A Dual Source, Parallel Architecture for Computer Vision

Recently, Time-of-Flight (ToF) cameras have emerged as a new mean for intra-operative image acquisition. The ToF camera features co-registered depth and intensity image data from the observed scene in video frame rate. Due to systematic distance errors, depth calibration is crucially needed. One of the sources of error that so far received little attention in literature related to ToF camera calibration is the temperature of the camera’s video chip. In this work we address the effect of active air conditioning in medically used rooms on the temperature related distance variability. The conducted experiments in which data were acquired over a long time indicate a reduction of the runtime related distance drift by up to factor five and a reduction of the measurement offset by factor three for certain examined ToF cameras in actively compared to passively climate controlled rooms. This has important implications on the ToF camera depth calibration process, for the calibration of the temperature related distance deviation in rooms with active air conditioning can be reduced to an easy to determine offset.

Crack segmentation through deep convolutional neural networks and heterogeneous image fusion

Edge detection is a fundamental image processing technique used to spot sudden shifts in color or intensity in image. It is utilized to detect and highlight boundaries between various items or regions in image, as well as to detect features such as corners, circles and lines. Edge detection approaches typically work by applying a filter to an image to detect areas where the image undergoes an immediate shift in magnitude. Applications for edge detection techniques include recognizing objects, healthcare images, and background segmentation. Many techniques have been presented based on the classical approaches (such as Sobel, Prewitt, and Roberts, Canny, Laplacian of Gaussian (LOG), etc.) and soft computing approaches (SCA), which are the two main approaches for detection of edge. This paper provides an overview of studies carried out on edge detection using various approaches. That will assist brand-new researchers in learning about these techniques and selecting one from among them to evolve or improve according to their field of study.

Quick and accurate estimation for the 6-DoF pose of a randomly arranged object in intricate shape plays an important role in robotic picking applications. In this paper we propose an approach based on template matching by using the aligned RGB-D image with prior knowledge to recover the 6-DoF pose of a randomly arranged object. First, the object’s template database is generated with the help of a defined virtual imaging model and its CAD model. Then in the practical phase, we segment RGB-D image to get the mask representing the location of the object and then these data are modified into a comparable format with the characteristics of scale invariance. At last, a similar function with adjustable attention weight to color and depth data is defined to find Top-K matched templates. The selected matched templates are refined by ICP to generate the final answer. Experiments are conducted using an RGB-D camera and a robot arm to pick up given objects in intricate shape. The average recognition rate of the object in different poses is 97.826%. It also can work well with multiple objects randomly arranged with good masks representing the locations.

The CCP11 project [2] aims to foster bioinformaticsin the UK through conferences, workshops andthe provision of Web resources. In March 2002,CCP11 held a meeting in Manchester, UK, on thefunctional analysis of microarrays. This was part ofManchester BioinformaticsWeek—three consecutiveshort bioinformatics meetings held in the attractivesetting of the Chancellor's Conference Centreat the University of Manchester. The other meetingsin the series were a workshop on ontologiesand the 12th Annual MASAMB (Mathematical andStatistical Aspects of Molecular Biology) Conference.Many delegates were able to attend more thanone meeting, which led to a useful cross-fertilizationof ideas across the bioinformatics community. TheCCP11 meeting shared with MASAMB a strongemphasis on the statistical analysis and interpretationof data—most often image intensity data.

Edge detection, especially from colour images, plays very important roles in many applications for image analysis, segmentation and recognition. Most existing methods extract colour edges via fusing edges detected from each colour components or detecting from the intensity image where inter-component information is ignored. In this study, an improved method on colour edge detection is proposed in which the significant advantage is the use of inter-component difference information for effective colour edge detection. For any given colour image C, a grey D-image is defined as the accumulative differences between each of its two colour components, and another grey R-image is then obtained by weighting of D-image and the grey intensity image G. The final edges are determined through fusion of edges extracted from R-image and G-image. Quantitative evaluations under various levels of Gaussian noise are achieved for further comparisons. Comprehensive results from different test images have proved that this approach outperforms edges detected from traditional colour spaces like RGB, YCbCr and HSV in terms of effectiveness and robustness.

The logarithmic image processing (LIP) model is a mathematical framework which provides a specific set of algebraic and functional operations for the processing and analysis of intensity images valued in a bounded range. The LIP model has been proved to be physically justified by that it is consistent with the multiplicative transmittance and reflectance image formation models, and with some important laws and characteristics of human brightness perception. This article addresses the edge detection problem using the LIP-model based differentiation. First, the LIP model is introduced, in particular, for the gray tones and gray tone functions, which represent intensity values and intensity images, respectively. Then, an extension of these LIP model notions, respectively called gray tone vectors and gray tone vector functions, is studied. Third, the LIP-model based differential operators are presented, focusing on their distinctive properties for image processing. Emphasis is also placed on highlighting the main characteristics of the LIP-model based differentiation. Next, the LIP-Sobel based edge detection technique is studied and applied to edge detection, showing its robustness in locally small changes in scene illumination conditions and its performance in the presence of noise. Its theoretical and practical advantages over several well-known edge detection techniques, such as the techniques of Sobel, Canny, Johnson and Wallis, are shown through a general discussion and illustrated by simulation results on different real images. Finally, a discussion on the role of the LIP-model based differentiation in the current context of edge detection is presented.

3D video representations usually associate to each view a depth map with the corresponding geometric information. Many compression schemes have been proposed for multi-view video and for depth data, but the exploitation of the correlation between the two representations to enhance compression performances is still an open research issue. This paper presents a novel compression scheme that exploits a segmentation of the color data to predict the shape of the different surfaces in the depth map. Then each segment is approximated with a parameterized plane. In case the approximation is sufficiently accurate for the target bit rate, the surface coefficients are compressed and transmitted. Otherwise, the region is coded using a standard H.264/AVC Intra coder. Experimental results show that the proposed scheme permits to outperformthe standardH.264/AVC Intra codec on depth data and can be effectively included into multi-view plus depth compression schemes.

In this paper the problem of image feature extraction is considered with emphasis on developing methods which are resilient in the presence of data contamination. The issue of robustness of estimation procedures has received considerable attention in the statistics community [1–3] but its results are only recently being applied to specific image analysis tasks [4–7]. In this paper we show how the design of robust methods applies to image description tasks posed within a statistical hypothesis testing and parameter estimation framework. The methodology is illustrated by applying it to finding robust, optimal estimation kernels for line detection and edge detection. We then discuss the relationship of these optimal solutions to both the well established Hough Transform technique and the standard estimation kernels developed in the statistics literature. The application of standard robust kernels to image analysis tasks is illustrated by two examples which involve circular arc detection in gray-level imagery and planar surface segmentation in depth data. Robust methods are found to be effective general tools for generating 2D and 3D image descriptions.

This paper presents a new algorithm for the joint restoration of depth and intensity images constructed from the time-correlated single-photon counting (TCSPC) measurement in the limit of very few photon counts [1]. Under some justified approximations, the restoration problem (regularized likelihood) reduces to a convex formulation with respect to the parameters of interest. The first advantage of this formulation is that it only processes the corrupted depth and intensity images obtained from preliminary estimation, without the need for the use of full TCSPC waveforms. The second advantage is its flexibility in being able to use different convex regularization terms such as: total variation (TV); and sparsity of the discrete cosine transform (DCT) coefficients. The estimation problems are efficiently solved using the alternating direction method of multipliers (ADMM) that presents good convergence properties and thus a reduced computational cost. Results on single photon depth data from field trials show the benefit of the proposed strategy that improves the quality of the estimated depth and intensity images.

For any modern 3D vision guided system, it is imperative to have complete range images for 3D model reconstruction. In practice, depth images obtained from a standard stereo camera can be error-prone with missing depth pixels. This paper proposes a method to augment the range data obtained from stereoscopy with model based image segmentation using planar patches. The method integrates both intensity and range data obtained from a standard stereo system. First, edges are extracted and linked to different segments from the intensity image with the embedded confidence edge detection technique and a general edge-linking algorithm respectively. Since edges are where disparity happens, most straight-line edges segmented from linked edges using a line-curvature extraction algorithm will have valid depth data. The planar patches are then defined by the straight-lines edge. With the knowledge of the planar structure, each depth missing pixels in the region is then determined by various 3-D line equations that pass through the pixel in the world coordinate system. Lastly, the range data in the world coordinate system is converted back into the image coordinate system using a pixel-to-pixel project algorithm. Result demonstrates the accuracy of method for filling up the missing depth in a region.

The objectives of this research are to develop robust methods for segmentation of multitemporal synthetic aperture radar (SAR) and optical data and to investigate the fusion of multitemporal ENVISAT advanced synthetic aperture radar (ASAR) and Chinese HJ-1B multispectral data for detailed urban land-cover mapping. Eight-date multiangle ENVISAT ASAR images and one-date HJ-1B charge-coupled device image acquired over Beijing in 2009 are selected for this research. The edge-aware region growing and merging (EARGM) algorithm is developed for segmentation of SAR and optical data. Edge detection using a Sobel filter is applied on SAR and optical data individually, and a majority voting approach is used to integrate all edge images. The edges are then used in a segmentation process to ensure that segments do not grow over edges. The segmentation is influenced by minimum and maximum segment sizes as well as the two homogeneity criteria, namely, a measure of color and a measure of texture. The classification is performed using support vector machines. The results show that our EARGM algorithm produces better segmentation than eCognition, particularly for built-up classes and linear features. The best classification result (80%) is achieved using the fusion of eight-date ENVISAT ASAR and HJ-1B data. This represents 5%, 11%, and 14% improvements over eCognition, HJ-1B, and ASAR classifications, respectively. The second best classification is achieved using fusion of four-date ENVISAT ASAR and HJ-1B data (78%). The result indicates that fewer multitemporal SAR images can achieve similar classification accuracy if multitemporal multiangle dual-look-direction SAR data are carefully selected.

The authors develop the optimal criterion for edge detection in single look complex (SLC) synthetic aperture radar (SAR) images. By working on complex data rather than intensity images, the authors can take the speckle autocorrelation into account, obtain more accurate estimations of local mean reflectivities, and thus achieve better edge detection performance.

In image processing, edge detection concerns with the localization of discontinuity of the gray scale images, accurately detecting continuous edges is difficult in noisy images. Usually for accurate edge detection requires smoothing and differentiation, to localize edge pixels in intensity images. Smoothing images with median filter instead of Gaussian filter has more edge preserving tendency. In this proposed method, filtered images with non- linear filter, which is convolved with two new developed 3×3 operators for detecting gradient magnitude of images. The resulted thick binary edges were filter with two new developed structure matrices for enhancement in binary edges. The new algorithm is examined and compared with the traditional edge detectors. The comparison is based on two type of distributed noises Gaussian and salt and pepper. The results comparison suggests that the new algorithm detect edges more accurate thinner and smoother than the edges detected by traditional edge detector.

Efficient patient modeling for visuo-haptic VR simulation using a generic patient atlas