Search

— In this study, an image processing-based deep learning approach for short-term forecast of solar radiation has been developed. For this purpose, firstly, cloud movements occurred during the day are tracked and future cloud movements are forecasted, accordingly. Subsequently, using the cloud motion estimation and extraterrestrial solar radiation data, 1-min averaged solar radiation values are estimated for 5-min time horizon. Shi-Tomasi method is employed to determine the feature points to be tracked on the sky images whereas, Lucas-Kanade optical flow method is employed to track the determined feature points on the sequential images. Average cloud velocity and directions are calculated by the help of linear regression method from tracked cloud movements. A hybrid approach including K-means and red/blue ratio is built to classify the pixels of the image whether they are clouds or sky. Finally, short-term solar radiations are estimated using the Long-Short Term Memory (LSTM) deep learning method. The performance of the proposed approach is compared with other methods in the literature. As a result it is concluded that, developed approach outperforms most methods in the literature with RMSE values of 47.576, 53.830, 68.103, and 92.386 for four different days and can be used as an alternative approach. [ABSTRACT FROM AUTHOR]

Due to the factors like rapidly fast motion, cluttered backgrounds, arbitrary object appearance variation and shape deformation, an effective target representation plays a key role in robust visual tracking. Existing methods often employ bounding boxes for target representations, which are easily polluted by noisy clutter backgrounds that may cause drifting problem when the target undergoes large-scale non-rigid or articulated motions. To address this issue, in this paper, motivated by the spatio-temporal nonlocality of target appearance reoccurrence in a video, we explore the nonlocal information to accurately represent and segment the target, yielding an object likelihood map to regularize a correlation filter (CF) for visual tracking. Specifically, given a set of tracked target bounding boxes, we first generate a set of superpixels to represent the foreground and background, and then update the appearance of each superpixel with its long-term spatio-temporally nonlocal counterparts. Then, with the updated appearances, we formulate a spatio-temporally graphical model comprised of the superpixel label consistency potentials. Afterwards, we generate segmentation by optimizing the graphical model via iteratively updating the appearance model and estimating the labels. Finally, with the segmentation mask, we obtain an object likelihood map that is employed to adaptively regularize the CF learning by suppressing the clutter background noises while making full use of the long-term stable target appearance information. Extensive evaluations on the OTB50, SegTrack, Youtube-Objects datasets demonstrate the effectiveness of the proposed method, which performs favorably against some state-of-art methods. [ABSTRACT FROM AUTHOR]

This article presents the implementation of a tracking system for a moving target using a fixed camera. The objective of this work is the ability to detect a moving object and locate their positions. In picture processing, tracking moving objects in a known or unknown environment is commonly studied. It is based on invariance properties of objects of interest. The invariance can affect the geometry of the scene or the objects. The proposed approach is composed of several steps; the first is the extraction of points of interest in the current image. Then, these points will be tracked in the following image by using techniques for calculating the optical flow. After this step, the static points will be removed to focus on moving objects, That is to say, there is only the characteristic points belonging to moving objects. Now, to detect moving targets using images of the video, the background is first extracted from the successive images. In our approach, a method of the average values of every pixel has been developed for modeling background. The last step which stays before switching to tracking moving object is the segmentation which allows identifying every moving object. And by using the characteristic points in the previous steps. [ABSTRACT FROM AUTHOR]

In this paper, we present a frame rate upconversion method using optical flow motion estimation and a patch-based reconstruction scheme. First, forward and backward motion vectors (MVs) are obtained using an optical flow algorithm, and reconstructed versions of the current and previous frames are generated by our patch-based reconstruction scheme. Using the original and reconstructed versions of the current and previous frames, two mismatch masks are obtained. Then, two versions of the middle frame are generated using a patch-based scheme, with estimated MVs and the current and previous frames. Finally, a middle mask, which identifies the mismatch areas of the two middle frames, is reconstructed. Using these three masks, the best candidates for interpolation are selected and fused to obtain the final middle frame. Due to the patch-based nature of our reconstruction scheme, most of the holes and cracks will be filled. Although there is always a probability of having holes, the size and number of such holes are much smaller than those that would be generated using pixel-based mapping. The rare holes are filled using existing hole-filling algorithms. The experimental results and a comparison of our method with existing algorithms show that our method performs better in terms of both objective and subjective quality of the final interpolated frames. The average peak signal-to-noise ratio (PSNR) improvement of our method is 1–2 dB. [ABSTRACT FROM AUTHOR]

Separation of video clips into foreground and background components is a useful and important technique, making recognition, classification, and scene analysis more efficient. In this paper, we propose a motion-assisted matrix restoration (MAMR) model for foreground–background separation in video clips. In the proposed MAMR model, the backgrounds across frames are modeled by a low-rank matrix, while the foreground objects are modeled by a sparse matrix. To facilitate efficient foreground-background separation, a dense motion field is estimated for each frame, and mapped into a weighting matrix which indicates the likelihood that each pixel belongs to the background. Anchor frames are selected in the dense motion estimation to overcome the difficulty of detecting slowly moving objects and camouflages. In addition, we extend our model to a robust MAMR model against noise for practical applications. Evaluations on challenging datasets demonstrate that our method outperforms many other state-of-the-art methods, and is versatile for a wide range of surveillance videos. [ABSTRACT FROM AUTHOR]

In super-resolution that constructs a high-resolution (HR) image from a set of low-resolution (LR) reference images, it is crucial to align the LR reference images in order to efficiently exploit the pixels therein. However, due to the existence of complex local motion, ideal registration is difficult to acquire. In this paper, we present a robust video super-resolution scheme with registration-reliability regulation and content adaptive total variation regularization, which make the scheme resilient to registration failures. In order to handle ill-registered pixels, we propose a registration-reliability regulated data-fidelity term, which assigns smaller weights to the pixels with larger locally-averaged registration residuals. In addition, a content adaptive total variation based on structure tensor, which is used to estimate image local structures, is proposed to regularize the super-resolved images. The structure tensor is derived not only from the gradients of local patches but also the nonlocal similar patches. Experimental results show that the proposed scheme can remarkably improve both the objective and subjective quality of the video super-resolution results. [ABSTRACT FROM AUTHOR]

Motion tracking algorithms are widely used in computer vision related research. However, the new video standards, especially those in high resolutions, cause that current implementations, even running on modern hardware, no longer meet the needs of real-time processing. To overcome this challenge several GPU (Graphics Processing Unit) computing approaches have recently been proposed. Although they present a great potential of a GPU platform, hardly any is able to process high definition video sequences efficiently. Thus, a need arose to develop a tool being able to address the outlined problem. In this paper we present software that implements optical flow motion tracking using the Lucas-Kanade algorithm. It is also integrated with the Harris corner detector and therefore the algorithm may perform sparse tracking, i.e. tracking of the meaningful pixels only. This allows to substantially lower the computational burden of the method. Moreover, both parts of the algorithm, i.e. corner selection and tracking, are implemented on GPU and, as a result, the software is immensely fast, allowing for real-time motion tracking on videos in Full HD or even 4K format. In order to deliver the highest performance, it also supports multiple GPU systems, where it scales up very well [ABSTRACT FROM AUTHOR]

We present a supervised learning-based method to estimate a per-pixel confidence for optical flow vectors. Regions of low texture and pixels close to occlusion boundaries are known to be difficult for optical flow algorithms. Using a spatiotemporal feature vector, we estimate if a flow algorithm is likely to fail in a given region. Our method is not restricted to any specific class of flow algorithm and does not make any scene specific assumptions. By automatically learning this confidence, we can combine the output of several computed flow fields from different algorithms to select the best performing algorithm per pixel. Our optical flow confidence measure allows one to achieve better overall results by discarding the most troublesome pixels. We illustrate the effectiveness of our method on four different optical flow algorithms over a variety of real and synthetic sequences. For algorithm selection, we achieve the top overall results on a large test set, and at times even surpass the results of the best algorithm among the candidates. [ABSTRACT FROM PUBLISHER]

Abstract: The intensity (grey value) consistency of image pixels in a sequence or stereo camera setup is of central importance to numerous computer vision applications. Most stereo matching and optical flow algorithms minimise an energy function composed of a data term and a regularity or smoothing term. To date, well performing methods rely on the intensity consistency of the image pixel values to model the data term. Such a simple model fails if the illumination is (even slightly) different between the input images. Amongst other situations, this may happen due to background illumination change over the sequence, different reflectivity of a surface, vignetting, or shading effects. In this paper, we investigate the removal of illumination artifacts and show that generalised residual images substantially improve the accuracy of correspondence algorithms. In particular, we motivate the concept of residual images and show two evaluation approaches using either ground truth correspondence fields (for stereo matching and optical flow algorithms) or errors based on a predicted view (for stereo matching algorithms). [Copyright &y& Elsevier]

A 3D model based approach for a face representation and recognition algorithm has been investigated as a robust solution for pose and illumination variation. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time and complexity. In this paper, we propose a novel 3D face representation algorithm based on a pixel to vertex map (PVM) to optimize the number of vertices. We explore shape and texture coefficient vectors of the 3D model by fitting it to an input face using inverse compositional image alignment (ICIA) to evaluate face recognition performance. Experimental results show that the proposed face representation and recognition algorithm is efficient in computation time while maintaining reasonable accuracy. [ABSTRACT FROM AUTHOR]

Abstract: This work presents a new method for motion estimation of tagged cardiac magnetic resonance sequences based on variational techniques. The variational method has been improved by adding a new term in the optical flow equation that incorporates tracking points with high stability of phase. Results were obtained through simulated and real data, and were validated by manual tracking and with respect to a reference state-of-the-art method: harmonic phase imaging (HARP). The error, measured in pixels per frame, obtained with the proposed variational method is one order of magnitude smaller than the one achieved by the reference method, and it requires a lower computational cost. [Copyright &y& Elsevier]

• A new method for non-contact measurement of vibration frequency. • Use deep learning methods to replace traditional edge detection methods. • Optical flow method can extract the vibration time history of the object. • A comparison of measurement accuracy between proposed methods and sensors. This paper proposes a non-contact vibration measurement method based on deep learning and image processing. The deep learning method is used to realize the automatic and efficient selection of effective pixels and the optical flow method is used to extract vibration signals to realize non-contact and targetless visual vibration measurement. In this study, a carbon plate board and aluminum C-beam structure were measured and verified under artificial and non-human excitation in a laboratory environment. Additionally, bridge and cable structures in an outdoor environment were selected as measurement targets to verify the reliability of the proposed method. This paper compares the experimental results of Canny and Sobel edge detection algorithms and deep learning methods to verify the efficiency of deep learning. The results demonstrate that our method is robust, even under real-world unfavorable conditions, meaning it can serve as a novel measurement method in the field of vibration measurement. [ABSTRACT FROM AUTHOR]

Abstract: Optical flow can be used to segment a moving object from its background provided the velocity of the object is distinguishable from that of the background, and has expected characteristics. Existing optical flow techniques often detect flow (and thus the object) in the background. To overcome this, we propose a new optical flow technique, which only determines optical flow in regions of motion. We also propose a method by which output from a tracking system can be fed back into the motion segmenter/optical flow system to reinforce the detected motion, or aid in predicting the optical flow. This technique has been developed for use in person tracking systems, and our testing shows that for this application it is more effective than other commonly used optical flow techniques. When tested within a tracking system, it works with an average position error of less than six and a half pixels, outperforming the current CAVIAR [1] The CAVIAR database, and the associated ground truth data is available for download at http://homepages.inf.ed.ac.uk/rbf/CAVIAR/. 1 benchmark system. [Copyright &y& Elsevier]

This paper proposes an accurate method for the restoration of missing intensities of still images by using the optical flow. It is important in restoration to reconstruct missing edges correctly. Therefore, this paper modifies the optical flow conventionally used for motion analysis in video images and applies it to the restoration of missing intensities. Further, the proposed method introduces a new index expressing the correlation of intensities between two pixels into the scheme for calculation of the optical flow in order to obtain a flow which gives more accurate estimated values. The optical flow calculated by this index provides the pixel from the neighborhood whose intensity is most similar to that of the target pixel, so that the estimated intensity is not affected by pixels whose intensities are quite different. Consequently, even when multiple edges pass through the missing area or the direction of the edge changes significantly inside the area, the proposed method can reconstruct the edges correctly. Some experimental results are presented in order to verify the high performance of the proposed method. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(3): 49–57, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20376 [ABSTRACT FROM AUTHOR]