Search

Depth image-based rendering (DIBR) techniques have recently drawn more attention in various 3D applications. In this paper, a real-time high-quality DIBR system that consists of disparity estimation and view synthesis is proposed. For disparity estimation, a local approach that focuses on depth discontinuities and disparity smoothness is presented to improve the disparity accuracy. For view synthesis, a method that contains view interpolation and extrapolation is proposed to render high-quality virtual views. Moreover, the system is designed with an optimized parallelism scheme to achieve a high throughput, and can be scaled up easily. It is implemented on an Altera Stratix IV FPGA at a processing speed of 45 frames per second for 1080p resolution. Evaluated on selected image sets of the Middlebury benchmark, the average error rate of the disparity maps is 6.02%; the average peak signal to noise ratio and structural similarity values of the virtual views are 30.07 dB and 0.9303, respectively. The experimental results indicate that the proposed DIBR system has the top-performing processing speed and its accuracy performance is among the best of state-of-the-art hardware implementations. [ABSTRACT FROM AUTHOR]

Although numerous trackers have been designed to adapt to the nonstationary image streams that change over time, it remains a challenging task to facilitate a tracker to accurately distinguish the target from the background in every frame. This paper proposes a robust superpixel-based tracker via depth fusion, which exploits the adequate structural information and great flexibility of mid-level features captured by superpixels, as well as the depth-map's discriminative ability for the target and background separation. By introducing graph-regularized sparse coding into the appearance model, the local geometrical structure of data is considered, and the resulting appearance model has a more powerful discriminative ability. Meanwhile, the similarity of the target superpixels' neighborhoods in two adjacent frames is also incorporated into the refinement of the target estimation, which helps a more accurate localization. Most importantly, the depth cue is fused into the superpixel-based target estimation so as to tackle the cluttered background with similar appearance to the target. To evaluate the effectiveness of the proposed tracker, four video sequences of different challenging situations are contributed by the authors. The comparison results demonstrate that the proposed tracker has more robust and accurate performance than seven ones representing the state-of-the-art. [ABSTRACT FROM AUTHOR]

As one of the fundamental technologies for scene understanding, semantic segmentation has been widely explored in the last few years. Light field cameras encode the geometric information by simultaneously recording the spatial information and angular information of light rays, which provides us with a new way to solve this issue. In this paper, we propose a high-quality and challenging urban scene dataset, containing 1074 samples composed of real-world and synthetic light field images as well as pixel-wise annotations for 14 semantic classes. To the best of our knowledge, it is the largest and the most diverse light field dataset for semantic segmentation. We further design two new semantic segmentation baselines tailored for light field and compare them with state-of-the-art RGB, video and RGB-D-based methods using the proposed dataset. The outperforming results of our baselines demonstrate the advantages of the geometric information in light field for this task. We also provide evaluations of super-resolution and depth estimation methods, showing that the proposed dataset presents new challenges and supports detailed comparisons among different methods. We expect this work inspires new research direction and stimulates scientific progress in related fields. The complete dataset is available at https://github.com/HAWKEYE-Group/UrbanLF. [ABSTRACT FROM AUTHOR]

As a specific data hiding technique, reversible data hiding (RDH) has recently received extensive attention. By this technique, both the embedded data and the original cover image can be exactly extracted from the marked image. In our previous work, a general expansion-shifting model for RDH is proposed by introducing the so-called reversible embedding function (REF). With REF, RDH can be designed and the corresponding rate-distortion formulations can be established, providing an approach to optimize the reversible embedding performance. In this paper, by extending our previous work, optimal REF for one-dimensional histogram is investigated, and all optimal REF are derived in this case when the maximum modification to the cover pixel is limited as a small value. Moreover, based on the derived optimal REF for one-dimensional histogram and multiple histograms modification, a practical RDH scheme is presented and it is experimental verified better than some state-of-the-art algorithms in terms of capacity-distortion performance. [ABSTRACT FROM AUTHOR]

Recently, region-based 3D video coding has been proposed. However, existing view synthesis distortion estimation (VSDE) methods are performed at the frame level. To guide the rate-distortion optimization process of region-based 3D video coding schemes, this paper proposes the first pixel-level VSDE (PL-VSDE) method. We first give the definition of the pixel-level view synthesis distortion. To estimate it, a backward prediction method is then developed, which starts from the pixels of interest (POIs) in the virtual view and finds their corresponding pixels in the reference view via a coarse-to-fine approach, denoted as coarse-to-fine backward prediction (CFBP) method. Additionally, the CFBP fully considers the details of 3D warping, the rounding operation and the warping competition in view synthesis, leading to improve accuracy of the prediction. Besides, a table-lookup method and a warping property are introduced to speed up the CFBP. After integrating the CFBP into the PL-VSDE, we can estimate the view synthesis distortion at the pixel level. Our method is carried out pixel-by-pixel independently, which is friendly for parallel processing. The experimental results demonstrate that our proposed method has significant advantages in both accuracy and efficiency compared with the state-of-the-art frame-level VSDE methods. [ABSTRACT FROM AUTHOR]

This paper presents a robust foreground detection method capable of adapting to different motion speeds in scenes. A key contribution of this paper is the background estimation using a proposed novel algorithm, neighbor-based intensity correction (NIC), that identifies and modifies the motion pixels from the difference of the background and the current frame. Concretely, the first frame is considered as an initial background that is updated with the pixel intensity from each new frame based on the examination of neighborhood pixels. These pixels are formed into windows generated from the background and the current frame to identify whether a pixel belongs to the background or the current frame. The intensity modification procedure is based on the comparison of the standard deviation values calculated from two pixel windows. The robustness of the current background is further measured using pixel steadiness as an additional condition for the updating process. Finally, the foreground is detected by the background subtraction scheme with an optimal threshold calculated by the Otsu method. This method is benchmarked on several well-known data sets in the object detection and tracking domain, such as CAVIAR 2004, AVSS 2007, PETS 2009, PETS 2014, and CDNET 2014. We also compare the accuracy of the proposed method with other state-of-the-art methods via standard quantitative metrics under different parameter configurations. In the experiments, NIC approach outperforms several advanced methods on depressing the detected foreground confusions due to light artifact, illumination change, and camera jitter in dynamic scenes. [ABSTRACT FROM PUBLISHER]

Depth estimation from a camera is an important task for 3D perception. Recently, without using the labeled ground truth of depth map, a self-supervised deep learning network can use relative pose to synthesize the target image from the reference image, and the photometric error between synthesized reference image and real one is used as self-supervisory signal. In this paper, we propose a novel self-supervised depth estimation network, which takes advantage of the quadtree constraint to optimize the depth estimation network. Based on the quadtree constraint, the photometric loss and depth loss of quadtree are proposed. In order to solve the problem that multiple depth values in repeated structures and uniform texture regions can cause relatively low photometric loss, we use quadtree-based photometric loss, which calculates the averaged photometric loss in quadtree blocks instead of the pixel-wise loss. For the problem of imbalanced depth distribution, we use quadtree depth loss, which constrains the depth inconsistency within quadtree blocks. The depth estimation network is composed of deep fusion module and cross-layer feature fusion module, which can better extract the feature information of RGB image and sparse keypoints depths, and makes full use of the detail information of the shallow feature map and the semantic information of the deep feature map to enrich the feature information extraction. Experimental results demonstrate that our method outperforms the state-of-the-art approaches of depth estimation. [ABSTRACT FROM AUTHOR]

High-resolution fingerprint recognition has been a hot topic for many years. Compared with a traditional fingerprint image, a high-resolution fingerprint image can provide more features, such as pores and ridge contours. Introducing these features into fingerprint comparison and recognition can improve the recognition accuracy and reduce the risk of identification errors. This paper proposes a novel method for comparing pores on high-resolution fingerprint images. The method can be divided into two steps. In the first step, fingerprints are aligned using the pixel-category-distance-based data-driven descending algorithm. Traditionally, fingerprints are aligned based on feature points, such as minutiae and singular points. Such alignment methods are not suitable when dealing with partial fingerprints because small overlapping areas often do not contain enough features to guarantee a correct alignment. In this research, the ridges and valleys on fingerprints are used in combination with the orientation field for alignment. The proposed algorithm performs well when aligning both partial and full fingerprints. The common areas between the two images can be estimated based on the alignment result. In the second step, pores lying in the common areas are selected for comparison. To improve the comparison accuracy, pores are compared using local features and spatial relations. A graph comparison algorithm is designed in this step. The experimental results show that the proposed method is more accurate than other state-of-the-art pore comparison algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a novel multidirectional weighted interpolation algorithm for color filter array interpolation. Our proposed method has two contributions to demosaicking. First, different from conventional interpolation methods based on two directions or four directions, the proposed method exploits to greater degree correlations among neighboring pixels along eight directions to improve the interpolation performance. Second, we propose an efficient postprocessing method to reduce interpolation artifacts based on the color difference planes. Compared with conventional state-of-the-art demosaicking algorithms, our experimental results show the proposed algorithm provides superior performance in both objective and subjective image quality. Furthermore, this implementation has moderate computational complexity. [ABSTRACT FROM PUBLISHER]

Visible light cameras commonly used for surveillance applications usually have a limited field of view (FoV). To acquire a broader FoV, distributed aperture systems (DASs) combine views from multiple cameras. Although some commercial or proprietary systems already exist, the open literature in this field reports solely the performance and/or hardware architecture of the respective systems, and omits the required details for a reimplementation. In this paper we present a low-cost, personal-computer-based 360° DAS, with a full description of the hardware architecture and the software implementation details. In particular, we describe in detail two problems, the offline estimation of the orientations of the cameras of the proposed DAS and the online synthesis of a virtual view in real time. For the first problem, we propose an area-based bundle adjuster by combining the forward additive Lucas–Kanade algorithm with a bundle adjustment strategy. The color virtual view of up to $2048\times 1024$ pixels is synthesized online at 39 frames/s. A large majority of the workload of the online phase is implemented on the graphic processing unit. The techniques and methods proposed in this paper are generic and independent on the arrangement of cameras. [ABSTRACT FROM PUBLISHER]

This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted by fence-like occlusions during capture. Our key observation lies in the visual parallax between fences and background scenes, which is caused by the fact that the former are typically closer to the camera. Unlike in traditional image inpainting, fence-occluded pixels in the videos tend to appear later in the temporal dimension and are therefore recoverable via optimized pixel selection from relevant frames. To eventually produce fence-free videos, major challenges include cross-frame subpixel image alignment under diverse scene depth, and correct pixel selection that is robust to dominating fence pixels. Several novel tools are developed in this paper, including soft fence detection, weighted truncated optical flow method, and robust temporal median filter. The proposed algorithm is validated on several real-world video clips with fences. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a novel method for 4D light-field (LF) depth estimation exploiting the special linear structure of an epipolar plane image (EPI) and locally linear embedding (LLE). Without high computational complexity, depth maps are locally estimated by locating the optimal slope of each line segmentation on the EPIs, which are projected by the corresponding scene points. For each pixel to be processed, we build and then minimize the matching cost that aggregates the intensity pixel value, gradient pixel value, spatial consistency, as well as reliability measure to select the optimal slope from a predefined set of directions. Next, a subangle estimation method is proposed to further refine the obtained optimal slope of each pixel. Furthermore, based on a local reliability measure, all the pixels are classified into reliable and unreliable pixels. For the unreliable pixels, LLE is employed to propagate the missing pixels by the reliable pixels based on the assumption of manifold preserving property maintained by natural images. We demonstrate the effectiveness of our approach on a number of synthetic LF examples and real-world LF data sets, and show that our experimental results can achieve higher performance than the typical and recent state-of-the-art LF stereo matching methods. [ABSTRACT FROM PUBLISHER]

This paper presents a statistical analysis of several key factors in H.264/AVC motion estimation, including the relationship between sum of absolute difference and sum of absolute transformed difference (SATD) in macroblock (MB) level, the changes of SATD from full-pixel precision to quarter-pixel precision, and so on. Based on these statistical characteristics, we proved the validity of a fractional motion estimation (FME) mode reduction criterion. During motion estimation, any MBs satisfying this criterion can keep their integer motion estimation best mode until after FME, thus avoiding many costly less probable prediction modes in the FME stage. Simulation results confirm that prediction schemes using this criterion have a very low miss rate in mode determination, FME speed-up is achieved and the peak signal-to-noise ratio drop is almost negligible. [ABSTRACT FROM PUBLISHER]

The autoregressive (AR) model has been widely used in signal processing for its effective estimation, especially in image processing. Many dedicated $2\times $ interpolation algorithms adopt the AR model to describe the strong correlation between low-resolution (LR) pixels and high-resolution (HR) pixels. However, these AR model-based methods closely depend on the fixed relative position between LR pixels and HR pixels that are nonexistent in the general scale interpolation. In this paper, we present an adaptive general scale interpolation algorithm that is capable of arbitrary scaling factors considering the nonstationarity of natural images. Different from other dedicated $2\times $ interpolation methods, the proposed AR terms are modeled by pixels with their adjacent unknown HR neighbors. To compensate for the information loss caused by mismatches of AR models, we consider a weighting scheme suitable for general scale situations based on the pixel similarity to increase accuracy of the estimation. Comprehensive experiments demonstrate the effectiveness of the proposed method on general scaling factors. The maximum gain of peak signal-to-noise ratio is 2.07 dB compared with segment adaptive gradient angle in $1.5 \times $ enlargements. To evaluate the performance in resolution adaptive video coding, we have also tested our method on Joint Scalable Video Model codec and obtained better subjective quality and rate-distortion performance. [ABSTRACT FROM PUBLISHER]

This paper presents a weighted least squares-based intrafield de-interlacing algorithm. First, we formulate the estimation of the missing pixels as a maximum a posteriori (MAP) framework. We deduce the weighted least squares structure from MAP based on the analysis of the statistic model of the original high-resolution images and the associated statistical model of the given low-resolution images and original high-resolution images. The weights affect the estimation of the statistical model. We also design adaptive weights to match regions with different properties. The method is compared with other de-interlacing algorithms in terms of PSNR and SSIM objective quality measures and de-interlacing speed. It was found to provide excellent performance and the best quality–speed tradeoff among the methods studied. [ABSTRACT FROM AUTHOR]

This paper proposes a novel multi-level frame interpolation scheme by exploiting the interactions among different levels. The proposed scheme includes three major stages that work at block level, pixel level, and sequence level, respectively. Effective algorithms are designed for each stage, i.e., block-level motion estimation with dropping unreliable motion vectors, pixel-level motion vector-guided partial scale-invariant feature transform flow matching, and sequence-level 3-D total variation regularized completion. Compared to traditional methods that focus mostly at one single level, the proposed scheme manages to recognize and utilize the interactions among the three levels based on their distinct characteristics and intertwined relationships. With a proper exploitation of interactions, unique advantages for each level can be effectively preserved while inherent limitations of a given level can be overcome by utilizing information from other levels. Extensive experiments have confirmed its superior performance over several classical schemes, in both subjective visual quality and objective peak signal-to-noise ratio/structure similarity measurements, and typical artifacts can be significantly reduced. [ABSTRACT FROM AUTHOR]

Video transmitted over an error-prone network may be received at the decoder with degradations due to packet losses. No-reference quality monitoring algorithms are the most practical way to measure the quality of the received video, since they do not impose any change with respect to the network architecture. Conventionally, these methods assume the availability of the corrupted bitstream. In some situations this is not possible, e.g., because the bitstream is encrypted or processed by third-party decoders, and only the decoded pixel values can be used. The major issue in this scenario is the lack of knowledge about which regions of the video have been actually lost, which is a fundamental ingredient for estimating channel-induced distortion. In this paper, we propose a maximum a posteriori estimation of the pattern of lost macroblocks, which assumes the knowledge of the decoded pixels only. This information can be used as input to a no-reference quality monitoring system, which produces an accurate estimate of the mean-square-error (MSE) distortion introduced by channel errors. The results of the proposed method are well correlated with the MSE distortion computed in full-reference mode, with a linear correlation coefficient equal to 0.9 at frame level and 0.98 at sequence level. [ABSTRACT FROM PUBLISHER]

In this paper, we develop a high-frame-rate (HFR) vision system that can estimate the optical flow in real time at 1000 f/s for 1024\,\times\,1024 pixel images via the hardware implementation of an improved optical flow detection algorithm on a high-speed vision platform. Based on the Lucas–Kanade method, we adopt an improved gradient-based algorithm that can adaptively select a pseudo-variable frame rate according to the amplitude of the estimated optical flow to accurately detect the optical flow for objects moving at high and low speeds in the same image. The performance of our developed HFR optical flow system was verified through experimental results for high-speed movements such as a top's spinnning motion and a human's pitching motion. [ABSTRACT FROM PUBLISHER]

Video stabilization is important in many application fields, such as visual surveillance. Video stabilization and completion based on a single camera have been well studied in recent years, but it remains a very challenging problem. In this paper, we propose a novel framework to produce a stable high-resolution video for visual surveillance by using two cameras, in which one static camera serves to capture low-resolution wide-view-angle images, and the other is a pan-tilt-zoom camera to capture high-resolution images. Different with using a single camera, the interesting target can be detected and tracked more effectively and much more high-resolution information can be utilized for the stabilization and completion by using two videos from two cameras. A three-step stabilization approach is designed to deal with the resolution's discrepancy between two synchro videos and a four-stage completion strategy is taken to utilize more high-resolution information. Experimental results show that the proposed algorithm has a satisfying performance. [ABSTRACT FROM AUTHOR]

Motion detection is the first essential process in the extraction of information regarding moving objects and makes use of stabilization in functional areas, such as tracking, classification, recognition, and so on. In this paper, we propose a novel and accurate approach to motion detection for the automatic video surveillance system. Our method achieves complete detection of moving objects by involving three significant proposed modules: a background modeling (BM) module, an alarm trigger (AT) module, and an object extraction (OE) module. For our proposed BM module, a unique two-phase background matching procedure is performed using rapid matching followed by accurate matching in order to produce optimum background pixels for the background model. Next, our proposed AT module eliminates the unnecessary examination of the entire background region, allowing the subsequent OE module to only process blocks containing moving objects. Finally, the OE module forms the binary object detection mask in order to achieve highly complete detection of moving objects. The detection results produced by our proposed (PRO) method were both qualitatively and quantitatively analyzed through visual inspection and for accuracy, along with comparisons to the results produced by other state-of-the-art methods. The analyses show that our PRO method has a substantially higher degree of efficacy, outperforming other methods by an F1 metric accuracy rate of up to 53.43%. [ABSTRACT FROM PUBLISHER]

Wyner–Ziv video coding (WZVC) is a newly emerged video coding scheme which compresses the input video frames with the side information (SI) frames only available at the decoder. WZVC exploits the statistics between the source frame and the SI frame at the decoder by utilizing their correlation information. This correlation information is important but also difficult to estimate due to the absence of the SI frame at the encoder, and the lack of the source frame at the decoder. In this paper, we focus on this problem and propose a novel transform-domain adaptive correlation estimation method called TRACE for WZVC. In TRACE, the correlation information is progressively learned during the decoding process of each frame. Within TRACE, we also propose a convex optimization based band-level correlation estimation method which is optimal in the sense of minimizing the theoretical bit rate. Experiments suggest that, when applied in motion compensated interpolation-based low complexity WZVC, TRACE yields competitive results against the state-of-the-art correlation estimation algorithms. More importantly, different from the existing coefficient-level correlation estimation algorithms, the proposed TRACE can be applied in many other WZVC schemes and can provide considerable gain over the popular band-level correlation estimation methods. [ABSTRACT FROM PUBLISHER]

A no-reference (NR) video quality assessment (VQA) method is presented for videos distorted by H.264/Advanced Video Coding (AVC) and MPEG-2. The assessment is performed without access to the bitstream. Instead, we analyze and estimate coefficients based on decoded pixels. The approach involves distinguishing between the two types of videos, estimating the level of quantization used in the I-frames, and exploiting this information to assess the video quality. To do this for H.264/AVC, the distribution of the discrete cosine transform-coefficients after intra-prediction and deblocking are modeled. To obtain VQA features for H.264/AVC, we propose a novel estimation method of the quantization in H.264/AVC videos without bitstream access, which can also be used for peak signal-to-noise ratio estimation. The results from the MPEG-2 and H.264/AVC analysis are mapped to a perceptual measure of video quality by support vector regression. For validation purposes, the proposed method was tested on two databases. In both cases, a good performance compared with state of the art full, reduced, and NR VQA algorithms was achieved. [ABSTRACT FROM PUBLISHER]

Deep convolutional neural networks (CNNs) have been successfully applied on no-reference image quality assessment (NR-IQA) with respect to human perception. Most of these methods deal with small image patches and use the average score of the test patches for predicting the whole image quality. We discovered that image patches from homogenous regions are unreliable for both neural network training and final image quality score estimation. In addition, image patches with complex structures have much higher chances of achieving better image quality prediction. Based on these findings, we enhanced the conventional CNN-based NR-IQA algorithm to avoid homogenous patches for the network training and quality score estimation. Moreover, we also use a variance-based weighting average to bias the final image quality score to the patches with complex structure. The experimental results show that this simple approach can achieve state-of-the-art performance compared with well-known NR-IQA algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we present a framework for real-time mosaicing from video sequences recorded from an uncalibrated pan tilt zoom camera based on multiframe registration. To this end, a new frame alignment algorithm, the direct local indirect global (DLIG), is presented. The key idea of the DLIG alignment is to divide the frame alignment problem into the problem of registering a set of spatially related image patches. The registration is iteratively computed by sequentially imposing a good local match and global spatial coherence. The patch registration is performed using a tracking algorithm, so a very efficient local matching can be achieved. We use the patch-based registration to obtain multiframe registration, using the mosaic coordinates to relate the current frame to patches from different frames that partially share the current field of view. Multiframe registration prevents the error accumulation problem, one of the most important problems in mosaicing. We also show how to embed a kernel tracking algorithm in order to obtain a precise and extremely efficient mosaicing algorithm. Finally, we perform a quantitative evaluation of our algorithm, including a comparison with other alignment approaches, and studying its performance against interlaced videos and illumination changes. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel algorithm for moving object detection and tracking. The proposed algorithm includes two schemes: one for spatio-temporal spatial segmentation and the other for temporal segmentation. A combination of these schemes is used to identify moving objects and to track them. A compound Markov random field (MRF) model is used as the prior image attribute model, which takes care of the spatial distribution of color, temporal color coherence and edge map in the temporal frames to obtain a spatio-temporal spatial segmentation. In this scheme, segmentation is considered as a pixel labeling problem and is solved using the maximum a posteriori probability (MAP) estimation technique. The MRF-MAP framework is computation intensive due to random initialization. To reduce this burden, we propose a change information based heuristic initialization technique. The scheme requires an initially segmented frame. For initial frame segmentation, compound MRF model is used to model attributes and MAP estimate is obtained by a hybrid algorithm [combination of both simulated annealing (SA) and iterative conditional mode (ICM)] that converges fast. For temporal segmentation, instead of using a gray level difference based change detection mask (CDM), we propose a CDM based on label difference of two frames. The proposed scheme resulted in less effect of silhouette. Further, a combination of both spatial and temporal segmentation process is used to detect the moving objects. Results of the proposed spatial segmentation approach are compared with those of JSEG method, and edgeless and edgebased approaches of segmentation. It is noticed that the proposed approach provides a better spatial segmentation compared to the other three methods. [ABSTRACT FROM AUTHOR]

For multiview video generation from 2-D video sequences, the most important stage is to efficiently synthesize the corresponding depth maps for all video frames. The depth map generation involving precise object segmentation and depth assignment requires intensive computation and human assistance which could be costly and possibly inconsistent. To achieve reliable depth map generation, an efficient depth map interpolation method from the existing pairs of keyframes and their corresponding depth maps at the both ends of video scene is presented. The proposed method contains forward/backward motion alignment, block-based updating, object-based updating, frame selection mechanism, and depth adjustment. Experimental results show that the proposed method can generate the depth maps successfully after objective and subjective evaluations. We believe that it could greatly help to achieve multiview video generation from 2-D video sequences effectively. [ABSTRACT FROM AUTHOR]

Estimating scene depth from a single image can be widely applied to understand 3D environments due to the easy access of the images captured by consumer-level cameras. Previous works exploit conditional random fields (CRFs) to estimate image depth, where neighboring pixels (superpixels) with similar appearances are constrained to share the same depth. However, the depth may vary significantly in the slanted surface, thus leading to severe estimation errors. In order to eliminate those errors, we propose a superpixel-based normal guided scale invariant deep convolutional field by encouraging the neighboring superpixels with similar appearance to lie on the same 3D plane of the scene. In doing so, a depth-normal multitask CNN is introduced to produce the superpixel-wise depth and surface normal predictions simultaneously. To correct the errors of the roughly estimated superpiexl-wise depth, we develop a normal guided scale invariant CRF (NGSI-CRF). NGSI-CRF consists of a scale invariant unary potential that is able to measure the relative depth between superpixels as well as the absolute depth of superpixels, and a normal guided pairwise potential that constrains spatial relationships between superpixels in accordance with the 3D layout of the scene. In other words, the normal guided pairwise potential is designed to smooth the depth prediction without deteriorating the 3D structure of the depth prediction. The superpixel-wise depth maps estimated by NGSI-CRF will be fed into a pixel-wise refinement module to produce a smooth fine-grained depth prediction. Furthermore, we derive a closed-form solution for the maximum a posteriori (MAP) inference of NGSI-CRF. Thus, our proposed network can be efficiently trained in an end-to-end manner. We conduct our experiments on various datasets, such as NYU-D2, KITTI, and Make 3D. As demonstrated in the experimental results, our method achieves superior performance in both indoor and outdoor scenes. [ABSTRACT FROM AUTHOR]

This letter proposes an efficient and robust background compensation method for pan-tilt-zoom cameras. The proposed method approximates the relation between consecutive images to a three-parameter similarity transformation, which is separable in horizontal and vertical axes, and extracts and matches 1-D features that are local minima and maxima of intensity projection profiles in each axis. These correspondences are used to estimate transformation parameters via an outlier rejection approach. Experimental results show that the proposed method is more robust with respect to blurring effects and moving object proportion while dramatically decreasing computational costs compared to previous methods. [ABSTRACT FROM PUBLISHER]

In just noticeable difference (JND) models, evaluation of contrast masking (CM) is a crucial step. More specifically, CM due to edge masking (EM) and texture masking (TM) needs to be distinguished due to the entropy masking property of the human visual system. However, TM is not estimated accurately in the existing JND models since they fail to distinguish TM from EM. In this letter, we propose an enhanced pixel domain JND model with a new algorithm for CM estimation. In our model, total-variation based image decomposition is used to decompose an image into structural image (i.e., cartoon like, piecewise smooth regions with sharp edges) and textural image for estimation of EM and TM, respectively. Compared with the existing models, the proposed one shows its advantages brought by the better EM and TM estimation. It has been also applied to noise shaping and visual distortion gauge, and favorable results are demonstrated by experiments on different images. [ABSTRACT FROM PUBLISHER]