Search

Surveying wide areas with only one camera is a typical scenario in surveillance and automotive applications. Ultra wide-angle fisheye cameras employed to that end produce video data with characteristics that differ significantly from conventional rectilinear imagery as obtained by perspective pinhole cameras. Those characteristics are not considered in typical image and video processing algorithms such as motion estimation, where translation is assumed to be the predominant kind of motion. This contribution introduces an adapted technique for use in block-based motion estimation that takes into the account the projection function of fisheye cameras and thus compensates for the non-perspective properties of fisheye videos. By including suitable projections, the translational motion model that would otherwise only hold for perspective material is exploited, leading to improved motion estimation results without altering the source material. In addition, we discuss extensions that allow for a better prediction of the peripheral image areas, where motion estimation falters due to spatial constraints, and further include calibration information to account for lens properties deviating from the theoretical function. Simulations and experiments are conducted on synthetic as well as real-world fisheye video sequences that are part of a data set created in the context of this paper. Average synthetic and real-world gains of 1.45 and 1.51 dB in luminance PSNR are achieved compared against conventional block matching. Furthermore, the proposed fisheye motion estimation method is successfully applied to motion compensated temporal resolution enhancement, where average gains amount to 0.79 and 0.76 dB. [ABSTRACT FROM AUTHOR]

Due to the limitation of objective conditions，imaging devices can only image at a lower resolution，and cannot distinguish the motion direction. We propose a fast object direction recognition method based on the SIFT. Firstly，according to the block matching algorithm，we use the corner feature extraction method to determine the position of the block，which is named as a detection block. The next frame image is traversed with the determined block，the matching block is found and named as the target block，and the motion direction between the check block and the target block is determined. Finally ？ the SIFT algorithm is used to match the feature points of two pictures. Each picture selects three corresponding feature points to construct a triangle，and the transformation relationship o£ two corresponding triangles constructs a mathematical model to identify the motion direction. Experimental results show that the motion direction recognition speed of our proposal is increased by 3. 3 times compared with the block matching? and the matching accuracy is increased by 2. 9 times，achieving higher judgment speed and accuracy. By comparison，the SIFT search algorithm has stronger feasibility and can determine the moving direction of objects faster in multi-frame images. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel image denoising method based on adaptive thresholding and k-means clustering. In this method, we adopt the adaptive thresholding technique as an alternative to the traditional hard-thresholding of the block-matching and 3D filtering (BM3D) method. This technique has a high capacity to adapt and change according to the amount of the noise. More precisely, in our method the soft-thresholding is applied to the areas with heavy noise, on the contrary the hard-thresholding is applied to the areas with slight noise. Based on the adaptation and stability of the adaptive thresholding, we can achieve optimal noise reduction and maintain the high spatial frequency detail (e.g. sharp edges). Owing to the capacity of k-means clustering in terms of finding the relevant candidate-blocks, we adopt this clustering at the last estimate to partition the denoised image into several regions and identify the boundaries between these regions. Applying k-means clustering will allow us to force the block matching to search within the region of the reference block, which in turn will lead to minimize the risk of finding poor matching. The main reason of applying the K-means clustering method on the denoised image and not on the noised image is specifically due to the flaw of accuracy in detecting edges in the noisy image. Experimental results demonstrate that the new algorithm consistently outperforms other reference methods in terms of visual quality, Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Furthermore, in the proposed algorithm the time consumption of the image denoising is less than that in the other reference algorithms. [ABSTRACT FROM AUTHOR]

Automated condition monitoring of pavements is seeing a paradigm shift in the twenty-first century, as the focus is increasingly shifting from visual to 3D imaging. The 3D measurement represents the ground truth, within the bounds of discretization of the imager. Hence, working with the 3D data and interpreting it is a lot easier. The 3D laser scanners are the current norm for range imaging. Laser scanners, although technically versatile and extremely accurate, are very expensive. Therefore, the need for alternative 3D imaging technologies is imperative, especially in the developing world context. The coming decade will see alternative technologies first target large pavement distresses, like potholes, before moving onto smaller defect types. In this regard, this is the first study that treats the stereo imaging of roads from a moving vehicle, for any distresses, and especially for pothole measurements. A fast stereo matching procedure is proposed. A preliminary keypoint matching estimates the global disparity between the stereo pair. The estimated disparity is used toward further keypoint and block matching procedure, by concentrating on smaller image regions. Images obtained from a moving vehicle are preprocessed to reduce the effects of image blur. Furthermore, algorithms to determine key critical metrological parameters, such as the area, depth, and volume, of a pothole are also developed. A benchmarking of the proposed system shows that the 3D measurements are within 3 mm for static situations and 5 mm when imaged from a moving vehicle. At 10-km/h vehicle speed, potholes are imaged to accuracies of −20% for volume, −15% for area, and −4% for depth, when compared to static imagery. [ABSTRACT FROM AUTHOR]

Purpose: To propose a novel method to improve the mega-voltage CT (MVCT) image quality for helical TomoTherapy while maintaining the stability on dose calculation. Materials and Methods: The Block-Matching 3D-transform (BM3D) and Discriminative Feature Representation (DFR) methods were combined into a novel BM3D + DFR method for their respective advantages. A phantom (Catphan504) and three serials of clinical (head & neck, chest, and pelvis) MVCT images from 30 patients were acquired using the helical TomoTherapy system. The contrast-to-noise ratio (CNR) and edge detection algorithm (canny) was employed for image quality comparisons between the original and BM3D + DFR enhanced MVCT. A simulated rectangular field of 6 MV X-ray beams were vertically delivered on the original and post-processed MVCT serials of the same CT density phantom, and the dose curves on both serials were compared to test the effects of image enhancement on dose calculation accuracy. Results: In total, 466 transversal MVCT slices were acquired and processed by both BM3D and the proposed BM3D + DFR methods. Compared to the original MVCT image, the BM3D + DFR method presented a remarkable improvement in terms of the soft tissue contrast and noise reduction. For the phantom image, the CNR of the region of interest (ROI) was improved from 1.70 to 4.03. The average CNR of ROIs for 10 patients from each anatomical group, were increased significantly from 1.45 ± 1.51 to 2.09 ± 1.68 for the head & neck (p < 0.001), from 0.92 ± 0.78 to 1.36 ± 0.85 for the chest (p < 0.001), and from 1.12 ± 1.22 to 1.76 ± 1.31 for the pelvis (p < 0.001), respectively. The canny edge detection operator showed that BM3D + DFR provided clearer organ boundaries with less chaos. The root-mean-square of the dosimetry difference on the iso-center passed horizontal dose profile curves and vertical percentage depth dose curves were only 0.09% and 0.06%, respectively. Conclusions: The proposed BM3D + DFR method is feasible to improve the soft tissue contrast for the original MVCT images with coincidence in dose calculation and without compromising resolution. After integration in clinical workflow, the post-processed MVCT may be better applied on image-guided and adaptive helical TomoTherapy. [ABSTRACT FROM AUTHOR]

Coherent imaging systems are greatly affected by speckle noise, which makes visual analysis and features extraction a difficult task. In this paper, we propose a speckle suppression algorithm based on weighted nuclear norm minimization (WNNM) and Grey theory. First, we use logarithmic transformation to the noisy images such that the speckle noise is transformed into additive noise. Second, by matching the local blocks based on Grey theory, we will get approximate low-rank matrices grouped by the similar blocks of the reference patches. We then estimate the noise variance of the noisy images with the wavelet transform. Finally, we use WNNM method to denoise the image. The results show that our algorithm not only effectively improves the visual effect of the denoised image and preserves the local structure of the image better but also improves the objective indexes values of the denoised image. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We propose a denoising method by integrating group sparsity and TV regularization based on self-similarity of the image blocks. By using the block matching technique, we introduce some local SVD operators to get a good sparsity representation for the groups of the image blocks. The sparsity regularization and TV are unified in a variational problem and each of the subproblems can be efficiently optimized by splitting schemes. The proposed algorithm mainly contains the following four steps: block matching, basis vectors updating, sparsity regularization and TV smoothing. The self-similarity information of the image is assembled by the block matching step. By concatenating all columns of the similar image block together, we get redundancy matrices whose column vectors are highly correlated and should have sparse coefficients after a proper transformation. In contrast with many transformation based denoising methods such as BM3D with fixed basis vectors, we update local basis vectors derived from the SVD to enforce the sparsity representation. This step is equivalent to a dictionary learning procedure. With the sparsity regularization step, one can remove the noise efficiently and keep the texture well. The TV regularization step can help us to reduced the artifacts caused by the image block stacking. Besides, we mathematically show the convergence of the algorithms when the proposed model is convex (with p=1) and the bases are fixed. This implies the iteration adopted in BM3D is converged, which was not mathematically shown in the BM3D method. Numerical experiments show that the proposed method is very competitive and outperforms state-of-the-art denoising methods such as BM3D. [ABSTRACT FROM AUTHOR]

Highlights • A computationally efficient block matching method is presented. • Novel updating strategies are proposed for PSO algorithm. • Significant improvements were demonstrated with a nano motion systems. Abstract This paper is devoted to the micro vision based displacement measurement for a nano-positioning stage with the aid of a single camera. For this purpose, a pinhole imaging model as well as corresponding Jacobin matrix is established, with which an efficient block matching (BM) algorithm is developed based on the particle swarm optimization (PSO) algorithm. In particular, an improved PSO algorithm is developed by proposing a new fitness updating strategy (FUS) such that the particles' migration can be performed with an efficient way in the whole optimization process. The improved PSO can significantly speed up the optimization process, but meanwhile resulting in a coarse-level estimation result. The full search algorithm (FSA) is thus performed on the coarse-level result in order to achieve the final fine-level result. The effectiveness of the presented method was demonstrated using the testing data acquired from an experimental platform, where comparative studies with those existing benchmark methods were also provided. The comparison results show that the method achieves a significant improvement on computational efficiency without loss of accuracy, which implies it has a better balance/trade-off between the measurement accuracy and computation efficiency in real applications. [ABSTRACT FROM AUTHOR]

Copy-move forgery is a common type of image forgery. Block matching detection often has the problems of low accuracy and high time complexity. In order to improve the accuracy and significantly, and reduce the time complexity, this paper used deep learning characteristics and clustering algorithm for detecting. Firstly, it used the sparse autoencoder to find out the internal laws of the images and trained the weight matrix of the hidden layer which obtained by a large number of sample sets. It obtained the hidden layer feature of the detection image by the weight matrix, that was, the sparse autoencoder feature. Secondly, it used the K-means algorithm to cluster the autoencoder features at the first time to remove the image smoothing region and to cluster the texture features to obtain the detection results. It used the Euclidean distance judgment and RANSAC algorithm to remove the abnormal blocks, in order to achieve tampering area detection. Experimental results show that the proposed algorithm can improve the accuracy by about 14. 3% compared with other algorithms, and the time efficiency is improved by 72%. The combination of the depth learning feature and the clustering algorithm makes the tampering of the copy-move forgery improved in both time efficiency and accuracy. [ABSTRACT FROM AUTHOR]

To achieve a high level of seismic random noise suppression, the conventional time-frequency peak filtering (TFPF) has been adequately studied and applied in previous researches in recent years. A window is used to improve linearity, thereby achieving the unbiased estimates. However, applying a fixed window length to all frequencies signals will result in serious loss of effective components. The recently proposed the parabolic-trace TFPF (PT-TFPF) resample seismic record along parabolic-trace to enhance linearity. But complex events in field data have different curvatures, and it is difficult to fit parabolic-trace. To resolve these problems, we present an adaptive linear TFPF (AL-TFPF) in this paper. In this novel method, the linearity of the effective signals is implemented by grouping instead of window or filtering trace. Based on temporal continuity and spatial correlation, grouping is able to adaptively resample. The AL-TFPF stores the similar blocks into a new matrix. In this approach, degree of improvement of linearity is related to the accuracy of block matching. Finally, we evaluate the performance of our method on both synthetic records and field data. The experimental results illustrate that our proposed method realizes the retention of useful components and attenuation of the noise simultaneously, compared with the conventional TFPF and the PT-TFPF. [ABSTRACT FROM AUTHOR]

Subject of Research.The paper deals with the motion estimation algorithms for the analysis of video sequences in compression standards MPEG-4 Visual and H.264. Anew algorithm has been offered based on the analysis of the advantages and disadvantages of existing algorithms. Method. Thealgorithm is called hierarchical adaptive rood pattern search (Hierarchical ARPS, HARPS). This new algorithm includes the classic adaptive rood pattern search ARPS and hierarchical search MP (Hierarchical search or Mean pyramid). All motion estimation algorithms have been implemented using MATLAB package and tested with several video sequences. Main Results. The criteria for evaluating the algorithms were: speed, peak signal to noise ratio, mean square error and mean absolute deviation. The proposed method showed a much better performance at a comparable error and deviation. The peak signal to noise ratio in different video sequences shows better and worse results than characteristics of known algorithms so it requires further investigation. Practical Relevance. Application of this algorithm in MPEG-4 and H.264 codecs instead of the standard can significantly reduce compression time. This feature enables to recommend it in telecommunication systems for multimedia data storing, transmission and processing.

Owing to the limitations of practical realizations, block-based motion is widely used as an alternative for pixel-based motion in video applications such as global motion estimation and frame rate up-conversion. We hereby present BlockNet, a compact but effective deep neural architecture for block-based motion estimation. First, BlockNet extracts rich features for a pair of input images. Then, it estimates coarse-to-fine block motion using a pyramidal structure. In each level, block-based motion is estimated using the proposed representative matching with a simple average operator. The experimental results show that BlockNet achieved a similar average end-point error with and without representative matching, whereas the proposed matching incurred 18% lower computational cost than full matching.

Image dense matching has become one of the widely used means for DSM generation due to its good performance in both accuracy and efficiency. However, for water areas, the most common ground object, accurate disparity estimation is always a challenge to excellent image dense matching methods, as represented by semi-global matching (SGM), due to the poor texture. For this reason, a great deal of manual editing is always inevitable before practical applications. The main reason for this is the lack of uniqueness of matching primitives, with fixed size and shape, used by those methods. In this paper, we propose a novel DSM generation method, namely semi-global and block matching (SGBM), to achieve accurate disparity and height estimation in water areas by adaptive block matching instead of pixel matching. First, the water blocks are extracted by seed point growth, and an adaptive block matching strategy considering geometrical deformations, called end-block matching (EBM), is adopted to achieve accurate disparity estimation. Then, the disparity of all other pixels beyond these water blocks is obtained by SGM. Last, the median value of height of all pixels within the same block is selected as the final height for this block after forward intersection. Experiments are conducted on ZiYuan-3 (ZY-3) stereo images, and the results show that DSM generated by our method in water areas has high accuracy and visual quality.

Copyright of Acta Automatica Sinica is the property of Chinese Academy of Sciences, Institute of Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

There is a recurrent idea being promoted in the recent literature on iterative solvers for imaging problems, the idea being the use of an actual denoising step in each iteration. We give a brief review of some algorithms from the literature which utilize this idea, and we broadly label these algorithms as Iterative Denoising Regularization (IDR) algorithms. We extend the Denoising Approximate Message Passing (D-AMP) algorithm from this list to the magnetic resonance imaging (MRI) reconstruction problem. We utilize Block Matching 3D (BM3D) as the denoiser of choice for the introduced MRI reconstruction algorithm. The application of the denoiser for complex-valued data necessitates a special handling of the denoiser. The use of the adaptive and image-dependent BM3D image model prior together with D-AMP results in highly competitive MRI reconstruction performance. [ABSTRACT FROM AUTHOR]

This work presents a video compression method based on sparse representation and dictionary learning algorithms. The proposed scheme achieves superb rate-distortion performance and decent subjective quality, compared to modern standards, especially at low bit-rates. Different from similar works, sparse representation is employed here for both intra-frame and block matching inter-frame motion information. Dividing video frames to reference and current frames, motion vectors and motion compensation residuals of current frames are estimated in regard to reference frames. The sparse codes of reference frames and motion compensation residuals are obtained using learned dictionaries, entropy-coded, and stored or sent to the receiver along with the coded motion field. In the receiver, after decoding the sparse codes and motion vectors, the reference frames and residuals are reconstructed employing the same learned dictionary and the current frames are recovered using the reference frames and motion fields. In the proposed scheme, the Iterative Least Square Dictionary Learning Algorithm (ILS-DLA) and K-SVD dictionary building methods are employed in the DCT domain. The compression rate and quality of the method based on the two dictionary learning algorithms are compared to each other and to H.264/AVC and HEVC modern standards. The results based on PSNR and SSIM criteria show that the proposed approach presents superior performance respect to H.264/AVC and even HEVC for higher bit-rates of QCIF video format, and the K-SVD learning algorithm performs slightly better than the ILS-DLA for the purpose. [ABSTRACT FROM AUTHOR]

A number of block-based image-denoising methods have been presented in the literature. Those methods, however, are generally adapted to denoising the Gaussian noise, and subsequently do not show good performance for denoising random-valued impulse, and salt-and-pepper noise. We propose an efficient block-based image-denoising method, which is devised specially for fast denoising of impulse noise. The method first constructs a set of array pointers to image blocks containing a specific pixel value at a specific location. With this scheme, finding of blocks similar to a given block can be done by considering only the blocks pointed by the pointers corresponding to the pixel values of the block without comparing all the blocks in the input image. The experimental results show that the proposed method can achieve superior denoising performance in terms of computational time and signal-to-noise ratio measure. [ABSTRACT FROM AUTHOR]

In this paper a colourizing technique based on some tensor properties is proposed. Toward this goal, it is clarified that tensor decomposition possesses the ability of extracting and gathering overall colour information. The methodology considers a grayscale pixel as a balanced vector in RGB colour space. Any deviation to unbalance the colour coordinates means adding colour information to the initial pixel. For finding the appropriate direction of deviation, the proposed technique uses tensor decomposition to extract colour information from a block divided exemplar colour image called reference. Then apply this direction to the best matched block of the grayscale image based on a similarity criterion while its basic structure is preserved. Finally by retrieving from tensor space into spatial domain the conversion is fulfilled. The similarity criteria for block matching and the plausibility of the system output are the most challenging problems. Both images blocks are considered as 3D tensors and Tucker3 with its unique properties is utilized for transferring the colour information. The novelty, simplicity, accuracy, and the conversion speed are some parameters which are introduced and developed by the proposed algorithm. This approach proves that in comparison with spatial or frequency domain, transforming the colour information into tensor space make it more clear and give us better ability of rendering. The results show that the proposed algorithm is able to present the average structural similarity up to 94%. [ABSTRACT FROM AUTHOR]

Block matching based 3D filtering methods have achieved great success in image denoising tasks. However, the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network (CNN) for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model (BMCNN) could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio (PSNR) when denoising images with high noise levels (σ > 40), and the best visual quality when denoising images with all the tested noise levels. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper proposes two new non-reference image quality metrics that can be adopted by the state-of-the-art image/video denoising algorithms for auto-denoising. The first metric is proposed based on the assumption that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus tackles the homogeneous regions and highly-structured regions separately. Nevertheless, this metric is only stable when the noise level is relatively low. Most denoising algorithms reduce noise by (weighted) averaging repeated noisy measurements. As a result, another metric is proposed for high-level noise based on the fact that more noisy measurements will be required when the noise level increases. The number of measurements before converging is thus related to the quality of noisy images. Our patch-matching based metric proposes to iteratively find and add noisy image measurements for averaging until there is no visible difference between two successively averaged images. Both metrics are evaluated on LIVE2 (Sheikh et al. in LIVE image quality assessment database release 2: 2013) and TID2013 (Ponomarenko et al. in Color image database tid2013: Peculiarities and preliminary results: 2005) data sets using standard Spearman and Kendall rank-order correlation coefficients (ROCC), showing that they subjectively outperforms current state-of-the-art no-reference metrics. Quantitative evaluation w.r.t. different level of synthetic noisy images also demonstrates consistently higher performance over state-of-the-art non-reference metrics when used for image denoising. [ABSTRACT FROM AUTHOR]

Block Matching is one of the most efficient techniques for motion estimation for video sequences. Metaheuristic algorithms have been used effectively for motion estimation. In this paper, we propose two hybrid algorithms: Artificial Bee Colony with Differential Evolution and Harmony Search with Differential Evolution based motion estimation algorithms. Extensive experiments are conducted using four standard video sequences. The video sequences utilized for experimentation have all essential features such as different formats, resolutions and number of frames which are generally required in input video sequences. We compare the performance of the proposed algorithms with other algorithms considering various parameters such as Structural Similarity, Peak Signal to Noise Ratio, Average Number of Search Points etc. The comparative results demonstrate that the proposed algorithms outperformed other algorithms. [ABSTRACT FROM AUTHOR]

Block matching (BM) motion estimation plays an inevitable role in video coding applications. BM approaches are used for data compression. The compression is achieved by removing the temporal redundancy in the video sequences. In the BM process, each video frame is subdivided into macroblocks. Each macroblock in the current frame is compared with the previous frame. The main objective is to minimize sum absolute difference. In this work, some modifications have been performed on conventional artificial bee colony algorithm to improve the conventional BM systems. An initial pattern is used in the proposed algorithm to reduce the computational cost. The computational cost is represented in terms of search points and convergence time. Experimental results results show the improvement for the proposed approach over other block matching algorithms in terms of the performance measures. [ABSTRACT FROM AUTHOR]

This paper addresses the disparity map estimation problem in the context of stereoscopic image coding. It is undeniable that the use of variable size blocks offers the possibility to describe more precisely the predicted view but at the expense of a high bitrate if no particular consideration is taken into account by the estimation algorithm. Indeed more information related to the block layout, considered here as a block-length map, is required at the prediction step. This paper presents an algorithm which jointly optimizes the block-length map as well as the disparity map so as to ensure a good reconstruction of the predicted view while minimizing the bitrate. This is done thanks to a joint metric taking into account the quality of the reconstruction as well as the bitrate needed to encode the maps. Moreover the developed algorithm iteratively improves its performance by refining the estimated maps. Simulation results conducted on several stereoscopic images from the CMU-VASC and the Middlebury dataset confirm the benefits of this approach as compared to competitive block matching algorithms. [ABSTRACT FROM AUTHOR]

In this paper the concept of sparsity for complex-valued variables is introduced in the following three types: directly in complex domain and for two real-valued pairs phase/amplitude and real/imaginary parts of complex variables. The nonlocal block-matching technique is used for sparsity implementation and filter design for each type of sparsity. These filters are complex domain generalizations of the Block Matching 3D collaborative (BM3D) filter based on the high-order singular value decomposition (HOSVD) in order to generate group-wise adaptive analysis/synthesis transforms. Complex domain denoising is developed and studied as a test-problem for comparison of the designed filters as well as the different types of sparsity modeling. [ABSTRACT FROM AUTHOR]

Tracking is essentially a matching problem. This paper proposes a tracking scheme for video objects on compressed domain. This method mainly focuses on locating the object region and evolving the detection of movement, which improves tracking precision. Motion Vectors (MVs) are used for block matching. At each frame, the decision of whether a particular block belongs to the object being tracked is made with the help of histogram matching. During the process of matching and evolving the direction of movement, similarities of target region are compared to ensure that there is no overlapping and tracking performed in a right way. Experiments using the proposed tracker on videos demonstrate that the method can reliably locate the object of interest effectively.

Classification is a common objective when analyzing hyperspectral images, where each pixel is assigned to a predefined label. Deep learning-based algorithms have been introduced in the remote-sensing community successfully in the past decade and have achieved significant performance improvements compared with conventional models. However, research on the extraction of sequential features utilizing a single image, instead of multi-temporal images still needs to be further investigated. In this paper, a novel strategy for constructing sequential features from a single image in long short-term memory (LSTM) is proposed. Two pixel-wise-based similarity measurements, including pixel-matching (PM) and block-matching (BM), are employed for the selection of sequence candidates from the whole image. Then, the sequential structure of a given pixel can be constructed as the input of LSTM by utilizing the first several matching pixels with high similarities. The resulting PM-based LSTM and BM-based LSTM are appealing, as all pixels in the whole image are taken into consideration when calculating the similarity. In addition, BM-based LSTM also utilizes local spectral-spatial information that has already shown its effectiveness in hyperspectral image classification. Two common distance measures, Euclidean distance and spectral angle mapping, are also investigated in this paper. Experiments with two benchmark hyperspectral images demonstrate that the proposed methods achieve marked improvements in classification performance relative to the other state-of-the-art methods considered. For instance, the highest overall accuracy achieved on the Pavia University image is 96.20% (using both BM-based LSTM and spectral angle mapping), which is an improvement compared with 84.45% overall accuracy generated by 1D convolutional neural networks.

Mosaic refers to a technique that forms images by gathering several small materials in various colors. Because of the recent developments in digital imaging technology, photomosaic technologies that form images using photos are utilized. In this paper, we present an automatic computer algorithm that forms photomosaic images through adaptive tiling and block matching. A photo database stores photos called tiles for mosaic and their feature values. A photomosaic image is generated through separating the input image into blocks of a pre-set size, performing adaptive tiling by comparing the similarity between adjacent blocks, conducting block matching to find a similar tile in the photo database, and adjusting the intensity to enhance tile similarity within each image block. Furthermore, the quality of the photomosaic image is improved by minimizing tile redundancy in adjacent blocks and limiting the number of tiles used. In our experiment, the performance of the proposed algorithm is compared with that of Andrea mosaic, Mosaically, and Mozaika software packages. The results indicate that the proposed algorithm is excellent in quantitative and qualitative analyses. [ABSTRACT FROM AUTHOR]

Purpose The implementation of motion management techniques in radiation therapy can aid in mitigating uncertainties and reducing margins. For motion management to be effective, it is necessary to track key structures both accurately and at a real-time speed. Therefore, the focus of this work was to develop a 2D algorithm for the real-time tracking of ultrasound features to aid in radiation therapy motion management. Materials and Methods The developed algorithm utilized a similarity measure-based block matching algorithm incorporating training methods and multiple simultaneous templates. The algorithm is broken down into three primary components, all of which use normalized cross-correlation (NCC) as a similarity metric. First, a global feature shift to account for gross displacements from the previous frame is determined using large block sizes which encompass the entirety of the feature. Second, the most similar reference frame is chosen from a series of training images that are accumulated during the first K frames of tracking to aid in contour consistency and provide a starting point for the localized template initialization. Finally, localized block matching is performed through the simultaneous use of both a training frame and the previous frame. The localized block matching utilizes a series of templates positioned at the boundary points of the training and previous contours. The weighted final boundary points from both the previous and the training frame are ultimately combined and used to determine an affine transformation from the previous frame to the current frame. Results A mean tracking error of 0.72 ± 1.25 mm was observed for 85 point-landmarks across 39 ultrasound sequences relative to manual ground truth annotations. The image processing speed per landmark with the GPU implementation was between 41 and 165 frames per second (fps) during the training set accumulation, and between 73 and 234 fps after training set accumulation. Relative to a comparable multithreaded CPU approach using OpenMP, the GPU implementation resulted in speedups between −30% and 355% during training set accumulation, and between −37% and 639% postaccumulation. Conclusions Initial implementations indicated an accuracy that was comparable to or exceeding those achieved by alternative 2D tracking methods, with a computational speed that is more than sufficient for real-time applications in a radiation therapy environment. While the overall performance reached levels suitable for implementation in radiation therapy, the observed increase in failures for smaller features, as well as the algorithm's inability to be applied to nonconvex features warrants additional investigation to address the shortcomings observed. [ABSTRACT FROM AUTHOR]

The paper presents a study of existing Block Matching Optical Flow algorithms, which estimate the motion from an image sequence. The seven algorithms selected for our performance and comparative study (ES, TSS, SETSS, NTSS, FSS, DS and ARPS) are finding a minimum cost match between the current image reference block and one of the considered blocks in the next image. The benchmark used for the performance testing was the Middlebury Dataset, with the conclusions leading to a parameters and algorithm selection criteria. [ABSTRACT FROM AUTHOR]

Noise is a random variation of image intensity and visible as grains in the image. Gaussian noise is one of the noise that can be found in gray as well as colored images. Gaussian noise is a noise that has a random and normal distribution of instantaneous amplitudes over time. Gaussian noise is statistical noise having a probability density function equal to that of the normal distribution, which is also known as the Gaussian distribution. A lot of algorithms and techniques have been developed to remove the Gaussian noise from the image (both gray scale and colored).In this paper, we compare the Bilateral Filter, Block-matching and 3D filtering, Gaussian smoothing Filter, Median Filter and Spatial gradient Bilateral Filter for gray scale images and, Adaptive Bilateral Filter and Sparse 3-D transform-domain collaborative Filter for colored images. A comparative study based on Peak Signal to Noise Ratio and Mean Absolute Error of these algorithms has been provided in this paper. [ABSTRACT FROM AUTHOR]

Parabolic sub-sample interpolation for 2D block-matching motion estimation is computationally efficient. However, it is well known that the parabolic interpolation gives a biased motion estimate for displacements greater than |y.2| samples (y = 0, 1, …). Grid slope sub-sample interpolation is less biased, but it shows large variability for displacements close to y.0. We therefore propose to combine these sub-sample methods into one method (GS15PI) using a threshold to determine when to use which method. The proposed method was evaluated on simulated, phantom, and in vivo ultrasound cine loops and was compared to three sub-sample interpolation methods. On average, GS15PI reduced the absolute sub-sample estimation errors in the simulated and phantom cine loops by 14, 8, and 24% compared to sub-sample interpolation of the image, parabolic sub-sample interpolation, and grid slope sub-sample interpolation, respectively. The limited in vivo evaluation of estimations of the longitudinal movement of the common carotid artery using parabolic and grid slope sub-sample interpolation and GS15PI resulted in coefficient of variation (CV) values of 6.9, 7.5, and 6.8%, respectively. The proposed method is computationally efficient and has low bias and variance. The method is another step toward a fast and reliable method for clinical investigations of longitudinal movement of the arterial wall. [ABSTRACT FROM AUTHOR]

Most fetal brain MRI reconstruction algorithms rely only on brain tissue-relevant voxels of low-resolution (LR) images to enhance the quality of inter-slice motion correction and image reconstruction. Consequently the fetal brain needs to be localized and extracted as a first step, which is usually a laborious and time consuming manual or semi-automatic task. We have proposed in this work to use age-matched template images as prior knowledge to automatize brain localization and extraction. This has been achieved through a novel automatic brain localization and extraction method based on robust template-to-slice block matching and deformable slice-to-template registration. Our template-based approach has also enabled the reconstruction of fetal brain images in standard radiological anatomical planes in a common coordinate space. We have integrated this approach into our new reconstruction pipeline that involves intensity normalization, inter-slice motion correction, and super-resolution (SR) reconstruction. To this end we have adopted a novel approach based on projection of every slice of the LR brain masks into the template space using a fusion strategy. This has enabled the refinement of brain masks in the LR images at each motion correction iteration. The overall brain localization and extraction algorithm has shown to produce brain masks that are very close to manually drawn brain masks, showing an average Dice overlap measure of 94.5%. We have also demonstrated that adopting a slice-to-template registration and propagation of the brain mask slice-by-slice leads to a significant improvement in brain extraction performance compared to global rigid brain extraction and consequently in the quality of the final reconstructed images. Ratings performed by two expert observers show that the proposed pipeline can achieve similar reconstruction quality to reference reconstruction based on manual slice-by-slice brain extraction. The proposed brain mask refinement and reconstruction method has shown to provide promising results in automatic fetal brain MRI segmentation and volumetry in 26 fetuses with gestational age range of 23 to 38 weeks. [ABSTRACT FROM AUTHOR]

Since compressed video sequences may be corrupted or lost when transmitted over error-prone networks, error concealment techniques are very important for video communication. As a video sequence is a group of high-dimensional data, it can be considered as a big 3-order tensor. The methodologies that matricize high-dimensional data and then apply matrix-based method for further analysis often cause a loss of the internal structure information. Therefore, we built a tensor model to process such data, in order to preserve the natural multilinear structure. The key idea of our tensor model includes two parts. The first part is to construct a small tensor consist of the corrupted block and its several reference blocks. This part could be accomplished by block matching, but the traditional block matching might give a wrong match when the corrupted area is large and continuous. In order to overcome such situation, we proposed a flexible block matching scheme (FBM). The second part is to figure out the data in the corrupted part by tensor low rank approximation. Unlike the traditional low rank approximation, we did not fix the rank of core tensor as a constant number. Instead, the rank is flexible in our method, which is adaptive to the situation. Compared with some other error concealment method in the experiments, our method is able to achieve significantly higher PSNR (Peak Signal to Noise Ratio) as well as better visual quality. [ABSTRACT FROM AUTHOR]