Search

This paper presents a framework to automatically replant timestamps for panorama video surveillance. The system mainly comprises six modules: 1) timestamp localization; 2) image registration; 3) timestamp pixel recovery; 4) color correction; 5) timestamp recognition; and 6) panorama video generation. The proposed framework first develops a method to localize the timestamp by employing the method of locating digital video clocks. Then, a fast and novel method is developed to recover the pixels covered by timestamps. The proposed method has fast speed because a fast image translation estimation procedure is introduced based on the PTZ camera motion estimation and global histogram-based image matching. Moreover, a hybrid color correction method by combining region matching with the gamma correction and the linear correction is presented. To plant timestamps accurately, a timestamp recognition procedure is developed by adopting the time recognition method for digit video clocks. Experimental results show that the proposed approach can accurately remove timestamps in real time, the recovered frames are visually consistent with the real scene, and the performance of color correction for panorama video is visually acceptable. [ABSTRACT FROM AUTHOR]

Many recent applications require text segmentation for born-digital compound images. To this end, we propose a coarse-to-fine framework for segmenting texts of arbitrary scales and orientations in born-digital compound images. In the coarse stage, the local image activity measure is designed based upon the variation distribution of characters, to highlight the difference between textual and pictorial regions. This stage outputs a coarse textual layer including textual regions as well as a few pictorial regions with high activity. In the fine stage, a textual connected component (TCC) based refinement is proposed to eliminate the survived pictorial regions. In particular, a scale and orientation invariant grouping algorithm is proposed to adaptively generate TCCs with uniform statistical features. The minimum average distance and morphological operations are employed to assist the formation of candidate TCCs. Then, three string-level features (i.e., shapeness, color similarity, and mean activity level) are designed to distinguish the true TCCs from the false positive ones that are formed by connecting the high activity pictorial components. Extensive experiments show that the proposed framework can segment textual regions precisely from born-digital compound images, while preserving the integrity of texts with varied scales and orientations, and avoiding over-connection of textual regions. [ABSTRACT FROM PUBLISHER]

It is known that local filtering-based edge-preserving smoothing techniques suffer from halo artifacts. In this paper, a weighted guided image filter (WGIF) is introduced by incorporating an edge-aware weighting into an existing guided image filter (GIF) to address the problem. The WGIF inherits advantages of both global and local smoothing filters in the sense that: 1) the complexity of the WGIF is $O(N)$ for an image with $N$ pixels, which is same as the GIF and 2) the WGIF can avoid halo artifacts like the existing global smoothing filters. The WGIF is applied for single image detail enhancement, single image haze removal, and fusion of differently exposed images. Experimental results show that the resultant algorithms produce images with better visual quality and at the same time halo artifacts can be reduced/avoided from appearing in the final images with negligible increment on running times. [ABSTRACT FROM AUTHOR]

In this paper, a novel learning algorithm for dynamic fuzzy neural networks based on extended radial basis function neural networks, which are functionally equivalent to Takagi–Sugeno–Kang fuzzy systems, is proposed. The algorithm comprises 4 parts: (1) criteria of rules generation; (2) allocation of premise parameters; (3) determination of consequent parameters and (4) pruning technology. The salient characteristics of the approach are: (1) a hierarchical on-line self-organizing learning paradigm is employed so that not only parameters can be adjusted, but also the determination of structure can be self-adaptive without partitioning the input space a priori; (2) fast learning speed can be achieved so that the system can be implemented in real time. Simulation studies and comprehensive comparisons with some other learning algorithms demonstrate that the proposed algorithm is superior in terms of simplicity of structure, learning efficiency and performance. [ABSTRACT FROM AUTHOR]

Capturing high-quality images via mobile devices in low-light or backlighting conditions is very challenging. In this paper, a new, single image brightening algorithm is proposed to enhance an image captured in low-light conditions. Two virtual images with larger exposure times are generated to increase brightness and enhance fine details of the underexposed regions. In order to reduce the brightness change, the virtual images are generated via intensity mapping functions (IMFs) which are computed using available camera response functions (CRFs). To avoid possible color distortion in the virtual image due to one-to-many mapping, a least square minimization problem is formulated to determine brightening factors for all pixels in the underexposed regions. In addition, an edge-preserving smoothing technique is adopted to avoid noise in the underexposed regions from being amplified in the virtual images. The final brightened image is obtained by fusing the original image and two virtual images via a gradient domain guided image filtering (GGIF) based multiscale exposure fusion (MEF) with properly defined weights for all the images. Experimental results show that the relative brightness and color are preserved better by the proposed algorithm. The details in bright regions are also preserved well in the final image. The proposed algorithm is expected to be useful for computational photography on smart phones. [ABSTRACT FROM AUTHOR]

Geometric model fitting is a fundamental issue in computer vision, and the fitting accuracy is affected by outliers. In order to eliminate the impact of the outliers, the inlier threshold or scale estimator is usually adopted. However, a single inlier threshold cannot satisfy multiple models in the data, and scale estimators with a certain noise distribution model work poorly in geometric model fitting. It can be observed that the residuals of outliers are big for all true models in the data, which makes the consensus of the outliers. Based on this observation, we propose a preference analysis method based on residual histograms to study the outlier consensus for outlier detection in this paper. We have found that the outlier consensus makes the outliers gather away from the inliers on the designed residual histogram preference space, which is quite convenient to separate outliers from inliers through linkage clustering. After the outliers are detected and removed, a linkage clustering with permutation preference is introduced to segment the inliers. In addition, in order to make the linkage clustering process stable and robust, an alternative sampling and clustering framework is proposed in both the outlier detection and inlier segmentation processes. The experimental results also show that the outlier detection scheme based on residual histogram preference can detect most of the outliers in the data sets, and the fitting results are better than most of the state-of-the-art methods in geometric multi-model fitting. [ABSTRACT FROM AUTHOR]

Calibration is a critical step for the phase measuring deflectometry system. Existing calibration methods are mainly optimizing the calibration parameters with respect to the 2D re-projection error criterion. However, such a procedure cannot reduce metric errors in the practical application. Therefore, an accurate and practical calibration method is proposed. In which, conventional calibration means is first applied for the primary calibration. Then, a precise square planar mirror is used for the optimization of system calibration parameters. All the intrinsic and extrinsic parameters are considered as a global multi-objective optimization problem. Three metric error criteria are introduced to evaluate the 3D reconstruction accuracy of the reference mirror. Compared with classical calibration means, which apply the parameter optimization in 2D image space to minimize the re-projection errors, the proposed optimization approach is executed in 3D space directly. An experiment and comparison are conducted to verify that the proposed optimal calibration approach can effectively reduce the system deviation and to improve the system measurement accuracy. [ABSTRACT FROM AUTHOR]

Estimating the Direction of Arrival (DOA) is a basic and crucial problem in array signal processing. The existing DOA methods fail to obtain reliable and accurate results when noise and reverberation occur in real applications. In this paper, an accurate and robust estimation method for estimating the DOA of sources signal is proposed. Incorporating the Estimating Signal Parameters via Rotational Invariance Techniques (ESPRIT) algorithm with the RANdom SAmple Consensus (RANSAC) algorithm gives rise to the RAN-ESPRIT method, which removes outliers automatically in noise-corrupted environments. In this work, a uniform circular array (UCA) is converted into a virtual uniform linear array (ULA) to begin with. Then, the covariance matrix of the received signals of the virtual linear array is reconstructed, and the ESPRIT algorithm is deployed to estimate initial DOA of the source signal. Finally, the modified RANSAC method with automatically selected thresholds is used to fit the source signal to obtain accurate DOA. The proposed method can remove the unreliable DOA feature data and leads to more accuracy of DOA estimation of source signals in reverberation environments. Experimental results demonstrate that the proposed method is more robust and efficient compared to the traditional methods (i.e., ESPRIT, TLS-ESPRIT). [ABSTRACT FROM AUTHOR]

It is challenging to convert a hazy color image into a gray-scale image because the color contrast field of a hazy image is distorted. In this paper, a novel decolorization algorithm is proposed to transfer a hazy image into a distortion-recovered gray-scale image. To recover the color contrast field, the relationship between the restored color contrast and its distorted input is presented in CIELab color space. Based on this restoration, a nonlinear optimization problem is formulated to construct the resultant gray-scale image. A new differentiable approximation solution is introduced to solve this problem with an extension of the Huber loss function. Experimental results show that the proposed algorithm effectively preserves the global luminance consistency while represents the original color contrast in gray-scales, which is very close to the corresponding ground truth gray-scale one. [ABSTRACT FROM AUTHOR]

RRT* (Rapidly-exploring Random Tree Star), as a variant of RRT (Rapidly-exploring Random Tree), is widely used to solve path planning problems because of its asymptotic optimality. However, the algorithm is inefficient due to the high initial path cost and the slow convergence rate. In this paper, we propose a More Quickly-RRT* (MQ-RRT*) path planning algorithm based on optimized sampling points to solve the problems. A sparse sampling mechanism is proposed in MQ-RRT* to improve the global search efficiency by reducing repetitive sampling. To make the random tree oriented when expanding, a dynamic goal-biased strategy is proposed, which can reduce the sampling time. Like Q-RRT* (Quick-RRT*), MQ-RRT* expands the set of possible parent nodes in the ChooseParent and Rewire phases, which reduces the path cost. On this basis, a method for creating a new parent node close to the obstacle is proposed. The creation process can be divided into two steps: Remove-tips and CreateNodes , which further reduces the cost of path generation and makes the path smoother by using the triangle inequality principle. Finally, numerical simulations are used to compare the proposed algorithm with RRT*, Q-RRT*, GuILD (Guided Incremental Local Densification), and F-RRT* (Fast-RRT*), which verifies that the proposed algorithm has certain advantages in path cost, convergence rate, and path smoothness. [ABSTRACT FROM AUTHOR]

Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free images with high PSNR and SSIM values for synthetic hazy images but with low contrast, and even some remaining haze for real-world hazy images. In this paper, a novel single image dehazing algorithm is introduced by combining model-based and data-driven approaches. Both transmission map and atmospheric light are first estimated by the model-based methods, and then refined by dual-scale generative adversarial networks (GANs) based approaches. The resultant algorithm forms a neural augmentation which converges very fast while the corresponding data-driven approach might not converge. Haze-free images are restored by using the estimated transmission map and atmospheric light as well as the Koschmieder’s law. Experimental results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images. [ABSTRACT FROM AUTHOR]

Audio–Visual Segmentation (AVS) aims to extract the sounding objects from a video. The current learning-based AVS methods are often supervised, which rely on specific task data annotations and expensive model training. Recognizing that the video background captured by a static camera is represented as a low-rank matrix, we introduce the non-convex robust principal component analysis into AVS task in this paper. This approach is unsupervised and only relies on input data patterns. Specifically, the proposed method decomposes each modality into the sum of two parts: the low-rank part that represents the background audio and visual information, and the sparse part that represents the foreground information. Furthermore, CUR decomposition is employed at each iteration to reduce the computational complexity in optimization. The experimental results also show that the proposed AVS outperforms the supervised methods on AVS-Bench Single-Source datasets. • Firstly introduces non-convex RPCA for Audio–Visual Segmentation. • Applies CUR decomposition to reduce computational complexity. • The task of unsupervised Audio–Visual Segmentation. • Demonstrates efficiency and effectiveness results on the AVS dataset. [ABSTRACT FROM AUTHOR]

A small ISO and a small exposure time are usually used to capture an image in back- or low-light condition which results in an image with negligible motion blur and small noise but looks dark. In this paper, a single image brightening algorithm is introduced to brighten such an image. The proposed algorithm includes a unique hybrid learning framework to generate two virtual images with large exposure times. The virtual images are first generated via intensity mapping functions (IMFs) which are computed using camera response functions (CRFs) and this is a model-driven approach. Both the virtual images are then enhanced by using a data-driven approach, i.e. a residual convolutional neural network to approach the ground truth images. The model-driven approach and the data-driven one compensate each other in the proposed hybrid learning framework. The final brightened image is obtained by fusing the original image and two virtual images via a multi-scale exposure fusion algorithm with properly defined weights. Experimental results show that the proposed brightening algorithm outperforms existing algorithms in terms of MEF-SSIM metric. [ABSTRACT FROM AUTHOR]