最新刊期
卷 19 ， 期 5 ， 2014
- 摘要：This is the nineteenth in the annual survey series of the yearly bibliographies on image engineering in China. The purpose of this survey work is mainly to capture the up-to-date development of image engineering in China, to provide a convenient means of literature searching facility for readers working in related areas, and to supply a useful reference for the editors of journals and potential authors of papers. Considering the wide distribution of related publications in China, 716 literatures on image engineering are selected carefully from 2986 research and application papers published in 140 issues of a set of 15 Chinese important journals related to image engineering. Those selected literatures are classified first into 5 categories(image processing, image analysis, image understanding, technique application and survey), and then into 23 specialized classes according to their main contents(same as the last 8 years). Some analysis and discussions about the statistics made on the results of classifications by journal and by category are also presented, respectively. According to the statistics and analysis on the results, it seems that image segmentation is still a focus and critical point in image analysis, and has strong challenging; identification of image authenticity and inpainting for image integrity get more and more attentions recently; the research on human biometrics based on image techniques requires some new pushing force; and the domains of remote sensing, radar as well as survey and draw are the hottest field for technology applications of image engineering in 2013. This work shows a general and off-the-shelf picture of the various progresses of image engineering research and application with some new developing characteristics and tendencies in China in 2013.关键词：image engineering;image processing;image analysis;image understanding;technique application;literature survey;literature statistics;literature classification;bibliometrics4013|503|0更新时间：2024-05-07
- 摘要：CCSDS-IDC(consultative committee for space data systems-image data compression),which has been proposed as a space remote image data compression standard by NASA,is suitable for synthetic aperture radar(SAR) amplitude image and other remote sensing image compression. It uses discrete wavelet transform(DWT),and performs hierarchical DWT coefficients encoding from large scales to small scales in the bit plane encoding. When the energy of DWT coefficients mainly concentrates on the large scale(low frequency) and there is energy attenuation from largescale to small scale,CCSDS-IDC can achieve high compression efficiency. Unlike optical images,SAR image data is always complex-valued,which has a wide range of use. For example,interferometric SAR can use the phase difference of two complex SAR images to obtain elevation information and has been widely applied in environmental monitoring,mapping,and other fields. However,vast amounts of complex SAR image data require transmission and storage resources,which raise the needs for efficient SAR complex image data compression. In this paper,we study the performance of CCSDS-IDC for complex SAR image data and identify that CCSDS-IDC suffers from low efficiency for complex SAR image data coding. As the real part and imaginary part of SAR complex image data have many high-frequency oscillation components,the large-amplitude significant DWT coefficients mainly concentrate on a small scale and the DWT coefficients do not exhibit attenuation from large scale to small scale. Due to this,CCSDS-IDC has to spend a large amount of bits on coding the significant DWT coefficients on a small scale for the complex SAR image data,which degrades the rate distortion performance of CCSDS-IDC. Considering the clustering characteristics of DWT coefficients corresponding to the spatial structure of the SAR complex image data,we propose Quadtree Coding(QC) based on DWT for complex SAR image data compression,and find that QC achieves high performance for complex SAR image data. Compared with CCSDS-IDC based on DWT,QC based on DWT can improve the amplitude peak-signal-to-noise-ratio(PSNR) up to 4.4 dB and reduce the MPE up to 0.368 at the same bitrate. Though the directional lifting wavelet transform(DLWT) can aggregate the energy of wavelet coefficients to low frequency and improve the performance of CCSDS-IDC,the QC based on DWT still outperform the CCSDS-IDC based on DLWT for complex SAR image data compression. Compared with CCSDS-IDC based on DLWT,the QC based on DWT can improve the amplitude PSNR up to 3.08 dB and reduce the MPE 0.25. For other images,such as SAR amplitude images and optical images,which exhibit different DWT coefficients properties from that of complex SAR image data,QC based on DWT also achieves nice compression performance. CCSDS-IDC has a poor performance for complex SAR image data,however,the QC is more suitable for complex SAR image data coding. For designing image coding algorithm based on DWT,compared with using the attenuation property,exploiting the clustering property may be the first choice to code more kinds of images efficiently. This is because clustering characteristic being related to the image geometrical structures always exist while attenuation characteristic being related to some smooth constrains may lack for some kinds of images.4011|357|0更新时间：2024-05-07
- 摘要：Reconstruction algorithms are critical for the successful use of the compressive sensing theory. To reduce the signal reconstruction time and ensure the relatively high reconstruction accuracy of the directional pursuit algorithm,an algorithm for compressive sensing signal reconstruction is studied. In this paper,a nonmonotone memory gradient pursuit algorithm(MGP)for reconstructed signals is proposed. Under the framework of direction pursuit based on optimization theory,the algorithm first adopts a regularization orthogonal matching strategy to select atom sets fast and efficiently. However,both the least square method part for residual minimization and the direction update part of regularization orthogonal matching are abandoned. Instead,the search step size is determined by a non-monotonic linear search strategy, Furthermore the update direction is fixed with the memory gradient algorithm which increases the degree of freedom of parameter selection. After that,estimated values of sparse coefficients are established. The proposed algorithm takes full advantage of globally fast and stable convergence of the memory gradient algorithm with Armijo line search to avoid local optimal solution under some mild condition. By choosing a larger accepted step size at each iteration, Therefore the evaluation of optimization function can be effectively reduced. Besides that,by formula derivation and clever manipulation, the parameter of the direction search can be calculated more rapidly. In this way,the efficiency of convergence is improved. Derivation of direction parameter formula in the original memory gradient method is achieved,and it is more efficiently. The computational cost for memory gradient algorithm is 30% less than that of approximate conjugate gradient pursuit algorithm. Moreover, the MGP algorithm is less insensitive to Gaussian noise than other greedy iteration algorithms. Finally,the one dimension signal and image signal is reconstructed accurately.The reconstruction quality is better when sample rate exceeds 0.2. The experiment results of one-dimensional signal and two-dimensional image signal demonstrate that the algorithm is striking a balance between efficiency and reconstruction accuracy and that it has an improved signal reconstruction performance. Additionally,under the same test conditions the proposed algorithm outperforms other similar reconstruction algorithm in time and quality.关键词：compressive sensing(CS);image reconstruction;directional pursuit;memory gradient method4084|296|0更新时间：2024-05-07
- 摘要：Motion blur due to camera shaking during exposure is a common phenomena of image degradation. Moreover, neglecting the outliers that exist in the blurred image will result in the ringing effect of restored images. In order to solve these problems, a method for camera-shake blurred images restoration with disposing of outliers is proposed. The algorithm, which takes the natural image statistics as prior model, combines variational Bayesian estimation theory with Kullback-Leibler divergence to construct a cost function, which can be easily optimized to estimate the blur kernel. Taking into consideration the ringing effect causing by outliers, an expectation-maximization based algorithm for deconvolution is proposed to reduce the ringing effect. A large quantity of blurred images are restored with this algorithm, the experimental results show that the algorithm of blind image restoration can effectively remove the blur caused by camera shaking, and can effectively reduce the ringing effect, while preserving the image edge and details. We propose a new method for blind image restoration, which deals with the outliers for suppressing ringing effect to improve the effect of restoration. The experimental results show that the method is practical and effective; this method also triggers the thinking about a new way to suppress ringing effect.关键词：camera shake;image restoration;expectation-maximization algorithm;kernel estimation5056|674|0更新时间：2024-05-07
- 摘要：Video caption contains abundant information related to the video content. Recognizing text in images is the premise of making full use of this information. Although optical character recogonition (OCR) software recognition accuracy has been improved,the video captions with complex backgrounds still cannot be recognized well. Therefore,in order to improve the recognition accuracy,the extracted caption shall be enhanced which can reduce the complexity of caption background and improve the contrast between background and text. In this paper, we propose a method of fusing multi-frame information to realize caption enhancement based on the Logistic model. Logistic curve is a common form of an S-type curve, which either end or converge to a constant. By counting and analyzing distribution proportion of different pixel values in a single background caption,we establish a proper Logistic model whose output can be used as the enhanced caption's pixel values and their distribution proportion shall generally be kept consistent with the single background caption. According to the convergence of the Logistic model,the majority of pixel values can be assigned to 0 or 255,and a small quantity of gray points can be taken as transitions of black points and white points. Therefore,the enhanced caption image not only keeps the continuity of the pixel values but also improves the contrast between background and text. Then we detect and track the video caption,and align the same segments of caption, which appears in consecutive frames to obtain multi-frame information of the pixel. In order to reduce the complexity of the background,we analyze the characteristics of the background changing in the time domain as well as, the inherent characteristics of the background and text. Furthermore, we take the fusion of them as the characteristics of Logistic model. Normalizing the characteristic of the model based on caption blocks which is the unit of enhancement,we take the result as the input parameter of the Logistic model. We select 60 videos with caption from the Paike column of Youku and divide caption into three categories:the special complex background caption containing shadows or stroke effects,the common complex background caption,and the single background caption. We respectively implement four caption enhancement methods: OTSU with adaptive threshold method based on single frame,multiple frame averaging method,minimum pixel value search method and the method proposed in this paper, we use these four methods for each kind of caption for our caption enhancement experiment. We use Hanwang OCR to recognize the enhanced caption and take the recognition accuracy as the evaluation instance of the caption enhancement effect. Experimental results show that the recognition accuracy of the three kinds of caption are 81.76%,97.13%, and 81.76% respectively after enhanced by adopting the method in this paper. Comparing with the best results of the other three methods,the accuracy respectively increased by 24.35%,2.70% and 2.70%. Thus,the method in this paper can adapt to both complex background and single background caption. Especially,the enhanced effect of complex background caption containing shadows or stoke show a significant improvement. In this paper, we propose a method of fusing multi-frame information to realize caption enhancement based on the Logistic model. This method can reduce the complexity of the caption background and improve the contrast between the background and the text as well. Furthermore, the enhanced caption can be recognized well by OCR software. However,the parameters of the Logistic model are static values acquired by artificial parameter adjustment. If we can dynamically adjust parameters according to the characteristics of different video caption,the recognition accuracy will be further improved.关键词：complex background;caption enhancement;Logistic model;caption detection and tracking;time domain feature3664|391|0更新时间：2024-05-07
- 摘要：Given the interference from noise, it is difficult to segment noisy images by traditional image segmentation method. Therefore,we propose a new neutrosophic image segmentation method integrating LPG&PCA(principal component analysis with local pixel grouping). First,the input image is converted into neutrosophic images by using the neutrosophic set theory. Then,we filter the noise image by applying the proposed -LPG&PCA filtering operation,and advance the denoised image by employing the -enhancing operation,with the uncertainty information from the input image,to smooth the noisy points in the input image. Finally,we segment the denoised and enhanced image with a -means clustering method. The experimental results indicate that the proposed algorithm can eliminate noise effectively as well as improve the PSNR,therefore,our method can achieve desirable results in noise immunity and segmentation accuracy. The accuracy of our algorithm is improved,through the neutrosophic set theory and the uncertainty information from the input image. Theoretical analysis and experimental results show the effectiveness of the proposed algorithm.关键词：image segmentation;neutrosophy;principal component analysis(PCA);local pixel grouping(LPG)3048|381|0更新时间：2024-05-07
- 摘要：During the segmentation of color image, optical flow methods can acquire the moving regions, but it can hardly obtain the correct segmentation boundaries of moving objects. Meanwhile, familiar algorithms usually suffer from over-segmentation. To overcome the shortage of optical flow method and suppress the over-segmentation, while preserving the salient regions, a new motion coherence image segmentation algorithm fused with multi-feature is proposed. First, the initial regions are acquired by the Mean Shift algorithm; second, the regions with homogenization of visual sensing are merged by utilizing spatial information (including color, edge and region area); third, the motion coherence regions are merged by using temporal information; finally, the segmentation result is obtained. The experimental results demonstrate that by combining spatial-temporal information, the proposed method can suppress over-segmentation effectively. It therefore does not only make up for the shortage that correct object edges can hardly be acquired by using optical flow, while also increasing the completeness of the segmented objects. Compared with two popular color image segmentation algorithms, our method gets better results.关键词：color image segmentation;motion coherence;region similarity measurement;region merge4151|475|0更新时间：2024-05-07
- 摘要：Mural images have large intra-class variance and strong background noise. We present a clustered multiple instance learning strategy to classify murals of different periods and styles. We divide the sample space into several different sub-spaces,and a classification model is trained for each sub-space with training samples falling into this sub-space. In the testing stage,we choose a classification model for the testing sample according to the sub-space it falls into. In each classifier's training,we treat each mural image sample as a "bag" which contains a set of instances,and we use multiple instance learning to train the classifier. In the training process,we introduce hidden variables to identify each instance,the presence of hidden variables makes the classifier's optimization problem not convex which cannot be directly solved using a gradient descent. In this paper we use an iterative process to train Latent SVM(support vector machine) as the classifier for each sub-space. The experimental results indicate that our classification model can improve the classification accuracy of mural images by about 5% with comparison to the baseline method. The strategy proposed in this paper can greatly reduce the impact of the intra-class variance and background noise brings to the classification result of mural images.关键词：mural images;image classification;multiple instance learning;Latent SVM3850|283|0更新时间：2024-05-07
- 摘要：The main difficulties identifying hinge points are due to the inherent noise and the low resolution of echocardiography. In this paper,a local context feature combined with additive support vector machines(SVM) classifier is proposed to identify the hinge points of mitral annulus(MA). The position of the hinge point of MA is important for segmentation, modeling, and multi-modalities registration of mitral valve. The innovation is as follows: 1) Extracting the hinge point of MA by local context feature.2) Applying the SVM classifier to identify the candidates of MA.3) Compute the weighted density field of candidates which represents the blocks of candidates.4) Applying the binary search algorithm on the weighted density field to maintain an adaptive threshold. This threshold is used to exclude the error from the SVM classifier. This algorithm is tested on echocardiographic four chamber image sequence of 10 pediatric patients. Compared with the manually selected hinge point of MA,the mean error is in 1.52±2.25 pixels. Add-itive SVM classifier can fast and accurately identify the MA hinge point.关键词：mitral annulus;local context;K-means;SVM classifier;additive SVM kernel3431|324|0更新时间：2024-05-07
- 摘要：Image matching is an important technique in image processing and recognition. In order to enhance the matching effectiveness and to obtain accurate matches,an iterative graph transformation matching algorithm is proposed in this paper to remove the error matches, which usually exist in the initial matches obtained by image features such as scale invariant feature transform (SIFT) and speeded up robust features (SURF). Generally,the proposed algorithm carries out the following three steps: first, the algorithm generates the accurate correspondences from the initial one-to-one correspondence set by using the traditional graph transformation matching algorithm,whose process is similar to that in graph transformation matching (GTM) algorithm; then,it further revises the initial correspondences by using the geometric relationship between the obtained correct matches and the initial matches; finally,based on the revised initial matches,the algorithm further searches the correct matches from the revised initializations by using graph transformation matching algorithm. Compared with GTM,the proposed algorithm further explores the geometric relationship in the matching process and thus returns more accurate matches. Experimental results on real-world image matching shows that under various image transformation scenes,the proposed algorithm can significantly outperform GTM on the matching recall while retain the similar high matching precision. The proposed iterative graph transformation matching algorithm can overcome the main drawback of GTM that usually returns small number of precise matches.关键词：graph transformation matching;image matching;K-nearest neighbor (KNN) graph;geometric constraint3688|383|0更新时间：2024-05-07
- 摘要：A robust tracking approach based on residual unscented particle filter (RUPF) and discriminative sparse representation is proposed to track an object accurately and efficiently. The Unscented Kalman filter is used to bring the target's observation into its proposal distribution. Then the Markov chain Monte Carlo (MCMC) improves the sampling result. The accuracy of filtering is enhanced and problems such as particle degeneration and dilution can be restrained with our RUPF. Observation likelihood is modeled based on the discriminative sparse representation, which improves the ability to extract the target from the background. The L1-regularized least squares problem in sparse representation is solved using the alternating direction method of multipliers (ADMM). Both quantitative and qualitative experiments are conducted on several challenging image sequences and the comparisons with other state-of-the-art trackers demonstrate that our tracker is more accurate than some common trackers and owns less computational complexity than traditional sparse-based trackers. With the development of the hardware, a quickly operated UKF guarantees a faster speed of our tracker with a high tracking accuracy.关键词：object tracking;Unscented particle filter;sparse representation;dynamic template update;alternating direction method of multipliers(ADMM)3485|400|0更新时间：2024-05-07
- 摘要：Solving the problem of a lack of matching points to complete the terrain reconstruction for the landing area during the Lunar Lander landing process. An SFS(shape from shading) algorithm for 3D terrain recovery based on gradient constraints of the feature edges. The irradiance equation is established on the Lommel-Seeliger model to simulate the Lunar surface reflection. Based on the extract results of the terrain feature edge, gradient ratio of the rest part can be solved after least square fitting and surface smoothness constraint. The SFS problem becomes regularized after the quantitative constraints of irradiance equation. The average relative recovery accuracy can reach -0.199 for synthetic images, and also can reach 0.051 and 0.022 for real image after testing. The proposed algorithm can work effectively for 3D terrain reconstruction, and the recovery accuracy is superior to the existing SFS algorithm.关键词：terrain reconstraction;lunar terrain;shape from shading;reflection model;irradiance equation;gradient constraint3570|319|0更新时间：2024-05-07
- 摘要：Depth from defocus is a common method for recovering scene depth information. In traditional methods we usually need to collect multiple defocused images. However, this is difficult in practical application. In this paper, we address a challenging problem of recovering the depth from a single photograph taken with an uncalibrated conventional camera. In order to achieve this, we present a simple yet effective two-step approach to estimate the blur map of the input image. 1)A sparse blur map is obtained by estimating the amount of defocus blur at the edge locations. 2)Based on image segmentation and the sparse blur map to get the global blur map, complete depth information can be restorated. In order to obtain accurate scene depth information, we join geometry constraints, the sky area extraction and segmentation strategy to eliminate the impact of color, texture and focal plane ambiguity. Experimental results on a variety of images show that our method can acquire a reliable estimation of the depth of a scene.关键词：blur estimation;defocus;image segment;depth information5151|670|0更新时间：2024-05-07
- 摘要：With the emergence of massive shared images in the Web2.0 era, it has become a significant research topic to get precise descriptive region-level annotations for images. In this paper, we propose a new image annotation algorithm based on region-semantic diverse density, focusing on the differences of visual feature and spatial structure among regions. In details, the algorithm uses diverse density method based on feature distance similarity and region spatial location, and introducing color, shape together with texture property annotations. Experiments on parts of the NUS-WIDE and MSRC datasets demonstrate that the proposed method is effective. The accuracy is more than 80% in property annotations. Furthermore, the average precision of image retrieval using property annotations is up to 82%. The experiments results show that the proposed image annotation framework can get relevant semantic regions and property annotations more accurately, and effectively solves the problem of regional annotation.关键词：diverse density;region-semantic;distance similarity;spatial location;property annotation3725|313|0更新时间：2024-05-07
- 摘要：A robust real-time mesh editing approach is proposed, which allows us to select precise regions for parameterization, and realize seamless cloning of the 3D surface geometry. First we select the region of interest(ROI) using a paintbrush interface, and ascertain the region for parameterization by traversing the mesh using half edge structures combined with a seed fill algorithm. The distance limitation is attached from the center of paintbrush to the vertexes of the ROI. Then, the mean value coordinates without cage are used for shape deformation. Finally, the source mesh patch is cloned seamlessly onto a target mesh. Experimental results demonstrate that the proposed method outperforms previous related mesh editing techniques on protuberant meshes with high curvature Furthermore, the method can be processed in real-time and it is rather robust. Mesh editing approach using mean value coordinates combined with Poisson equation is robust and real-time capable, which allows us to select precise region for parameterization and realize seamless cloning of 3D surface geometry. It performs more robust compared with the existing mesh cloning methods.关键词：mesh editing;local parameterization;Poisson cloning;mean value coordinates3410|524|0更新时间：2024-05-07
- 摘要：In this paper a modified self-organized algorithm for the generation of tetrahedral meshes is introduced for the optimization of meshes in the FEA. First, a geometric method is applied to reconstruct a classified volume data of specified size from the triangular surface model in this method and a balanced octree based on the given surface model is built to compute a 3D array, which used to control the mesh size. Then, the volume data is converted into a boundary indicator array in which different iso-surfaces are conformed in the neighborhood. Tetrahedral meshes can be generated finally by combining our improved self-organized algorithm with the interpolation function of the related 3D data. The experimental result shows that this method can be used to generate high quality tetrahedral meshes at higher proportions and enhance the ability to reduce the number of slivers. It also ensures the conformation of the boundary additionally. The algorithm in this paper can provide an effective and robust method when building finite element models for watertight 3D surface meshes.关键词：tetrahedral meshes;Delaunay triangulation;size control array;smoothing filter3285|397|0更新时间：2024-05-07
- 摘要：Fluid animation has recently become more popular and it is widely used in industrial fields, like movies, animation, and games. Because of the complexity of its movement, various methods have been presented to produce visibly pleasing effects. The commonly used simulation methods are velocity based methods. However, they suffer from fast loss of fluid details. In order to maintain details in the simulation process, vorticity based methods produce many impressive effects. However, they suffer from serious problems when considering boundaries and the problem of stability. Our goal is to produce methods to get rid of these drawbacks. We use vortexes to represent the vorticity of the domain. Similarly to other vortex methods, we also do convection, stretching and adding body force. However, we use a new grid to compute the velocity. With this new grid structure, we stagger the different components of vorticity on the center of edges of each voxel. This grid structure is highly compatible with the commonly used grid structure, which staggers the different components of velocity on center of faces of each voxel. Using this grid structure, we can easily cope with different boundaries including solid boundaries and free surfaces, and we can easily enforce incompressibility in one voxel. We present several scenes of smoke animation to represent the capability of our method to cope with different boundaries. Moreover, we also present a chart about the energy changing process in these scenes with fixed vortexes with an initial vorticity vector. Furthermore, we neglect the body force in this experiment. The chart shows that our method is very stable and the amplitude of the energy wave is less than 0.005%. We present a new vortex method with a new grid structure. Byusing this new grid structure, our method can process with different boundaries, including solid boundaries and free surface. Moreover, the results show that our method can preserve fluid details in the simulation process and it is very stable.关键词：fluid simulation;vortex;vorticity based simulation methods;boundaries2948|299|0更新时间：2024-05-07
- 摘要：A method of PolSAR imagery segmentation based on region statistical characteristic is proposed in this paper to deal with the shortage of recent reasearch in speckle noise and segmentation efficiency. First, watershed using gradient to segment imagery is used to get the initial segmentation. The ROA gradient is introduced because to the differential gradient is not showing a constant false alarm rate which probably provides false edges. Meanwhile, a method of gradient construction based on morphological operations is given to eliminate the local minimum of the gradient, which would induce massive over-segmentation after the watershed transformation and suppresses over-segmentation. After that the maximum likelihood estimation of the region coherence matrix is estimated by the arithmetical mean of pixels in region. Then, an object function effectively weigh dissimilarity between regions is deduced in combination with the Wishart distribution of the coherence matrix and a hypothesis test, Additionally, the RAG is build based on an object function and the final segmentation is retrieved after merging the hierarchical regions. Simulated data, L-band airborne SAR data of oberpfaffenhofen test site, provided by the DLR and X-band PolSAR data acquired in Hainan Lingshui County, are used to validate the method of this paper. The initial segmentation proved that gradient reconstruction would not undermine the original gradient construction and can effectively suppress over-segmentation. The qualitative and quantitative analysis of the final segmentation show that object function can provide a good segmentation result and has a high segmentation efficiency, information maintenance and segmentation precision. These results validate that the proposed method can effectively reduce the speckle noise and improve efficiency, thereby it can provides a more accurate segmentation.关键词：segmenation of PolSAR imagery;region stastical characristic;watershed;ROA gradient3245|406|0更新时间：2024-05-07
- 摘要：The acquisition process of remote sensing images is influenced by many factors, such as the internal turbulences of the sensor and the external environmental variations, which causes degradations in the observed image. The uneven intensity distribution is a typical degradation caused by internal and external factors, directly related to the decrease of the accuracy of the interpretation and applications of remote sensing images. Therefore, the correction of uneven intensity is necessary for improving the quality of remote sensing images. The perceptually inspired variational method(PIVM) for the uneven intensity correction is a novel method to correct the uneven intensity of a single remote sensing image. PIVM can effectively correct the overall brightness of the image while enhancing the local contrast, which is inspired by the human visual system properties. In this paper, the split Bregman algorithm is used to optimize this variational model. The model is composed of two kinds of priors: the total variation (TV) and the L. The combination model can be split into two sub problems, which can increase the computational efficiency while ensuring the even intensity. Experiments on synthetic and real remote sensing images are taken to validate the split Bregman based PIVM. Results show that the uneven intensity can be effectively corrected by the proposed split Bregman method, and meanwhile the global color and local contrast are satisfied. Moreover, the running time of the split Bregman algorithm is one seventh to one sixth of that of the traditional steepest decent method. The split Bregman based PIVM is an efficient and effective method for correcting uneven intensity in remote sensing images. It provides the opportunity to extend the PIVM to the application on large scenes.关键词：remote sensing image;uneven intensity correction;perceptually inspired;variational;split Bregman3405|432|0更新时间：2024-05-07
- 摘要：This paper presents a novel method based on Wallis dodging and distance weight enhancement to improve the effectiveness and efficiency of unmanned aerial vehicle UAV image seam elimination, which includes brightness and texture seam elimination. In order to eliminate brightness seam, we designed a Wallis parameters setting method. Then, we propose a distance weight algorithm based on spatial correlation to eliminate the texture seam. To evaluate the method, we choose seven different types and eight lines UAV images as our experimental data. The algorithm will share local geometric dislocation with the whole overlap. Comparisons with four existing classical methods show the proposed method performs well in seam elimination, and it is suitable for UAV image rapid processing.关键词：unmanned aerial vehicle image;wallis dogoding;spatial correlation;seam elimination2824|501|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