Search

With the development of video and image processing technology, the field of video tampering forensics is facing enormous challenges. Specifically, as the fundamental basis of judicial forensics, passive forensics for object removal video forgery is particularly essential. To extract tampering traces in video more sufficiently, the author proposed a spatiotemporal trident network based on the spatial rich model (SRM) and 3D convolution (C3D), which provides three branches and can theoretically improve the detection and localization accuracy of tampered regions. Based on the spatiotemporal trident network, a temporal detector and a spatial locator were designed to detect and locate the tampered regions in the temporal and spatial domains of videos. For the temporal detector, 3D CNNs were employed in three branches as the encoders and a bidirectional long short-term memory (BiLSTM) as the decoder. For the spatial locator, a backbone network named C3D-ResNet12 was designed as the encoder of the three branches, and the region proposal networks (RPNs) were employed as the decoders in three branches. In addition, we optimized the loss functions of the above two algorithms based on focal loss and GIoU loss. The experimental results revealed the effectiveness of spatiotemporal detection and localization algorithms: for temporal forgery detection, the accuracy of the frame classification increased to 99+%; for spatial forgery localization, the successful localization rate of the tampered regions in forged frames reached 96+%, and the mean intersection over union of the located tampered regions and the real tampered regions reached 62+%. [ABSTRACT FROM AUTHOR]

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]

Detection of relative changes in circulating blood volume is important to guide resuscitation and manage a variety of medical conditions, including sepsis, trauma, dialysis, and congestive heart failure. Recent studies have shown that estimates of circulating blood volume can be obtained from the cross-sectional area of the internal jugular vein (IJV) from ultrasound images. However, accurate segmentation and tracking of the IJV in ultrasound imaging is a challenging task and is significantly influenced by a number of parameters, such as the image quality, shape, and temporal variation. In this paper, we propose a novel adaptive polar active contour (Ad-PAC) algorithm for the segmentation and tracking of the IJV in ultrasound videos. In the proposed algorithm, the parameters of the Ad-PAC algorithm are adapted based on the results of segmentation in previous frames. The Ad-PAC algorithm is applied to 65 ultrasound videos captured from 13 healthy subjects, with each video containing 450 frames. The results show that spatial and temporal adaptation of the energy function significantly improves segmentation performance when compared with the current state-of-the-art active contour algorithms. [ABSTRACT FROM AUTHOR]

Gesture recognition has raised wide attention in computer vision owing to its many applications. However, the task of video-based large-scale gesture recognition yet faces many challenges, since many gesture-irrelevant factors like the background may disturb the recognition accuracy. To better recognize gestures with large-scale videos, we propose a method based on RGB-D data in this paper, where the “RGB-D” means RGB and depth data captured simultaneously by specific devices like Kinect. To learn gesture details better, we first use an adaptive frame unification strategy to unify the frame number of inputs, and then the RGB and depth data are sent to the C3D model to extract spatiotemporal features, respectively. In order to alleviate the interference of gesture-irrelevant factors, the saliency theory is also employed to generate auxiliary data. Next the features of these data are combined to boost the performance, which can also avoid unreasonable synthetic data, since the dimension of C3D features is uniform. Finally the performances of several classifiers are tested and the best one of SVM classifier is selected to output the ultimate accuracy. Our approach achieves 52.04% and 59.43% accuracy on the validation and testing subset of the Chalearn LAP IsoGD, respectively, both of which outperform our results in the chalearn LAP Large-scale Gesture Recognition Challenge as reported in ICPR 2016. [ABSTRACT FROM AUTHOR]

Video-based person re-identification (re-id) has attracted a lot of research interest. When facing dramatic growth in new pedestrian videos, existing video-based person re-id methods usually need large quantities of labeled pedestrian videos to train a discriminative model. In practice, labeling large quantities of pedestrian videos is a costly and time-consuming task, which will limit the application of these methods in the real environment. Therefore, it is valuable and necessary to investigate how to learn a discriminative re-id model by using limited labeled training pedestrian videos. In this paper, we propose a semi-supervised cross-view projection-based dictionary learning (SCPDL) approach for video-based person re-id. Specifically, SCPDL jointly learns a pair of feature projection matrices and a pair of dictionaries by integrating the information contained in labeled and unlabeled pedestrian videos. With the learned feature projection matrices, the influence of variations within each video to the re-id can be reduced. With the learned dictionary pair, pedestrian videos from two different cameras can be converted into coding coefficients in a common representation space, such that the differences between different cameras can be bridged. In the learning process, the labeled pedestrian videos are used to ensure that the learned dictionaries have favorable discriminability; the large quantities of unlabeled pedestrian videos are used to ensure that SCPDL can better capture the variations between pedestrian videos, such that the learned dictionaries can own stronger representative capability. Experiments on two public pedestrian sequence data sets (iLIDS-VID and PRID 2011) demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of recognizing human actions from depth videos. We propose a depth-based local descriptor and affine subspace coding representation with locality-constrained affine subspace coding (LASC) for 3D action recognition. First, each depth video sequence is divided into a set of subsequences (i.e., multi-scale sub-actions) based on the normalized motion energy vector. Next, depth motion map-based gradient local auto-correlation features are employed to capture the shape information and motion cues of each sub-action. In order to obtain discriminative and compact representation, we extract the local high-order information of the depth video using LASC. Through experiments, we show that the use of LASC exhibits better performance compared with existing methods such as locality-constrained linear coding. We compared LASC with the state-of-the-art methods based on similar principle, using features extracted from a single modality, on four datasets, and with those using multiple features or nonlinear recognition machines. The results on four datasets clearly show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Detection of moving objects in videos is a crucial step toward successful surveillance and monitoring applications. A key component for such tasks is called background subtraction and tries to extract regions of interest from the image background for further processing or action. For this reason, its accuracy and real-time performance are of great significance. Although effective background subtraction methods have been proposed, only a few of them take into consideration the special characteristics of thermal imagery. In this paper, we propose a background subtraction scheme, which models the thermal responses of each pixel as a mixture of Gaussians with unknown number of components. Following a Bayesian approach, our method automatically estimates the mixture structure, while simultaneously it avoids over-/underfitting. The pixel density estimate is followed by an efficient and highly accurate updating mechanism, which permits our system to be automatically adapted to dynamically changing operation conditions. We propose a reference implementation of our method in reconfigurable hardware achieving both adequate performance and low-power consumption. Adopting a high-level synthesis design and demanding floating point arithmetic operations are mapped in reconfigurable hardware, demonstrating fast prototyping and on-field customization at the same time. [ABSTRACT FROM AUTHOR]

Existing unsupervised video object segmentation generates object information from the whole video, which ignores analysis of the local clips. However, we observe that local clips and their relationships are also useful for the video object segmentation. For example, the simple background clips can be used to improve the segmentation of complex background clips. In this paper, we propose a novel unsupervised segmentation framework to segment the primary object based on two aspects, i.e., the complexity awareness of video clips and their segmentation propagation. The first one is used to select the simple clips with smooth backgrounds and the second one generates an object prior from the simple clips and propagates the object prior to help and improve the segmentation of the complex clips. A complexity awareness method using the static cues and the dynamic cues are proposed to evaluate the complexity of the video frames. A new object prior learning model based on the local part structure is designed and a local part-based prior propagation is proposed for the complex clip segmentation. To verify our method, we collect a new challenging video segmentation data set, in which each video contains diverse backgrounds. Experimental results demonstrate that our method outperforms several state-of-the-art methods both on a classical data set and our new data set. [ABSTRACT FROM AUTHOR]

Recent digital acquisition systems can acquire high-resolution videos, generating a large amount of dynamic data and leading to higher computational cost in online target tracking and learning, especially for complex scenes. We introduce an efficient and robust approach to improve the performance of multi-object online tracking and learning. Prior methods saved on computational cost by scaling down each video frame to a fixed smaller resolution, without considering the image features. Our algorithm computes the optimal image resolution adaptively by exploiting the correlation between an image’s gray-value distribution and resolution. This dimensionality reduction step significantly improves the time performance in subsequent online tracking and learning, while preserving high tracking accuracy. Since a small detection error in one frame can cause cumulative error in the video sequence leading to incorrect labeling and tracking, we introduce a new tracklet reliability assessment metric to eliminate incorrect samples. Experimental results show that our approach can successfully track multiple objects in real time with both high precision and recall. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient real-time background subtraction algorithm, which is essential in many computer vision applications. Initially, histograms of the intensity values for each channel of a pixel position in a set of training framesare constructed. A background model, histogram min-max bucket, is constructed from the minimum and maximum values of contiguous non-zero frequencies of the temporal intensity histogram. A novel feature of this algorithm is the use of a single sliding window to update the system adaptively, capturing the proper background even under sudden and/or gradual illumination changes in the scene. We incorporate both local and global information with the help of the current and the previously visited pixel values for binary classification of a pixel into foreground and background. This algorithm is compared with several state-of-the-art techniques and experimental studies show that the proposed method outperforms all these methods in terms of accurate binary classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a nonlinear structural hashing approach to learn compact binary codes for scalable video search. Unlike most existing video hashing methods which consider image frames within a video separately for binary code learning, we develop a multi-layer neural network to learn compact and discriminative binary codes by exploiting both the structural information between different frames within a video and the nonlinear relationship between video samples. To be specific, we learn these binary codes under two different constraints at the output of our network: 1) the distance between the learned binary codes for frames within the same scene is minimized and 2) the distance between the learned binary matrices for a video pair with the same label is less than a threshold and that for a video pair with different labels is larger than a threshold. To better measure the structural information of the scenes from videos, we employ a subspace clustering method to cluster frames into different scenes. Moreover, we design multiple hierarchical nonlinear transformations to preserve the nonlinear relationship between videos. Experimental results on three video data sets show that our method outperforms state-of-the-art hashing approaches on the scalable video search task. [ABSTRACT FROM AUTHOR]

We present a new statistical approach combining temporal and spatial information for robust online background subtraction (BS) in videos. Temporal information is modeled by coupling finite mixtures of generalized Gaussian distributions with foreground/background co-occurrence analysis. Spatial information is modeled by combining multiscale inter-frame correlation analysis and histogram matching. We propose an online algorithm that efficiently fuses both information to cope with several BS challenges, such as cast shadows, illumination changes, and various complex background dynamics. In addition, global video information is used through a displacement measuring technique to deal with pan-tilt-zoom camera effects. Experiments with comparison with recent state-of-the-art methods have been conducted on standard data sets. Obtained results have shown that our approach surpasses several state-of-the-art methods on the aforementioned challenges while maintaining comparable computational time. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) is the theory and practice of sub-Nyquist sampling of sparse signals of interest. Exact reconstruction may then be possible with much fewer than the Nyquist-required number of data. In this paper, we consider a multiview video system in which multiple cameras at different locations perform independent CS to simultaneously capture different views of a scene. At the decoder, we propose a disparity- and motion-compensated total variation minimization algorithm to jointly reconstruct the multiview video sequence. The experimental results show that the proposed joint reconstruction algorithm successfully exploits simultaneously intra-frame, inter-frame, and inter-view sparsity and significantly outperforms existing independent-view reconstruction, residue-view reconstruction, and motion-adaptive reconstruction algorithms. [ABSTRACT FROM AUTHOR]

Moving object segmentation and classification from compressed video plays an important role in intelligent video surveillance. Compared with H.264/AVC, High Efficiency Video Coding (HEVC) introduces a host of new coding features that can be further exploited for moving object segmentation and classification. In this paper, we present a real-time approach to segment and classify moving objects using unique features directly extracted from the HEVC compressed domain for video surveillance. In the proposed method, first, motion vector (MV) interpolation for intra-coded prediction unit (PU) and MV outlier removal are employed for preprocessing. Second, blocks with nonzero MVs are clustered into the connected foreground regions using the four-connectivity component labeling algorithm. Third, object region tracking based on temporal consistency is applied to the connected foreground regions to remove the noise regions. The boundary of moving object region is further refined by the coding unit size and PU size. Finally, a person–vehicle classification model using bag of spatial–temporal HEVC syntax words is trained to classify the moving objects, either persons or vehicles. The experimental results demonstrate that the proposed method provides solid performance and can classify moving persons and vehicles accurately. [ABSTRACT FROM AUTHOR]

Background modeling constitutes the building block of many computer-vision tasks. Traditional schemes model the background as a low rank matrix with corrupted entries. These schemes operate in batch mode and do not scale well with the data size. Moreover, without enforcing spatiotemporal information in the low-rank component, and because of occlusions by foreground objects and redundancy in video data, the design of a background initialization method robust against outliers is very challenging. To overcome these limitations, this paper presents a spatiotemporal low-rank modeling method on dynamic video clips for estimating the robust background model. The proposed method encodes spatiotemporal constraints by regularizing spectral graphs. Initially, a motion-compensated binary matrix is generated using optical flow information to remove redundant data and to create a set of dynamic frames from the input video sequence. Then two graphs are constructed, one between frames for temporal consistency and the other between features for spatial consistency, to encode the local structure for continuously promoting the intrinsic behavior of the low-rank model against outliers. These two terms are then incorporated in the iterative Matrix Completion framework for improved segmentation of background. Rigorous evaluation on severely occluded and dynamic background sequences demonstrates the superior performance of the proposed method over state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

With the advance of coding and network technology, the multiview video (MVV) system has received growing attention in the 3-D TV market since it can provide consumers with more realistic scenes from different viewpoints. In the MVV system, each video sequence consists of one color-map video and one depth video to be encoded and the depth-image-based rendering technique is often used to create/synthesize virtual views for different viewpoints. To attain the same quality of virtual views, encoding depth videos in a fast and bitrate-saving manner is crucial. Based on the depth no-synthesis-error model developed by Zhao et al., this paper proposes a new intra-/inter-prediction scheme first and then a fast quadtree structure determination scheme for encoding depth videos in 3-D High Efficiency Video Coding (3D-HEVC). The first proposed scheme has bitrate-saving merit because for each coding unit, each depth value is modified to approach the predicted intra-/inter-depth value as closely as possible, but without causing any synthesis errors in the resultant virtual views. The second proposed scheme has the merit of low computational cost because it can terminate the quadtree structure determination for coding tree units as early as possible. Based on four typical test video sequences, the empirical results demonstrate that on average, our proposed encoding method for depth videos has 16.3% bitrate and 13.8% encoding-time improvement ratios when compared with the traditional method in 3D-HEVC test model, while preserving the quality of the rendered virtual views. In addition, our proposed method outperforms that of Lee et al. in terms of the required bitrate and encoding time. [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]

To save manufacturing cost, most color digital video cameras employ a single-sensor technology with a red–green–blue (RGB) color filter array (CFA) to capture real-world scenes. Due to only one primary color measured at each pixel location, the captured videos are usually referred to as the mosaic videos. For the purposes of economical storage and transmission, it is very important to achieve a good tradeoff between the quality and bitrate when compressing mosaic videos with different RGB-CFA structures. In this paper, based on mathematical optimization technique, a novel chroma subsampling strategy is presented for compressing mosaic videos with arbitrary RGB-CFA structures in H.264/AVC and High Efficiency Video Coding (HEVC). For each $2 \times 2$ YUV block to be subsampled with 4:2:0 format, the proposed strategy determines the proper sampled $U$ and $V$ components by minimizing, prior to compression, the quality distortion between the original colocated mosaic block and the mosaic block conversed from the current subsampled YUV block. Through the mathematical optimization formulated in the proposed strategy, the significance of the sampled $U$ and $V$ components for reconstructing R, G, and B pixels can be simultaneously taken into consideration. The experimental results demonstrate that the proposed chroma subsampling strategy has the best quality and bitrate tradeoff at a similar execution time requirement for compressing mosaic videos with arbitrary RGB-CFA structures in H.264/AVC and HEVC compared with the state-of-the-art ones by Chen et al. and Yang et al. as well as the three commonly used ones. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new method for detecting primary objects in unconstrained videos in a completely automatic setting. Here, we define the primary object in a video as the object that presents saliently in most of the frames. Unlike previous works considering only local saliency detection or common pattern discovery, the proposed method integrates the local visual/motion saliency extracted from each frame, global appearance consistency throughout the video, and spatiotemporal smoothness constraint on object trajectories. We first identify a temporal coherent salient region throughout the whole video, and then explicitly learn a global appearance model to distinguish the primary object against the background. In order to obtain high-quality saliency estimations from both appearance and motion cues, we propose a novel self-adaptive saliency map fusion method by learning the reliability of saliency maps from labeled data. As a whole, our method can robustly localize and track primary objects in diverse video content, and handle the challenges such as fast object and camera motion, large scale and appearance variation, background clutter, and pose deformation. Moreover, compared with some existing approaches that assume the object is present in all the frames, our approach can naturally handle the case where the object is present only in part of the frames, e.g., the object enters the scene in the middle of the video or leaves the scene before the video ends. We also propose a new video data set containing 51 videos for primary object detection with per-frame ground-truth labeling. Quantitative experiments on several challenging video data sets demonstrate the superiority of our method compared with the recent state of the arts. [ABSTRACT FROM PUBLISHER]

We describe a methodology that is designed to match key point and region-based features in real-world images, acquired from long-running security cameras with no control over the environment. We detect frame duplication and images from static scenes that have no activity to prevent processing saliently identical images, and describe a novel blur-sensitive feature detection method, a combinatorial feature descriptor, and a distance calculation that efficiently unites texture and color attributes to discriminate feature correspondence in low-quality images. Our methods are tested by performing key point matching on real-world security images such as outdoor closed-circuit television videos that are low quality and acquired in uncontrolled conditions with visual distortions caused by weather, crowded scenes, emergency lighting, or the high angle of the camera mounting. We demonstrate an improvement in accuracy of matching key points between images compared with state-of-the-art feature descriptors. We use key point features from a Harris corner detector, scale-invariant feature transform, speeded-up robust features, binary robust invariant scalable keypoints, and features from accelerated segment test as well as MSER and MSCR region detectors to provide a comprehensive analysis of our generic method. We demonstrate feature matching using a 138D descriptor that improves the matching performance of a state-of-the-art 384D color descriptor with just 36% of the storage requirements. [ABSTRACT FROM PUBLISHER]

It is known that the human visual system (HVS) employs independent processes (distortion detection and artifact perception—also often referred to as near-threshold and suprathreshold distortion perception) to assess video quality for various distortion levels. Visual masking effects also play an important role in video distortion perception, especially within spatial and temporal textures. In this paper, a novel perception-based hybrid model for video quality assessment is presented. This simulates the HVS perception process by adaptively combining noticeable distortion and blurring artifacts using an enhanced nonlinear model. Noticeable distortion is defined by thresholding absolute differences using spatial and temporal tolerance maps that characterize texture masking effects, and this makes a significant contribution to quality assessment when the quality of the distorted video is similar to that of the original video. Characterization of blurring artifacts, estimated by computing high frequency energy variations and weighted with motion speed, is found to further improve metric performance. This is especially true for low quality cases. All stages of our model exploit the orientation selectivity and shift invariance properties of the dual-tree complex wavelet transform. This not only helps to improve the performance but also offers the potential for new low complexity in-loop application. Our approach is evaluated on both the Video Quality Experts Group (VQEG) full reference television Phase I and the Laboratory for Image and Video Engineering (LIVE) video databases. The resulting overall performance is superior to the existing metrics, exhibiting statistically better or equivalent performance with significantly lower complexity. [ABSTRACT FROM PUBLISHER]

In this paper, we propose an efficient general-purpose no-reference (NR) video quality assessment (VQA) framework that is based on 3D shearlet transform and convolutional neural network (CNN). Taking video blocks as input, simple and efficient primary spatiotemporal features are extracted by 3D shearlet transform, which are capable of capturing natural scene statistics properties. Then, CNN and logistic regression are concatenated to exaggerate the discriminative parts of the primary features and predict a perceptual quality score. The resulting algorithm, which we name shearlet- and CNN-based NR VQA (SACONVA), is tested on well-known VQA databases of Laboratory for Image & Video Engineering, Image & Video Processing Laboratory, and CSIQ. The testing results have demonstrated that SACONVA performs well in predicting video quality and is competitive with current state-of-the-art full-reference VQA methods and general-purpose NR-VQA algorithms. Besides, SACONVA is extended to classify different video distortion types in these three databases and achieves excellent classification accuracy. In addition, we also demonstrate that SACONVA can be directly applied in real applications such as blind video denoising. [ABSTRACT FROM PUBLISHER]

Supervoxels have been widely used as a preprocessing step to exploit object boundaries to improve the performance of video processing tasks. However, most of the traditional supervoxel algorithms do not perform well in regions with complex textures or weak boundaries. These methods may generate supervoxels with overlapping boundaries. In this paper, we present the novel video supervoxel generation algorithm using partially absorbing random walks to get more accurate supervoxels in these regions. Our spatial–temporal framework is introduced by making full use of the appearance and motion cues, which effectively exploits the temporal consistency in video sequence. Moreover, we build a novel Laplacian optimization structure using two adjacent frames to make our approach more efficient. Experimental results demonstrated that our method achieved better performance than the state-of-the-art supervoxel algorithms. [ABSTRACT FROM PUBLISHER]

Human action can be recognized from a single still image by modeling human–object interactions (HOIs), which infers the mutual spatial structure information between human and the manipulated object as well as their appearance. Existing approaches rely heavily on accurate detection of human and object and estimation of human pose; they are thus sensitive to large variations of human poses, occlusion, and unsatisfactory detection of small size objects. To overcome this limitation, a novel exemplar-based approach is proposed in this paper. Our approach learns a set of spatial pose–object interaction exemplars, which are probabilistic density functions describing spatially how a person is interacting with a manipulated object for different activities. Specifically, a new framework consisting of an exemplar-based HOI descriptor and an associated matching model is formulated for robust human action recognition in still images. In addition, the framework is extended to perform HOI recognition in videos, where the proposed exemplar representation is used for implicit frame selection to negate irrelevant or noisy frames by temporal structured HOI modeling. Extensive experiments are carried out on two image action datasets and two video action datasets. The results demonstrate the effectiveness of our proposed methods and show that our approach is able to achieve state-of-the-art performance, compared with several recently proposed competitors. [ABSTRACT FROM PUBLISHER]

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]

Recently, most background modeling approaches represent distributions of background changes by using parametric models such as Gaussian mixture models. Because of significant illumination changes and dynamic moving backgrounds with time, variations of background changes are hard to be modeled by parametric background models. Moreover, how to efficiently and effectively update parameters of parametric models to reflect background changes remains a problem. In this paper, we propose a novel coarse-to-fine detection theory algorithm to extract foreground objects on the basis of nonparametric background and foreground models represented by binary descriptors. We update background and foreground models by a first-in–first-out strategy to maintain the most recent observed background and foreground instances. As shown in the experiments, our method can achieve better foreground extraction results and fewer false alarms of surveillance videos with lighting changes and dynamic backgrounds in both collected and CDnet 2012 benchmark data sets. [ABSTRACT FROM AUTHOR]

We present a framework for multitarget detection and tracking that infers candidate target locations in videos containing a high density of homogeneous targets. We propose a gradient-climbing technique and an isocontor slicing approach for intensity maps to localize targets. The former uses Markov chain Monte Carlo to iteratively fit a shape model onto the target locations, whereas the latter uses the intensity values at different levels to find consistent object shapes. We generate trajectories by recursively associating detections with a hierarchical graph-based tracker on temporal windows. The solution to the graph is obtained with a greedy algorithm that accounts for false-positive associations. The edges of the graph are weighted with a likelihood function based on location information. We evaluate the performance of the proposed framework on challenging datasets containing videos with high density of targets and compare it with six alternative trackers. [ABSTRACT FROM AUTHOR]

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]

Automatic detection of salient objects in visual media (e.g., videos and images) has been attracting much attention. The detected salient objects can be utilized for segmentation, recognition, and retrieval. However, the accuracy of saliency detection remains a challenge. The reason behind this challenge is mainly due to the lack of a well-defined model for interpreting saliency formulation. To tackle this problem, this letter proposes to detect salient objects based on selective contrast. Selective contrast intrinsically explores the most distinguishable component information in color, texture, and location. A large number of experiments are thereafter carried out upon a benchmark dataset, and the results are compared with those of 12 other popular state-of-the-art algorithms. In addition, the advantage of the proposed algorithm is also demonstrated in a retargeting application. [ABSTRACT FROM AUTHOR]

We propose a content-based 3-D mosaic (CB3M) representation for long video sequences of 3-D and dynamic urban scenes captured by a camera on a mobile platform. In the first phase, a set of parallel-perspective (pushbroom) mosaics with varying viewing directions is generated to capture both the 3-D and dynamic aspects of the scene under the camera coverage. In the second phase, a segmentation-based stereo matching algorithm is applied to extract parametric representations of the color, structure and motion of the dynamic and/or 3-D objects in urban scenes, where a lot of planar surfaces exist. Multiple pairs of stereo mosaics are used for facilitating reliable stereo matching, occlusion handling, accurate 3-D reconstruction, and robust moving target detection. CB3M is a highly compressed visual representation for a dynamic 3-D scene, and has object contents of both 3-D and motion information. Experimental results are given for various real video sequences of large-scale 3-D scenes. [ABSTRACT FROM PUBLISHER]

The research context of this paper is dynamic texture analysis and characterization. Many dynamic textures can be modeled as large scale propagating wavefronts and local oscillating phenomena. After introducing a formal model for dynamic textures, the morphological component analysis (MCA) approach with a well-chosen dictionary is used to retrieve the components of dynamic textures. We define two new strategies for adaptive thresholding in the MCA framework, which greatly reduce the computation time when applied on videos. Tests on real image sequences illustrate the efficiency of the proposed method. An application to global motion estimation is proposed and future prospects are finally exposed. [ABSTRACT FROM PUBLISHER]

This paper presents a novel method for detecting salient regions in both images and videos based on a discriminant center-surround hypothesis that the salient region stands out from its surroundings. To this end, our spatiotemporal approach combines the spatial saliency by computing distances between ordinal signatures of edge and color orientations obtained from the center and the surrounding regions and the temporal saliency by simply computing the sum of absolute difference between temporal gradients of the center and the surrounding regions. Our proposed method is computationally efficient, reliable, and simple to implement and thus it can be easily extended to various applications such as image retargeting and moving object extraction. The proposed method has been extensively tested and the results show that the proposed scheme is effective in detecting saliency compared to various state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

We revisit the classic problem of developing a spatial correlation model for natural images and videos by proposing a conditional correlation model for relatively nearby pixels that is dependent upon five parameters. The conditioning is on local texture and the optimal parameters can be calculated for a specific image or video with a mean absolute error usually smaller than 5%. We use this conditional correlation model to calculate the conditional rate distortion function when universal side information on local texture is available at both the encoder and the decoder. We demonstrate that this side information, when available, can save as much as 1 bit per pixel for selected videos at low distortions. We further study the scenario when the video frame is processed in macroblocks (MBs) or smaller blocks and calculate the rate distortion bound when the texture information is coded losslessly and optimal predictive coding is utilized to partially incorporate the correlation between the neighboring MBs or blocks. These rate distortion bounds are compared to the operational rate distortion functions generated in intra-frame coding using the H.264/AVC video coding standard. [ABSTRACT FROM AUTHOR]

Image inpainting or image completion is the technique that automatically restores/completes removed areas in an image. When dealing with a similar problem in video, not only should a robust tracking algorithm be used, but the temporal continuity among video frames also needs to be taken into account, especially when the video has camera motions such as zooming and tilting. In this paper, we extend an exemplar-based image inpainting algorithm by incorporating an improved patch matching strategy for video inpainting. In our proposed algorithm, different motion segments with different temporal continuity call for different candidate patches, which are used to inpaint holes after a selected video object is tracked and removed. The proposed new video inpainting algorithm produces very few "ghost shadows," which were produced by most image inpainting algorithms directly applied on video. Our experiments use different types of videos, including cartoon, video from games, and video from digital camera with different camera motions. Our demonstration at http://member.mine.tku.edu.tw/www/T_CSVT/web/shows the promising results. [ABSTRACT FROM AUTHOR]

As adoption of the newly standardized H.264 becomes increasingly more widespread, efforts must be made to transcode video from earlier standards, such as MPEG-2, to the H.264 format. One aspect of transcoding is the conversion from the discrete cosine transform (DCT) used in MPEG-2 to the integer-based DCT of H.264, the integer cosine transform. By investigating the structure of the transform kernels, two efficient schemes are introduced to convert an 8 × 8 DCT block into its corresponding four 4 × 4 integer cosine transform blocks. An analysis of computational complexity shows a reduction of up to 42% in multiplications over existing conversion schemes, while simulations of the conversion system with pre- and post-quantization show that the proposed methods yield high fidelity in terms of peak signal-to-noise ratio. Further approximation of matrix coefficients in the second proposed method yields additional conversion schemes which require no multiplications. These also provide comparable quality with fewer operations than existing schemes. Thus, the proposed transform conversion methods can potentially contribute to efficient transcoding systems. [ABSTRACT FROM AUTHOR]

Shape masks are used in object-based video coding, such as MPEG-4 part 2, to specify the boundaries of a video object. The term "binary shape" is used to describe shape masks where each pixel is either completely inside the object or completely out- side it, i.e., there is no blending of pixels at object boundaries. In this paper, we present a new lossless block-based coding algorithm for binary shapes that combines a quad-tree structure with con- text-based arithmetic coding. Experimental results demonstrate that this new approach provides a saving in bits generated up to approximately 66% compared to the MPEG-4 binary shape coding algorithm. [ABSTRACT FROM AUTHOR]

In this paper, an operationally optimal joint shape and texture coding algorithm is proposed that uses shape-adaptive texture coding as well as texture-aware shape coding. The solution is optimal in the operational rate distortion sense, i.e, given the coding setup, the solution will guarantee the smallest possible distortion for a given rate. The shape is approximated using polygons or higher order curves. We also consider biasing the cost function to favor horizontal and vertical edges for the case of polygon approximation (biased polygon approximation). The texture is encoded using shape-adaptive discrete cosine transform or shape- adaptive discrete wavelet transform of the MPEG-4 video codec. A comparison is drawn between the two techniques. Both a fixed- width and a variable-width tolerance band for shape coding are considered. The variable width of the tolerance band is a function of the texture profile, i.e, the width is inversely proportional to the magnitude of the image gradient. Experimental results are presented and conclusions are drawn. [ABSTRACT FROM AUTHOR]

This paper deals with coding of natural scenes in order to extract semantic information. We present a new scheme to project natural scenes onto a basis in which each dimension encodes statistically independent information. Basis extraction is performed by independent component analysis (ICA) applied to image patches culled from natural scenes. The study of the resulting coding units (coding filters) extracted from well-chosen categories of images shows that they adapt and respond selectively to discriminant features in natural scenes. Given this basis, we define global and local image signatures relying on the maximal activity of filters on the input image. Locally, the construction of the signature takes into account the spatial distribution of the maximal responses within the image. We propose a criterion to reduce the size of the space of representation for faster computation. The proposed approach is tested in the context of texture classification (111 classes), as well as natural scenes classification (11 categories, 2037 images). Using a common protocol, the other commonly used descriptors have at most 47.7% accuracy on average while our method obtains performances of up to 63.8%. We show that this advantage does not depend on the size of the signature and demonstrate the efficiency of the proposed criterion to select ICA filters and reduce the dimension. [ABSTRACT FROM AUTHOR]

A new motion vector composition scheme, which we call spatial dominant vector selection (SDVS), for arbitrary down-sampling of precoded video using cascaded pixel domain transcoder is presented. The SDVS uses the existing relationship between pixels of a frame and its reference frame(s) via motion vectors and selects a dominant motion vector from a set of candidate vectors to minimize prediction errors. Compared with the existing methods, experimental results show performance gain, in terms of both quality and bit rate, with reduced computation. We also propose a refinement method that adaptively adjusts the search range to further improve the performance at marginal cost. [ABSTRACT FROM AUTHOR]

We investigate image and video convolutions based on Fermat number transform (FNT) modulo q = 2M + 1 where M is an integer power of two. These transforms are found to be ideal for image convolutions, except that the choices for the word length, restricted by the transform modulus, are rather limited. We discuss two methods to overcome this limitation. First, we allow M to be an arbitrary integer. This gives much wider variety in possible moduli, at the cost of decreased transform length of 16 or 32 points for M < 32. Nevertheless, the transform length appears still to be useful especially with block-based image and video filtering applications. We call these transforms the generalized FNT (GFNT). The second solution is to use a residue number system (RNS) to enlarge the effective modulus, while performing actual number theoretic transforms with smaller moduli. This approach appears to be particularly useful with moduli q1 = 216+1 and q2 = 28+ 1, which allow transforms up to 256 points with a dynamic range of about 24 bits. We design an efficient reconstruction circuit based on mixed radix conversion for converting the result from diminished-1 RNS into normal binary code. The circuit is implemented in VHDL and found to be very small in area. We also discuss the necessary steps in performing convolutions with the GFNT and evaluate the integrated circuit implementation cost for various elementary operations. [ABSTRACT FROM AUTHOR]

This paper presents a novel rate-distortion (R-D) model for rate control of video coding. First, we investigate the well-known heat conduction equation (HCE) in the heat conduction process for a thin bar. HCE describes the dynamic distribution of temperature in a thin bar using a partial differential equation (PDE). Motivated by the heat conduction process in a thin bar, a new rate transmission equation (RTE) is proposed to describe the dynamic behaviors of the bit-rate fluctuation during video coding. Second, a particular solution of RTE is employed as our proposed R-D model, which consists of two variables, i.e., the distortion D and the source statistical character M. Based on our model, a corresponding rate-control scheme is proposed for MPEG coding. Finally, extensive experimental results are reported to show that, compared with the well-known MPEG-4 Q2 rate-control scheme, our proposed work achieves better buffer status, higher control accuracy, and stabler and more consistent picture quality. [ABSTRACT FROM AUTHOR]

Foveation is one of the nonuniform resolution properties of the human visual system. Recently, different foveation models are proposed and utilized for image and video coding, for the sake of bit-rate saving with no or minor perceptual quality distortion. In the first part of this paper, we propose an efficient and practical DCT-domain foveation model, which is deduced from existing experimental results. In the second part, we present a foveation-based rate-shaping mechanism for MPEG bitstreams, as an application example of the proposed foveation model. The rate shaper is based on eliminating DCT coefficients embedded in MPEG bitstreams. An efficient rate-shaping mechanism is developed to meet various bit-rate requirements. Our simulation confirmed that the proposed foveation model and the rate-shaping mechanism are practical for real-world usage. [ABSTRACT FROM AUTHOR]

Examines the use of robust scene-change detection method for video segmentation. Consideration of intensity and motion information to detect scene changes; Development of novel intensity statistics model; Segmentation of video sequence into shots.

Describes a semi-automatic approach for segmenting a video sequence into spatio-temporal video objects in the presence of occlusion. Object tracking; Object-based video; Two-dimensional mesh presentation of motion and shape of each video object; Automatic detection of covered and uncovered regions at each frame.

Features a precise error-tracking scheme for robust transmission of real-time H.263 video. Feedback channel; Error concealment; Error propagation; Video coding; Video quality improvements in error-prone environments; Advantages of the low memory requirement and the low computation complexity.

Examines a technique which consisted of segmentation and temporal tracking, for unsupervised video segmentation in image processing. Details on the initial segmentation; Information on an algorithm for spatial segmentation; Analysis of motion-based region merging.

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]