Search

With the increase in the number of communication networks and digital multimedia technologies, ensuring the confidentiality of information has become increasingly important. Digital watermarking and scrambling are two methods that can be used to provide security to digital data such as video and to limit the chances of piracy. By implementing these techniques, it becomes more difficult for unauthorized users to access or distribute the video content, thereby protecting the integrity of the video data. This paper presents a novel approach to video watermarking, where a watermark bit is inserted into the motion vectors obtained through motion estimation. This is done to ensure copyright protection for the video content. In the proposed architecture, the negative horizontal components of the motion vectors generated by the three step search (TSS) algorithm are used, followed by a perturbation of the motion vectors (MVs). The perturbation helps to increase the security of the watermark and prevent it from being easily detected or removed. The experimental results of the proposed architecture have shown that it uses few resources, thereby making it a practical and efficient solution for video watermarking. Overall, the proposed architecture provides a better quality watermarked image sequence, operating with low power consumption that does not exceed 1.39 W and a maximum frequency of approximately 75.7 MHz. [ABSTRACT FROM AUTHOR]

Most of the existing research on video watermarking schemes focus on improving the robustness of watermarking. However, in application scenarios such as judicial forensics and telemedicine, the distortion caused by watermark embedding on the original video is unacceptable. To solve this problem, this paper proposes a robust reversible watermarking (RRW)scheme based on multi-layer embedding in the video compression domain. Firstly, the watermarking data are divided into several sub-secrets by using Shamir's (t, n)-threshold secret sharing. After that, the chroma sub-block with more complex texture information is filtered out in the I-frame of each group of pictures (GOP), and the sub-secret is embedded in that frame by modifying the discrete cosine transform (DCT) coefficients within the sub-block. Finally, the auxiliary information required to recover the coefficients is embedded into the motion vector of the P-frame of each GOP by a reversible steganography algorithm. In the absence of an attack, the receiver can recover the DCT coefficients by extracting the auxiliary information in the vectors, ultimately recovering the video correctly. The watermarking scheme demonstrates strong robustness even when it suffers from malicious attacks such as recompression attacks and requantization attacks. The experimental results demonstrate that the watermarking scheme proposed in this paper exhibits reversibility and high visual quality. Moreover, the scheme surpasses other comparable methods in the robustness test session. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In multimedia correspondence, steganography schemes are commonly applied. To reduce storage capacity, multimedia files, including images, are always compressed. Most steganographic video schemes are, therefore, not compression tolerant. In the frame sequences, the video includes extra hidden space. Artificial intelligence (AI) creates a digital world of real-time information for athletes, sponsors, and broadcasters. AI is reshaping business, and although it has already produced a significant impact on other sectors, the sports industry is the newest and most receptive one. Human-centered AI for web applications has substantially influenced audience participation, strategic plan execution, and other aspects of the sports industry that have traditionally relied heavily on statistics. Thus, this study presents the motion vector steganography of sports training video integrating with the artificial bee colony algorithm (MVS-ABC). The motion vector stenography detects the hidden information from the motion vectors in the sports training video bitstreams. Artificial bee colony (ABC) algorithm optimizes the block assignment to inject a hidden message into a host video, in which the block assignment is considered a combinatorial optimization problem. The experimental analysis evaluates the data embedding performance using steganographic technology compared with existing embedding technologies, using the ABC algorithm compared with other genetic algorithms. The findings show that the proposed model can give the highest performance in terms of embedding capacity and the least error rate of video steganography compared with the existing models.

Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick two). Current attempts to exploit temporal information in video data to overcome this trilemma are bottlenecked by the state of the art in object detection models. This work presents motion vector extrapolation (MOVEX), a technique which performs video object detection through the use of off-the-shelf object detectors alongside existing optical flow-based motion estimation techniques in parallel. This work demonstrates that this approach significantly reduces the baseline latency of any given object detector without sacrificing accuracy performance. Further latency reductions up to 24 times lower than the original latency can be achieved with minimal accuracy loss. MOVEX enables low-latency video object detection on common CPU-based systems, thus allowing for high-performance video object detection beyond the domain of GPU computing. [ABSTRACT FROM AUTHOR]

The motion of the camera in a video effectively conveys to the viewers the intention of the director, and is an essential element that enhances their interest. Therefore, detecting the motion of the camera is a very important factor in movie analysis. Existing research to detect the motion of the camera in a video has mainly focused on pan, tilt, and zoom. However, movies use more diverse camera motions to represent complex and varied emotions. Recognizing only pan, tilt, and zoom in a movie has limitations, especially not being able to detect lateral and longitudinal movements of the camera. In this study, a method is proposed to additionally detect boom and truck as well as pan, tilt, and zoom by using deep learning technology to improve this recognition ability. Thus, this study proposes the Improved Extractor of Camera Motion along with the CNN-Based Detector. The Improved Extractor of Camera Motion uses optical flow to extract camera motion vectors from video at eight-frame intervals. The CNN-Based Detector identifies five camera motions by using ResNet-152. As a result, the performance of our proposed method shows accuracy of 86.2%. [ABSTRACT FROM AUTHOR]

Multi-view video (MVV) data processed by three-dimensional (3D) video systems often suffer from compression artifacts, which can degrade the rendering quality of 3D spaces. In this paper, we focus on the task of artifact reduction in multi-view video compression using spatial and temporal motion priors. Previous MVV quality enhancement networks using a warping-and-fusion approach employed reference-to-target motion priors to exploit inter-view and temporal correlation among MVV frames. However, these motion priors were sensitive to quantization noise, and the warping accuracy was degraded, when the target frame used low-quality features in the corresponding search. To overcome these limitations, we propose a novel approach that utilizes bilateral spatial and temporal motion priors, leveraging the geometry relations of a structured MVV camera system, to exploit motion coherency. Our method involves a multi-view prior generation module that produces both unidirectional and bilateral warping vectors to exploit rich features in adjacent reference MVV frames and generate robust warping features. These features are further refined to account for unreliable alignments cross MVV frames caused by occlusions. The performance of the proposed method is evaluated in comparison with state-of-the-art MVV quality enhancement networks. Synthetic MVV dataset facilitates to train our network that produces various motion priors. Experimental results demonstrate that the proposed method significantly improves the quality of the reconstructed MVV frames in recent video coding standards such as the multi-view extension of High Efficiency Video Coding and the MPEG immersive video standard.

This paper proposes a sign language recognition system based on machine learning, which can infer the meaning of body movement in realtime video. It has a feature that motion vectors constructed with keypoint data of moving body are used for machine learning. This enables the proposed system to reduce the training time of an artificial neural network model and to enhance the recognition accuracy. Since those motion vectors have the same size and format regardless of the different expression times of words, the confidence level of an inference could be further increased. To correctly divide a part of video corresponding to each word in a sentence, we propose an iterative evaluation method of confidence levels for inferences with the gradual length adjustment of video fragment. The experimental results showed that our system outperforms a conventional method using the video itself for training and inference, in training time, inference speed, confidence level of inference and accuracy of video fragmentation. [ABSTRACT FROM AUTHOR]

A tremendous amount of image and video data are being generated and shared in our daily lives. Image and video data are typically stored and transmitted in compressed form in order to reduce storage space and transmission time. The processing and analysis of compressed image and video data can greatly reduce input data size and eliminate the need for decompression and recompression, thereby achieving significant savings in memory and computation time. There exists a body of research on compression domain data processing and analysis. This survey focuses on the work related to image and video data. The papers cited are categorized based on their target applications, including image and video resizing and retrieval, information hiding and watermark embedding, image and video enhancement and segmentation, object and motion detection, as well as pattern classification, among several other applications. Key methods used for these applications are explained and discussed. Comparisons are drawn among similar approaches. We then point out possible directions of further research. [ABSTRACT FROM AUTHOR]

As the opponent of motion vector (MV)-based video steganography, the corresponding symmetric steganalysis has also developed a lot in recent years, among which the logic-based steganalytic schemes, e.g., AoSO, NPELO and MVC, are the most prevailing. Although currently achieving the best detection performance, these steganalytic schemes are less effective in detecting some logic-maintaining steganographic schemes. In view of the fact that the distributions of covers' local Lagrangian cost quotients are normally more concentrated in the small value ranges than those of stegos and "spread" to the large values ranges after modifying the motion vector, the local Lagrangian cost quotient would thus be an efficient indicator to reflect the difference between cover videos and stego ones. In this regard, combining the logic-based (Lg) and local Lagrangian cost quotient (LLCQ)-based feature, we finally proposed a more effective and general steganalysis feature, i.e., Lg-LLCQ, which is composed of diverse subfeatures and performs much better than the corresponding single-type feature. Extensive experimental results show that the proposed method exhibits detection performance superior to other state-of-the-art schemes and even works well under cover sources and steganographic scheme mismatch scenes, which indicates our proposed feature is more conducive to real-world applications. [ABSTRACT FROM AUTHOR]

Video compression technology for Ultra-High Definition (UHD) and 8K UHD video has been established and is being widely adopted by major broadcasting companies and video content providers, allowing them to produce high-quality videos that meet the demands of today's consumers. However, high-resolution video content broadcasting is not an easy problem to be resolved in the near future due to limited resources in network bandwidth and data storage. An alternative solution to overcome the challenges of broadcasting high-resolution video content is to downsample UHD or 8K video at the transmission side using existing infrastructure, and then utilizing Video Super-Resolution (VSR) technology at the receiving end to recover the original quality of the video content. Current deep learning-based methods for Video Super-Resolution (VSR) fail to consider the fact that the delivered video to viewers goes through a compression and decompression process, which can introduce additional distortion and loss of information. Therefore, it is crucial to develop VSR methods that are specifically designed to work with the compression–decompression pipeline. In general, various information in the compressed video is not utilized enough to realize the VSR model. This research proposes a highly efficient VSR network making use of data from decompressed video such as frame type, Group of Pictures (GOP), macroblock type and motion vector. The proposed Convolutional Neural Network (CNN)-based lightweight VSR model is suitable for real-time video services. The performance of the model is extensively evaluated through a series of experiments, demonstrating its effectiveness and applicability in practical scenarios. [ABSTRACT FROM AUTHOR]

Aiming at the weak correlation between video steganography algorithm based on histogram translation and video content, this paper proposed a multiple histogram modification H. 264 video steganography algorithm based on motion vector. The algorithm designs correction parameters by counting the speed characteristics of macroblock movement and the sensitivity of dispersion to human vision in a specific frame, then designs multiple two-dimensional histograms according to the correction parameters, and finally embeds information in a non-specific frame through the two-dimensional histogram modification algorithm. The experimental results show that compared with the same type of video steganography algorithm, the embedding capacity is increased by 8.2% on average. When fully embedded, the change values of PSNR and SSIM of the algorithm are reduced by 19.9% and 17.5% respectively. The algorithm has better embedding capacity and imperceptibility while maintaining a low bit rate change. [ABSTRACT FROM AUTHOR]

Aiming at the problem of visual quality after video decoding effected by the existing video data hiding algorithms based on motion vector, a reversible data hiding algorithm based on motion vector ordering was proposed. The algorithm divides the motion vectors into several groups, arranges the motion vectors in each group in ascending order, embeds secret data in the difference between the maximum (minimum) value and the second maximum (minimum) value, which realizes lossless recovery of motion vectors at the decoding end. Experimental results showed that the proposed algorithm had a good visual quality. Compared with the same type of data hiding algorithm, the change value of peak signal-to-noise ratio and structural similarity index of this algorithm was reduced by 59. 36% and 41. 38% on average. [ABSTRACT FROM AUTHOR]

DASH is a popular technology for video streaming over the Internet. However, the quality of experience (QoE), a measure of humans’ perceived satisfaction of the quality of these streamed videos, is their subjective opinion, which is difficult to evaluate. Previous studies only considered network-based indices and focused on them to provide smooth video playback instead of improving the true QoE experienced by humans. In this study, we designed a series of click density experiments to verify whether different resolutions could affect the QoE for different video scenes. We observed that, in a single video segment, different scenes with the same resolution could affect the viewer’s QoE differently. It is true that the user’s satisfaction as a result of watching high-resolution video segments is always greater than that when watching low-resolution video segments of the same scenes. However, the most important observation is that low-resolution video segments yield higher viewing QoE gain in slow motion scenes than in fast motion scenes. Thus, the inclusion of more high-resolution segments in the fast motion scenes and more low-resolution segments in the slow motion scenes would be expected to maximize the user’s viewing QoE. In this study, to evaluate the user’s true experience, we convert the viewing QoE into a satisfaction quality score, termed the Q-score, for scenes with different resolutions in each video segment. Additionally, we developed an optimal segment assignment (OSA) algorithm for Q-score optimization in environments characterized by a constrained network bandwidth. Our experimental results show that application of the OSA algorithm to the playback schedule significantly improved users’ viewing satisfaction.

Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick two). Current attempts to exploit temporal information in video data to overcome this trilemma are bottlenecked by the state of the art in object detection models. This work presents motion vector extrapolation (MOVEX), a technique which performs video object detection through the use of off-the-shelf object detectors alongside existing optical flow-based motion estimation techniques in parallel. This work demonstrates that this approach significantly reduces the baseline latency of any given object detector without sacrificing accuracy performance. Further latency reductions up to 24 times lower than the original latency can be achieved with minimal accuracy loss. MOVEX enables low-latency video object detection on common CPU-based systems, thus allowing for high-performance video object detection beyond the domain of GPU computing.

Digital medical images and image sequences, such as magnetic resonance imaging, computed tomography, and ultrasound, are widely used to diagnose diseases and abnormalities. The secure storage and exchange of such images and image sequences present challenges for hospital management. The objective of this study is to provide a framework for the integrity verification and copyright protection of medical images and image sequences. We design a systematic dual-medium watermarking model that focuses on the security of these images and sequences. Watermark bits (Wbs) are embedded in the transformed and temporal domains of images and image sequences, respectively, instead of in the spatial domain. The images are transformed using integer wavelet transforms, and motion vectors (MVs) are estimated from the image sequences to transform them into the temporal domain using seven block-matching algorithms. The best-performing MVs during frame reconstruction are reconstructed using a genetic algorithm to improve imperceptibility in the watermark-embedded image sequences. To increase the embedding capacity, the Wbs are embedded in regions with minimum or no movement, contrary to the conventional method. Conventionally, Wbs are embedded in regions of image sequences with significant movements. We evaluate the proposed model on typically used MATLAB test images and video datasets available online in Luminance (Y), blue–luminance (U), red–luminance (V) format. A comparison with five state-of-the-art methods shows that the proposed model outperforms the other methods in terms of imperceptibility and embedding capacity. [ABSTRACT FROM AUTHOR]

In this letter, a novel steganographic scheme in motion vector domain (MV) for H.264 video is presented, which can significantly improve the security performance against the newly emerged powerful multi-domain feature set MVC (motion vector consistency). By taking into account both the consistency degree of motion vectors for sub-blocks within a macroblock (MB) or sub-macroblock (sub-MB), and the MV statistics, the corresponding distortion function called dMVC is proposed. The proposed dMVC is also shown to be capable of integrating with existing methods to resist the joint steganalytic attacks of both MVC feature and local optimality features, e.g., NPELO, in the framework of minimal distortion embedding. Compared with other state-of-the-art MV-based steganographic schemes, experimental results on YUV sequences at various embedding rates and QPs show that the proposed method gains significant performance improvement while maintaining good coding efficiency. [ABSTRACT FROM AUTHOR]

Due to the quad-tree with nested multi-type tree coding tree architecture used in versatile video coding (VVC), encoding process has great computational complexity, and this brings difficulties to practical use. To solve this problem, a fast coding unit (CU)partitioning algorithm based on temporal and spatial information is proposed. The proposed algorithm consists of two parts, in the first part, according to the shape of current CU, three different models are utilized to derive motion vectors from corresponding area in the reference frame, according to distribution of motion vectors in models, the CU partition modes that need to be traversed will be reduced by early selecting process; the second part utilizes the correlation of prediction modes between the current CU and adjacent same size CUs, by comparing their prediction modes and rate distortion cost, determines whether to do further traverse in the next depth, thus partition depths that need to be traversed is reduced. Experimental results show that, comparing with the latest encoder VTM10.0, the proposed method can save 39.28% of encoding time with 1.62% increase in BDBR and 0.05 dB increase in PSNR in random access mode. [ABSTRACT FROM AUTHOR]

High Efficiency Video Coding (HEVC) is a video compression standard that offers 50% more efficiency at the expense of high encoding time contrasted with the H.264 Advanced Video Coding (AVC) standard. The encoding time must be reduced to satisfy the needs of real-time applications. This paper has proposed the Multi-Level Resolution Vertical Subsampling (MLRVS) algorithm to reduce the encoding time. The vertical subsampling minimises the number of Sum of Absolute Difference (SAD) computations during the motion estimation process. The complexity reduction algorithm is also used for fast coding the coefficients of the quantised block using a flag decision. Two distinct search patterns are suggested: New Cross Diamond Diamond (NCDD) and New Cross Diamond Hexagonal (NCDH) search patterns, which reduce the time needed to locate the motion vectors. In this paper, the MLRVS algorithm with NCDD and MLRVS algorithm with NCDH search patterns are simulated separately and analysed. The results show that the encoding time of the encoder is decreased by 55% with MLRVS algorithm using NCDD search pattern and 56% with MLRVS using NCDH search pattern compared to HM16.5 with Test Zone (TZ) search algorithm. These results are achieved with a slight increase in bit rate and negligible deterioration in output video quality. [ABSTRACT FROM AUTHOR]

Most of the current video steganography algorithms do not meet the Kerckhoffs criterion. Based on the game theory steganography model, this paper proposed a new H.264 video steganography algorithm based on motion vector modification. The algorithm calculated the distortion cost function according to the different sensitivity of human visual characteristics to the direction and speed characteristics of the motion vector, and then obtained the embedding probability of each motion vector according to the game theory and the distortion cost function, and realized a video steganography algorithm which met the Kerckhoffs criterion in theory. Experimental results show that, compared with the same type of video steganography algorithms, the change values of PSNR and SSIM of this algorithm are reduced by 18.9% and 5.9% respectively when it is fully embedded. This algorithm has better security and imperceptibility. [ABSTRACT FROM AUTHOR]

In the last few decades, information security has gained huge importance owing to the massive growth in digital communication; hence, driving steganography to the forefront for secure communication. Steganography is a practice of concealing information or message in covert communication which involves hiding the information in any multimedia file such as text, image, or video. Many contributions have been made in the domain of image steganography; however, due to the low embedding capacity and robustness of images; videos are gaining more attention of academic researchers. This paper aims to provide a qualitative as well as quantitative analysis of various video steganography techniques by highlighting their properties, challenges, pros, and cons. Moreover, different quality metrics for the evaluation of distinct steganography techniques have also been discussed. The paper also provides an overview of steganalysis attacks which are commonly employed to test the security of the steganography techniques. The experimental analysis of some of the prominent techniques using different quality metrics has also been done. This paper also presented a critical analysis driven from the literature and the experimental results. The primary objective of this paper is to help the beginners to understand the basic concepts of this research domain to initiate their research in this field. Further, the paper highlighted the real-life applications of video steganography and also suggested some future directions which require the attention of the research community. [ABSTRACT FROM AUTHOR]

In this article, a motion vector-based video key frame detection algorithm is proposed to solve the problem of miss election and missing selection caused by the difficulty in detecting the moving target characteristics of the video key frame. Firstly, the entropy of adjacent frame difference and the two-dimensional entropy of image are introduced, and the combination of the two is taken as the measurement of the difference between video frames. Secondly, outliers are detected by statistical tools to obtain the lens boundary, thus realizing the adaptive lens detection of video content. Then, ViBe algorithm is used to detect the foreground object in the video sequence and extract the scale-invariant feature transformation features of the foreground moving object. Finally, the motion vector is introduced, and the sum of the block matching results is motion vector by partitioning the two adjacent frames and performing block matching. The magnitude of motion vector reflects the intensity of motion in the video, so active and inactive motion regions are obtained, and the similarity of video frames is calculated according to the defined formula, and key frames are extracted in these regions respectively. The experimental results show that the detection algorithm proposed in this article improves the video results with rich motion information obviously, and the objective indexes and subjective scores are improved to some extent, which improves the universality of the algorithm. In addition, this article also studies the display mode of key frame extraction results in virtual reality environment. The key frame display mode of video in virtual reality is optimized mainly by changing the display mode of information and changing the scene and testing the result of user task execution.

As the opponent of motion vector (MV)-based video steganography, the corresponding symmetric steganalysis has also developed a lot in recent years, among which the logic-based steganalytic schemes, e.g., AoSO, NPELO and MVC, are the most prevailing. Although currently achieving the best detection performance, these steganalytic schemes are less effective in detecting some logic-maintaining steganographic schemes. In view of the fact that the distributions of covers’ local Lagrangian cost quotients are normally more concentrated in the small value ranges than those of stegos and “spread” to the large values ranges after modifying the motion vector, the local Lagrangian cost quotient would thus be an efficient indicator to reflect the difference between cover videos and stego ones. In this regard, combining the logic-based (Lg) and local Lagrangian cost quotient (LLCQ)-based feature, we finally proposed a more effective and general steganalysis feature, i.e., Lg-LLCQ, which is composed of diverse subfeatures and performs much better than the corresponding single-type feature. Extensive experimental results show that the proposed method exhibits detection performance superior to other state-of-the-art schemes and even works well under cover sources and steganographic scheme mismatch scenes, which indicates our proposed feature is more conducive to real-world applications.

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the clinical diagnosis of mood disorder, a large proportion of patients with bipolar disorder (BD) are misdiagnosed as having unipolar depression (UD). Generally, long-term tracking is required for patients with BD to conduct an appropriate diagnosis by using traditional diagnosis tools. A one-time diagnosis system for facilitating diagnosis procedures is thus highly desirable. Accordingly, in this study, the facial expressions of patients with BD, patients with UD, and healthy controls elicited by emotional video clips were used for conducting mood disorder classification; the classification was performed by exploring the temporal fluctuation characteristics among the three groups. First, macroscopic facial expressions characterized by action units (AUs) were applied for describing the temporal transformation of muscles. Modulation spectrum analysis was applied to extract short-term intensity variations in the AUs. An interval-based multilayer perceptron (MLP) neural network was then used to classify mood disorder on the basis of the detected AU intensities. Moreover, motion vectors (MVs) were employed to describe subtle changes in facial expressions in the microscopic view. Eight basic orientations of MV change were considered for representing microfluctuation. Wavelet decomposition was then applied to extract entropy and energy features in different frequency bands. A long short-term memory model was finally used to model long-term variations for conducting mood disorder classification. A decision-level fusion approach was conducted on the combined results of macroscopic and microscopic facial expressions. For evaluating the described methods, the facial expressions elicited from the 36 subjects (12 from each of the BD, UD, and control groups) were used in 12-fold cross-validation experiments. Approaches for macroscopic and microscopic expressions achieved classification accuracies of 63.9 and 66.7 percent, respectively, and the accuracy of the fusion approach reached 72.2 percent. The results indicate that macroscopic and microscopic view descriptors are complementary to each other and helpful for conducting mood disorder classification. [ABSTRACT FROM AUTHOR]

Advanced driver-assistance systems need a camera calibration algorithm for various vision applications including surround-view monitoring (SVM) and lane departure warning (LDW). Although cameras mounted on a vehicle are calibrated in the manufacturing process, their orientation angles are subject to tilting because of continuing vibration and external impact. To solve the problem, this paper presents an online calibration algorithm for camera orientation estimation using motion vectors and three-dimensional geometry. The proposed algorithm consists of three steps: i) driving direction estimation by calculating an intersection of motion vectors, ii) camera orientation estimation based on 3-line random sample consensus (RANSAC) using the estimated intersection, and iii) final orientation decision using extended Kalman filter from the result of each frame. Experimental results demonstrate that the proposed algorithm stably estimates camera orientation angles from motion vectors and lines under the parallelism and orthogonality assumptions. [ABSTRACT FROM AUTHOR]

Current video steganography operates with either the decoded frame images or the compression coding parameters, which could cause quality degradation of the reconstructed frames. In this letter, by exploiting the advanced motion vector prediction (AMVP) technique of High Efficiency Video Coding (HEVC) standard, we propose a non-degraded adaptive steganographic approach for H.265/HEVC videos. The index value in the candidate list of the prediction unit (PU) is used for embedding. Experimental results demonstrate the superiority of the proposed steganographic approach against both hand-crafted feature-based and deep learning network-based steganalytic detectors. Our work explores a new embedding space that is not previously studied. It is a significant development in finding new ways to escape from video quality change-based steganalysis. [ABSTRACT FROM AUTHOR]

The continuous Sign Language recognition (SLR) system suffers from a problem called movement epenthesis (me) which involves certain intermediate connecting movement between two consecutive signs. In this paper, a novel framework for spotting of continuous fingerspelling sequence is proposed, which can directly extract motion information of signs from a compressed video. The framework is based on motion vectors extracted from H.264/AVC compressed videos. A Spatio-Temporal Markov Random Field (ST-MRF) based model is employed to model non-rigid motions of fingers as sign or me. The proposed framework is tested on a number of sign language videos encoded with an H.264/AVC JM encoder, and the accuracy of spotting was found to be around 75%. [ABSTRACT FROM AUTHOR]

• Previous steganalytic methods cannot detect HEVC-exclusive MV modification strategy that keeps the MV values unchanged. • We find out the local optimality in candidate list can better characterize the perturbation for MV modification. • We proposed a new HEVC steganalytic method based on a 40-dimensional feature set. • Our method outperforms existing ones against both the traditional and the HEVC-exclusive MV modifications. Current research of video steganalysis is mainly oriented to H.264 or even earlier formats. As the H.265/HEVC standard is becoming more and more popular, there have been steganographic methods specifically designed for HEVC videos. Previous steganalytic methods are no longer effective due to the new features of HEVC. The advanced motion vector prediction technique employed by HEVC provides a new way for motion vector (MV) modification, utilizing the index of the candidate MV list. Such modification cannot be detected by previous steganalytic methods because the value of MV is not changed. To solve this problem, we proposed a new steganalytic strategy employing not only the local optimality of MV but also the local optimality in the candidate list. Combining the two types of local optimality, a 40-dimensional feature set is designed. Extensive experiments are carried out to evaluate the effectiveness of the proposed feature set. It is shown that compared with three current steganalyzers, our approach improves the performance against typical MV modification methods under various settings. In particular, our approach significantly boosts the detection accuracy of the index modification method that is exclusive to HEVC videos. To our best knowledge, this is the first work of video steganalytic method exploiting the new features of HEVC format. [ABSTRACT FROM AUTHOR]

Interactive virtual reality (VR) services such as VR gaming require considerable computing power for rendering higher quality VR images at a high frame rate. Thus offloading such VR processing to a cloud or edge computing entity is promising, but is accompanied by long latency leads for a user to see an image of the past viewport, resulting in prohibitive motion sickness. Time warp is a technique for VR that warps a rendered image before scanning it out to the display to correct for the head movement occurring after the rendering and will play an important role in reducing the perceived latency in cloud/edge VR. However, time warp has to be applied to the image areas excluding the head-locked objects such as head-up display, menu bar, and notification that are intended to have a fixed position on a screen; otherwise, they are shown to judder. In this paper, we propose an algorithm that identifies head-locked objects in encoded VR frames at low computational load with no explicit information of the head-locked objects for selective time warp in the cloud/edge VR environments. First, we make a key observation from testbed experiments that motion vectors embedded in an encoded VR video stream are highly correlated with the user’s head motion. Based on this finding, the head-locked object detection algorithm is designed to: 1) find a raw shape of each head-locked object from motion vectors embedded in frames and 2) identify the exact pixel-level head-locked region within a limited search area (along the boundary of each raw shape) by monitoring pixel color changes over frames. In order to achieve even lower computational load, the costly part of the algorithm is activated only when a new head-locked object appears. The experimental study demonstrates that the algorithm is able to detect multiple head-locked objects with zero pixel error under limited computational load.

Camera shakes cause video motion blur. Video deblurring has been studied for years, and however, there are still unresolved problems, such as video frame alignment, frame selection, and frame ambiguity evaluation. We propose a video deblurring algorithm based on the motion vector and an encoder-decoder network. Our algorithm consists of four steps: first, the blurry image blocks in a video frame are located using a blurred image quality evaluation algorithm based on a response function of singular values. Second, the corresponding candidates of the blurry image block in the consecutive frames are searched using the motion vector, and the optimal candidate blocks are obtained using an objective function. Third, the blurry image block and the optimal candidate blocks are served as samples, which are inputted to an encoder-decoder network, so that the blurry image block is repaired. Finally, all blurry image blocks are replaced with the repaired ones, the boundary artifacts are eliminated, and the entire video frame is repaired. The experiments show that our algorithm yields sharper repair results, and the overall performance of our algorithm is better than other related algorithms.