词：tail swing frequency;skeleton centerline;motion activity;image analysis2975|225|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