最新刊期
卷 13 ， 期 4 ， 2008
- 摘要：A new baseline based shape coding algorithm is designed in this paper. Distance set and turning point are chosen from the shape contour，and coded by DPCM. So the 2 dimensional data can be described by 1 dimensional data，and K K reduce the bit streams effectively. The algorithm can adapt to every particular boundary trend，and gives a better reconstructed effect〖JP〗The reconstructed shape only has a geometrical error，and can overcome the ladder effect which always appears in the block based shape coding关键词：distance set;turning point;baseline;shape coding3615|170|0更新时间：2024-05-08
- 摘要：n this paper, a new intra prediction algorithm for enhancement layer in spatially scalable video coding is proposed. It takes the spatial correlation between adjacent layers into consideration, and makes use of the magnified decoded and reconstructed base layer block for intra prediction in the lack of neighboring predicting samples. Furthermore, two adaptive weight factors (Wv, Wh) related to the texture characteristic within an image are introduced to improve the coding efficiency of proposed algorithm. Experimental results show that the PSNR value of luminance component has been increased and both coding bit rate and computation complexity are preserved. As a result, it can be used as an efficient intra coding scheme for enhancement layer in spatially scalable video coding.关键词：H.264;intra prediction;scalable video coding;spatial enhancement layer2443|178|0更新时间：2024-05-08
- 摘要：This paper presents a novel DCT coefficients layered scrambling algorithm (DCLSA) for H.264/AVC based on the deficiencies of current DCT coefficients encryption algorithms in respect of security,compact ratio and signal to noise ratio. According to the characteristics of the 4×4 DCT transform of H.264/AVC,the algorithm first divides the coefficients of every 4×4 block of the same macro block into several layers,and build a coefficients layered model. Then different layer is scrambled,respectively,by security requirements to achieve secure video coding. DCLSA has shown significant advantages on security,compact ratio and signal to noise ratio through performance comparisons with other algorithms and concrete experimental results,thus making it especially suitable for secure network applications.关键词：H.264/AVC;DCT coefficients scrambling;video encryption;key synchronization2846|200|0更新时间：2024-05-08
- 摘要：Excellent smoothing algorithm should be able to deal with images corrupted by noise and has the capability of preserving detailed information. Robust filtering is a very easy algorithm, but it has disadvantages that it cannot filter images which are highly corrupted. In this paper, both the traditional robust filtering and its existing improved algorithm are analyzed and realized. Meanwhile, a new adaptive robust filtering is proposed. Based on platform MATALB, comparing the proposed algorithm and these existing algorithms proved that this new algorithm can work properly when images are highly corrupted and preserve image details better than those present algorithms.关键词：robust filtering;image filtering;salt and pepper;adaptive2670|222|0更新时间：2024-05-08
- 摘要：To reduce the complexity of I frame mode decision process，a fast mode decision algorithm is proposedA low pass filter is implemented for each macroblock. After the macroblock is smoothed by this filter we compare the result with the original data and generate the difference between themThen the basic candidate mode class is determined based on the difference，so that the number of candidate modes is reducedTherefore this new method can reduce the complexity of mode decision process in H264 coding at a certain degree with almost no influence on the performance and the bitrate. Further experiments indicate that this new method can save about 16% time in computation with 01dB decline of performance，and less than 1% increase on bitrate关键词：I frame;intra prediction;low pass filter2870|169|0更新时间：2024-05-08
- 摘要：Pixel analysis is the primary step for region,shape and texture analysis and even for semantic analysis. The correctness of the color and luminance analysis of certain pixel in an image or a series of video streams is a guarantee to the acceptable result of other image processing. Based on a reasonable mapping operation to vectors in RGB color space,this paper applies the ART2 to the layered detecting approach to categorize color pixels. The processing steps and final results not only demonstrate the functions of “neoteny learning” and adjusting of vigilance value,but also illustrate that the method is coherent with the human psychological and physiological process of observing an image and also has strong adaptability for shadow noise suppression.关键词：pixel analysis;shadow;ART2;image processing2604|182|0更新时间：2024-05-08
- 摘要：n this paper ,slant correction methods of vehicle license plate are analyzed and an approach based on color pair and principal component analysis is prestented.A pixel is considered as a color pair point if its color pattern matches the combination of the background color and text color of the plate.The principal component orientation of the plate is achieved through principal component analysis of the color pair pixels.The principal component orientation is considered as the slant angle of the plate and the correction of the plate is accomplished.The experiment results demonstrate that this method makes the correction of the plate easier and more precise.The images of dirty vehicle license can also obtain effective results through this algorithm.关键词：vehicle license plate;slant correction;color pair;principal component analysis (PCA)3408|200|0更新时间：2024-05-08
- 摘要：Recently,Katsevich proposed an exact FBP algorithm and its improved version for image reconstruction in helical cone beam CT. In this paper,we present a new FBP image reconstruction algorithm based on the Katsevich’s original algorithm paradigm. This proposed algorithm can achieve good image quality improvement and fewer artifacts since it successfully avoids the direct derivatives with respect to rotation angle,The new algorithm still performs a 1D shift invariant filtering of the modified data on the detector plane and the redundancy weight is applied after filtering,allowing a more efficient numerical implementation. Results in these studies confirm the observation that the proposed algorithm can improve the image resolution over Katsevich’s original algorithm with noiseless and noise projection data.关键词：computerized tomography;helical cone beam;Hilbert filter2744|196|0更新时间：2024-05-08
- 摘要：The 3D laser scan technology is applied in the digital model of great historic site,which is involved with data acquisition,data post processing,rebuilding 3D model,etc. In this paper,we used that the first fete pit of San Xingdui ruins as an example,which used Riegl LMS Z420i 3D laser scanner and Nikon D100 digital camera to obtain geometry point clouds and texture separately. And then,we accomplished that the registering multiple laser scans and accurate 3D model by the soft ware of PolyWorks. In conclusion,we could present the whole process flow in the digital model of great historic site.关键词：laser scan;data register;ICP algorithm;3D model3082|186|0更新时间：2024-05-08
- 摘要：Most threshold based segmentation algorithms rely on the information of the gray level of the original image，without taking account of the spatial information. In this paper a new segmentation method is proposed，in which K means algorithm is combined with mutual information (MI) technique. The initial threshold can be chosen by using K means algorithm，and in the iteration process，an optimal threshold will be determined by maximizing the MI between the original and the segmented image. We evaluate the effectiveness of the proposed approach by applying it to the segmentation of medical images and license plate images. The experimental results indicate that the new method has visually better segmentation effect.关键词：image segmentation;thresholding;mutual information;K means algorithm2927|206|0更新时间：2024-05-08
- 摘要：This paper presents the concept of optimal two dimensional entropy function at first.Then we presents an undistorted fast recursion algorithm and a distorted optimal search strategy.In this way,the proposed algorithm can decrease computational time when it gets the similar image segmentation as traditional algorithm does.Finally we analyze and validate the algorithm theoretically and experimentally.关键词：two dimensional entropies;fast recursion;search strategy2705|158|0更新时间：2024-05-08
- 摘要：Threshold selection is the critical process of image threshold segmentation method.Considering the neglect of spatial correlation of image pixels in current threshold segmentation methods,we propose to combine Hilbert image scan with wavelet transform to obtain a continuous and smooth threshold curve,and then propose a local self adaptive threshold method in this paper.Firstly,the image is translated into 1D Hilbert order via Hilbert image scan method；Secondly,the curve of the developing trend of the Hilbert order is obtained by the multi resolution analysis using wavelet transform.Furthermore this curve is chosen as self adaptive threshold and the Hilbert order binarization is realized.Lastly,the binaried Hilbert order is translated into 2D image using the reverse Hilbert matrix scan and the image segmentation is achieved.The threshold curve achieved by the above mentioned method is able to self adaptively adjust along with neighborhood property,and reflects the developing trend of grayscale information in current image region.So the present algorithm preserves the local information and the relativity of adjacency pixels in the image.Moreover,it also improves the efficiency of image segmentation.Experiments indicate that the proposed method is an extraordinary effective image segmentation technique.It is with very good performance and immunes to noise.关键词：image segmentation;image scanning;Hilbert curve;multi resolution analysis;threshold curve2957|207|0更新时间：2024-05-08
- 摘要：A combined method to segment fingerprint images,based on automatic parameter normalization,is presented in this paper.Taking directional field and gray variance information in the fingerprint image into account,the method holds an efficient and robust feature.Compared with fixed parameter normalization in former segmentation methods,the automatic parameter normalization presented in this paper can normalize the fingerprint image to a maximum extent while not deteriorating any local image feature.关键词：fingerprint segmentation;histogram;threshold;Valid area window;Gray variance2636|192|0更新时间：2024-05-08
- 摘要：In this paper，a fractal based graph theoretic approach for face recognition is presented.Based on the image compression of fractal,pixel blocks(Range blocks) are defined as basal elements. The interdependence of pixel blocks is inherent within the fractal code in the form of circular plants. Fristly，the fractal code of face images is calculated and the corresponding circular plants can be obtained.Secondly，affine parameters for each pixel block are computed according to the acquired circular plants. Lastly，face recognition can be realized by appropriate distance measurement. The presented way is more effective，faster and more robust than the previous technique based on pixels. In addition，we detail the growth of circular plants in a general case to cover the shortage of predecessor.关键词：face recognition;fractal compression;graph expression;circular plant2641|246|0更新时间：2024-05-08
- 摘要：Two dimensional (2D）feature extraction using methods such as 2DPCA(two dimensional principal component analysis）and 2DLDA(two dimensional linear discriminant analysis）is of interest in face recognition because it extracts discriminative features faster than one dimensional (1D）discrimination analysis.Recently,diagonal principal component analysis (DiaPCA）is proposed for face recognition based on 2DPCA.DiaPCA reserves the correlations between variations of rows and those of columns of images.It overcomes that the projective vectors of 2DPCA only reflect variations between rows of images and variations between columns of images are omitted,while the omitted variations between columns of images are usually also useful for recognition.However,DiaPCA in particular cannot make full use of discriminative information during process of feature extraction and the projective vectors of 2DLDA also only reflect variations between rows of images,Therefore recognition performance of DiaPCA and 2DLDA is affected.To solve the problem,diagonal linear dicriminant analysis (DiaLDA）was proposed in this paper.Experimental results on ORL and FERET face database demonstrate the proposed algorithm is superior to 2DLDA and DiaPCA method and some existing well known methods.关键词：2DPCA(two dimensional principal component analysis);2DLDA(two dimensional linear discriminantanalysis);DiaPCA(diagonal principal component analysis);DiaLDA(diagonal linear dicriminant analysis);feature extraction;face recognition2676|202|0更新时间：2024-05-08
- 摘要：In this paper，a novel learning algorithm called center based neighborhood embedding(CNE) is proposed to deal with face recognition. Unlike the classical methods such as local linear embedding(LLE) and local preserving projection(LPP)，CNE is a supervised linear dimensionality reduction method. It first computes centers of all sample classes. The input of the weight function between two samples was replaced by center based neighborhood(CN) distance. Then，the high dimensional data are embedded into a low dimensional space with preserving the CN geometric structure. The CNE approach is compared with principle component analysis(PCA)，linear discriminant analysis(LDA) and local preserving projection(LPP) on ORL，Yale and UMIST databases. Experiments demonstrate the proposed method is superior to other three methods in terms of both lower dimensional visualization and recognition accuracy.关键词：face recognition;center based neighborhood embedding;supervised learning;linear dimensionality reduction3076|221|0更新时间：2024-05-08
- 摘要：A multi model segmentation and recognition algorithm of courtesy amount on Chinese bank checks with the form lines is presented in this paper.Based on some characteristics of Chinese bank checks,we adopt three models for different parts of the courtesy amount.The pre segmentation model deals with the isolated characters.The touching zeros detection model is designed for the part of touching zeros.The segmentation based recognition model deals with other touching part in the courtesy amount.In the third model,we use genetic algorithm to accelerate the searching process.The system is validated with 1 053 real bank checks.The reject rate is 336%,and the recognition rate at the amount level can reach 661%.The experiment results show that the recognition rate of the real bank checks can be improved with this new method.关键词：multi model segmentation;recognition;courtesy amount;bank check2671|210|0更新时间：2024-05-08
- 摘要：Principal Components Analysis (PCA）and Linear Discriminant Analysis (LDA）are two popular feature extraction methods for pattern recognition,and in image recognition,researchers usually use PCA+LDA instead of LDA.An enhanced linear discriminant analysis (ELDA）criterion,which integrates their merits,is proposed in the paper.It can not only overcome the PCA’s shortcomings of lower precision when using the minimal distance,but also resolve the problem of projective vector solution of LDA when the within class scatter matrix is singular.So the two step method of PCA+LDA can be substituted by ELDA.Moreover,its recognition rate exceeds the single PCA,LDA,or PCA+LDA largely.Many experiments on ORL,YALE and NUST603 face database indicate that our method is effective.2968|203|0更新时间：2024-05-08
- 摘要：A lane and preceding vehicle detection and overtake system based on the monocular vision is designed for intelligent vehicle in structural two lane road environment，which can work in both sunny and cloudy days. Experimental results show that the algorithm used in the system can detect the lane and the different preceding vehicle and overtake vehicle automatically，safely and exactly under different visibility conditions.关键词：monocular vision;lane detection;preceding vehicle detection;overtake vehicle2829|217|0更新时间：2024-05-08
- 摘要：To improve the accuracy rate of passenger flow estimation during rush hour,a vision based procedure to estimate passenger flow in buses was presented for the embedded application.The contour feature of the passenger’s head was exploited to locate every passenger’s position.In order to eliminate the false candidate head contour effectively and obtain the position of every passenger accurately,the modification of the Hough Transform to detect quasi circle and the perceptual grouping with fuzzy measures were applied.The results of field tests show the accuracy rate may reach above 85 percent by using the proposed method to estimate the passenger flow in bus.关键词：passenger flow estimation;Hough transform;perceptual grouping;fuzzy measure3085|262|0更新时间：2024-05-08
- 摘要：A global optimization method based on mutual information is proposed for multimodality medical image registration. First external surfaces are extracted from various image modalities and the ICP algorithm is adopted to initially align unregistered images. Then the registration is performed by maximization of normalized mutual information using a deterministic global optimization algorithm named Dividing Rectangles. The surface based matching is used to provide a good start point for Dividing Rectangles in order to fully utilize its high efficiency in small search space. The results of experiment on three dimensional human brain data show that this method is accurate, fast, and avoids local minimums efficiently.3381|209|0更新时间：2024-05-08
- 摘要：Background reconstruction is the key to moving detection. So a background reconstruction algorithm based on the hypothesis of background pixel with maximum probability is presented in this paper. First, we calculated the difference between sequential frames which are sampled from a section of video sequences, and get the full moving area by area growing, then label the pixels in moving area as moving points and others as background point. We calculate the mean of the intensity value of the background point in these frames [JP]and consider the mean of the intensity value as the background pixel intensity. The results of experiments show that this new algorithm can reconstruct the background quickly and successfully.关键词：background subtraction;background reconstruction;area growing;motion detection3666|242|0更新时间：2024-05-08
- 摘要：In this paper a dynamic background modeling approach for moving objects detection is proposed. This model is based on mixture Gaussian model suggested by Stauffer et al. It constructs a mixture Gaussians Model for each pixel. In sequence frames subtracting the model classify the pixels in each frame into background area，uncovered background area and moving objection area. In order to quick restore the background covered by stagnated objects when they move again，the model set the update rate in uncovered background area larger than which in background area. Compare to the Stauffers model，our model moving objection area no longer creates new Gaussian distribution，so it can avoid classifying slow moving objects to the background.The experimental resultal indicate that our model has preferable adaptive performance to the scene with many uncertain factors，and correspondence quickly.关键词：background model;mixture Gaussian model;moving object detection;frames subtraction4375|291|0更新时间：2024-05-08
- 摘要：Techniques for video abstraction has attracted tremendous attention for its application in video browsing,video indexing,video retrieval and so on.Video abstraction is brief summary of the video content like the text abstraction.In the paper,an automatic method for video abstraction is presented which is based on manifold modeling and mixture model.Manifold modeling is applied to generate the scene manifold of the video,Isomap is used to reduce the dimension of the video frames in larger scenes and the low dimension vectors are put into the mixture model with model selection to complete cluster analysis.Because mixture model with model selection can adapt to the data from any distribution, it is applied to generate the video abstraction automatically.The results from manifold modeling together with those from mixture model constitute the abstraction results.The experiments present the abstraction with less redundance,which demonstrates the effective and efficiency of the proposed method.关键词：video abstraction;Manifold learning;isomap;model selection;mixture model2910|232|0更新时间：2024-05-08
- 摘要：To deal with the limitation of robot’s working range, a multiple axes laser 3D scanning system is constructed by robot, a portable 3D laser scanner and turntable. Using a sphere with a known diameter as calibration tool, the pose of the portable scanner relative to the robot is calibrated accurately by scanning the sphere and computing the center position of the sphere. Meanwhile, a method is proposed to calibrate the pose of the turntable relative to the robot. In this approach, several rotational angles of turntable and two different height of the sphere are made to determine the rotational axis of turntable. Experiment results show that the multiple axes laser scanning system can measure the object of large scales from multiple angles and directions. Meanwhile, this system is robust flexible and of high measurement accuracy.关键词：computer vision;robot vision;3D laser scanning;TCP calibration2910|367|0更新时间：2024-05-08
- 摘要：Stereo matching is one of the most important researches in computer vision.In order to obtain dense and correct disparity,a stereo matching algorithm using dynamic programming and left right consistency is presented.Firstly,the left and right disparity space images are computed using the left and right images as basic image separately.Secondly,in the computed disparity space images,the disparity images are computed using dynamic programming.Then the left right consistency of the disparity images is used to remove the mismatching pixels,and to generate the part of near real disparity images.At last,according to the ordering constraint of disparity image,a method detecting the searching space of unmatched pixels is presented.And an ordinary but efficient strategy is proposed to finalize these pixels.The experiments on some standard stereo pairs are executed,and the results show the algorithm is effective.关键词：stereo matching;dynamic programming;left right consistency;disparity searching strategy5208|235|0更新时间：2024-05-08
- 摘要：Image matching is very important in image processing.The conventional matching methods are easily affected by occlusions,light and noises,which make the matching more complicated.In order to improve the robust performance of image matching,this paper proposes an orientation based robust Hausdorff distance for image matching.An edge detector based on the direction information is performed to get edge image.To achieve the promptness of image matching,EMR (edge matching rate）is introduced to determine which position can be the possible matching location,and further to construct a similarity measure based on the improved Hausdorff distance to find the correct location.The experimental results show that the proposed algorithm speeds up the matching process and it improves the resistance to noise.In addition,this method matches the image occlusions correctly and overcomes the mismatching problems that induced by noise,spurious edge segments and outlier points,which demonstrate that the proposed method is feasible and effective.关键词：image matching;Hausdorff distance;edge detection2863|207|0更新时间：2024-05-08
- 摘要：3D tiling patterns with the symmetry of the extended Picard group are automatically generated by means of dynamic systems equivalent to the extended Picard group.The derived patterns have the symmetry of the wallpaper group pmm on the cross section plane parallel to the xy plane,and own the symmetry of the extended modular group on the cross section plane containing the x axis.The numerical experiments show that the generated patterns are artistic.The method provides a novel approach to devise exotic symmetric tiling patterns from a dynamic system’s point of view.关键词：extended Picard group;tiling pattern;quaternion;symmetry3096|222|0更新时间：2024-05-08
- 摘要：As the previous two step texture mapping algorithm does not suit the annular objects,a texture mapping algorithm for the annular objects is proposed.The torus is chosen as the media surface,whose upside and underside are mapped respectively with two pairs of the same style textures applying restraint of equal ratio of areas.The two textures are stitched on the torus using the interpolation technique to avoid the joint.Finally,the media surface normal method is adapted to map the texture from the torus to the object’s surfaces.The experimental results show that the algorithm can be used to map the texture from the plane to most of the Annular Object’s surfaces,on which the rendered texture has little distortion and looks continuous.The proposed method can be used in realistic rendering or VR system to map texture onto the surfaces of annular objects.3305|202|0更新时间：2024-05-08
- 摘要：In order to integrate a virtual object in a real scene seamlessly in augmented reality(AR）system,we need to simulate the interactions of the virtual object with the illumination of the scene.Acquiring the knowledge of illuminant direction is crucial in this work.We present a novel approach for estimating the direction from a single image of a scene that is illuminated by a light source regardless it is point light source or directional one.We propose to employ a maker cube,which is used to register to determine the rigid transformation relating 2D images to known 3D geometry,and a lambertian probe sphere,which is used to estimate the light source direction by image processing.The key process is to find and extract the intensity occluding curve on the sphere.Experimental results show that our approach is computationally efficient and the light source direction can be accurately obtained by it.关键词：augmented reality;illuminant direction detection;image processing3143|196|0更新时间：2024-05-08
- 摘要：PTZ (Pan/Tilt/Zoom）cameras have been widely used in visual surveillance domain because of its capability of changing both view angle and image resolution.Dual PTZ camera system is one of the simplest systems that multi resolution information and stereo information can be obtained synchronously.Although there are few related researches about dual PTZ camera system in the state of the art,we believe it has wide aspplication prospects.Building the common coordinate system is an important problem in dual PTZ camera calibration,which can be used for image alignment and stereo matching.From this point,we adopt the longitude latitude coordinate system and use a multi fundamental matrix approach to deal with the calibration problem.Traditional multi camera calibration approaches mainly deal with the static cameras,and which always take advantage of the known camera locations or use calibration tools.The proposed calibration is independent to specific PTZ parameters,which is very convenient in application.The experimental results show the practicality of our approach.关键词：PTZ camera;calibration;epipolar geometry;fundamental matrix;stereo rectification5545|191|0更新时间：2024-05-08
- 摘要：With the decreasing price of multimedia capturing and processing devices, as well as the capability to capture more complex, and sophisticated objectives, multimedia systems are facine the challenge of large data analysis and management. How to handle real time capturing, compressing, transferring, decompressing as well as information representation and management in a multimedia system has become an important research topic. We propose a real time distributed multimedia system framework for dynamic context environment based on a survey of the requirements of multimedia systems under dynamic context environment. It can be divided into two parts, the software infrastructure and the information system, fusing all needed functions in a real time distributed multimedia system into a unique framework. The former is used to encapsulate the function of capturing, compressing, and decompressing and so on, isolating logical functions from physical devices. The latter is used for information representation, isolating information from special capturing or processing devices, and it also provides the capacity of information management, which means users can search for specified information later. The experiments of the meeting system based on this frame show the openness, configurability and extensibility of our framework.关键词：framework;context;real time;distributed4846|213|0更新时间：2024-05-08
- 摘要：To classify correctly the runing vehicles in the crossing is the basis of traffic flow statistics,traffic situation analysis,and accident analysis.Based on the detection for running objects and the calibration for representation,we draw into the multi support vector machine and propose a method to classify the vehicles in crossing,which needs several features and can overcome “wrong classification”.The test shows that the method has high accuracy and can meet the requirements to classify the vehicles at cross roads.Furthermore,based on the former study,we also offer a method to obtain“flowing speed” and provide a basis for the traffic management.关键词：vehicle classification;multi class support vector machine;representation calibration;feature extracting;flowing speed4243|205|0更新时间：2024-05-08
- 摘要：Video smoke detection has many advantages over traditional methods,such as fast response,non contact.But most of current methods for video smoke detection have high rates of false alarms.Through analyzing the characteristics of smoke motion,a novel video smoke detection is presented.In order to accelerate detection speed,video images are divided into blocks.Each block motion orientation is estimated by block matching methods.And a time sequence of motion orientation for each block is generated over a sliding time window.Then accumulation and main motion orientation are computed according to the sequence.The accumulation represents the degree of motion duration and the main motion orientation describes the maximum possible orientation of each block over the time window.A 3D feature is extracted from the accumulation and main motion orientation,and a Bayesian classifier is used for smoke detection.Experiments show that the algorithm is robust and significant for improving the accuracy of smoke detection.关键词：video smoke detection;accumulation;main motion orientation;feature analysis;computer vision6637|244|0更新时间：2024-05-08
- 摘要：In this paper we analyzed and researched the cause of the error during the aerial detection sequence continuous image stitching.The stitching of large visual battlefield damage panoramic image is important in military,but the accumulation of the error usually results in awful image quality or stitching process’s failure.Aiming at the character of complicated movement pose of floating aerial platform and the difficulties to establishing imaging model,in the paper presents a method which can avoid accumulated errors by transforming the base image in the continuous stitching process.The experiment with the floating aerial platform real time serial images and the simulated serial images proves that the transform of base image can obviously weaken the accumulation of error in stitching,and repetitious transform can induce the local edge’s distortion,but it does not have infection to the past processing and application.We present an effective method to avoid errors in image stitching under the situations like complicated vision transform.关键词：error analysis;error elimination;recon sequential;image stitching5127|204|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