SwinTransTrack: Multi-object Tracking Using Shifted Window Transformers

Digital forensics (now and later called digital forensic science) forensic is a branch of science that involves retrieving and testing objects initiated on cardinal procedures. Images and videos need to develop significant data exporters in the current era. Doctor Images is gradually approaching as an approach that affects individuals and changes their feelings and emotions in the light of different occasions. In the present case, the video counterfeit size has expanded with the expansion of malware work on the Internet, which has made it possible for any customer to download and share items, including images, audio, and video on the Internet. Digital image forensics aims to recognize the legitimacy of images by retrieving data about their history. There are two basic problems: the unique source of the image imaging device and the detection of duplicate notes. Image duplication detection techniques are expected to ensure the validity of computerized images lacking past data about the novel image. There are various courses for modifying an image, for example, rearrangement, splitting, and copy moving. These days, due to the promising results of early selections and constantly growing applications, digital image forensics speaks of an attractive selection space for some researchers. This research study is a comprehensive study of image forensic image processing detection and pixel resolution in video frames.

A dark image enhancement algorithm based on the pairwise target contrast and the multi-scale detail boosting is proposed in this work. We first compute the pairwise target contrast between a pair of pixels, which represents the desired gray level difference of the two pixels in the output image. By aggregating the pairwise target contrasts for all pairs of pixels in an image, we formulate a cost function for the enhancement. By minimizing the cost function, we obtain the optimal transformation function and enhance the image. In addition, we propose a multi-scale approach to boost details in the globally enhanced image. Experimental results show that the proposed algorithm enhances the contrast and visibility of dark images more effectively than conventional algorithms.

Matching cost aggregation is one of the oldest and still popular methods for stereo correspondence. While effective and efficient, cost aggregation methods typically aggregate the matching cost by summing/averaging over a user-specified, local support region. This is obviously only locally-optimal, and the computational complexity of the full-kernel implementation usually depends on the region size. In this paper, the cost aggregation problem is re-examined and a non-local solution is proposed. The matching cost values are aggregated adaptively based on pixel similarity on a tree structure derived from the stereo image pair to preserve depth edges. The nodes of this tree are all the image pixels, and the edges are all the edges between the nearest neighboring pixels. The similarity between any two pixels is decided by their shortest distance on the tree. The proposed method is non-local as every node receives supports from all other nodes on the tree. The proposed method can be naturally extended to the time domain for enforcing temporal coherence. Unlike previous methods, the non-local property guarantees that the depth edges will be preserved when the temporal coherency between all the video frames are considered. A non-local weighted median filter is also proposed based on the non-local cost aggregation algorithm. It has been demonstrated to outperform all local weighted median filters on disparity/depth upsampling and refinement.

A problem of human body localization in video frames using growing neural gas and feature description based on the Histograms of Oriented Gradients is solved. The original neuro-fuzzy model of growing neural gas for reinforcement learning (GNG-FIS) is used as a basis of the algorithm. A modification of the GNG-FIS algorithm using a two-pass training with fuzzy remarking of classes and building of a heat map is also proposed. As follows from the experiments, the index of the correct localizations of the developed classifier from 90.5% to 93.2%, depending on the conditions of the scene, that allows the use of the algorithm in real systems of situational video analytics.

In this study, we present the performance of Support Vector Machine (SVM), Convolution Neural Network (CNN), and Artificial Neural Network (ANN) with Bag of Words (BoW), Histogram of Oriented Gradients (HOG), and Image Pixels (IP) for face recognition. SVM, CNN, and ANN are machine learning approaches and has been used for pattern recognition, especially in face recognition technology. BoW, HOG, and IP are being used for image feature extraction. The testing has been conducted from publicly available AT&T face database. Every individual subject consists of 10 images with different facial expression, different illumination and the dimensions of the images is unified as 92-by-112 pixels with PGM formats. SVM achieved recognition accuracy of 97.00%, 96.00%, and 98.00% with subsequently BoW, HOG, and IP. CNN achieved recognition accuracy of 94.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. ANN achieved recognition accuracy of 96.00%, 99.00%, and 99.50% with subsequently BoW, HOG, and IP. The experimental results show that the IP with ANN approach clearly outperformed the others approaches.

View-plus-depth is a scene representation format where each pixel of a color image or video frame is augmented by per-pixel depth represented as gray-scale image (map). In the representation, the quality of the depth map plays a crucial role as it determines the quality of the rendered views. Among the artifacts in the received depth map, the compression artifacts are usually most pronounced and considered most annoying. In this article, we study the problem of post-processing of depth maps degraded by improper estimation or by block-transform-based compression. A number of post-filtering methods are studied, modified and compared for their applicability to the task of depth map restoration and post-filtering. The methods range from simple and trivial Gaussian smoothing, to in-loop deblocking filter standardized in H.264 video coding standard, to more comprehensive methods which utilize structural and color information from the accompanying color image frame. The latter group contains our modification of the powerful local polynomial approximation, the popular bilateral filter, and an extension of it, originally suggested for depth super-resolution. We further modify this latter approach by developing an efficient implementation of it. We present experimental results demonstrating high-quality filtered depth maps and offering practitioners options for highest-quality or better efficiency.

The International Standards Organization (ISO) has proposed a family of standards for compression of image and video sequences, including the JPEG, MPEG-1 and MPEG-2. The latest MPEG-4 standard has many new dimensions to coding and manipulation of visual content. A video sequence usually contains a background object and many foreground objects. Portions of this background may not be visible in certain frames due to the occlusion of the foreground objects or camera motion. MPEG-4 introduces the novel concepts of Video Object Planes (VOPs) and Sprites. A VOP is a visual representation of real world objects with shapes that need not be rectangular. Sprite is a large image composed of pixels belonging to a video object visible throughout a video segment. Since a sprite contains all parts of the background that were at least visible once, it can be used for direct reconstruction of the background Video Object Plane (VOP). Sprite reconstruction is dependent on the mode in which it is transmitted. In the Static sprite mode, the entire sprite is decoded as an Intra VOP before decoding the individual VOPs. Since sprites consist of the information needed to display multiple frames of a video sequence, they are typically much larger than a single frame of video. Therefore a static sprite can be considered as a large static image. In this paper, a novel solution to address the problem of spatial scalability has been proposed, where the sprite is encoded in Discrete Wavelet Transform (DWT). A lifting kernel method of DWT implementation has been used for encoding and decoding sprites. Modifying the existing lifting scheme while maintaining it to be shape adaptive results in a reduced complexity. The proposed scheme has the advantages of (1) avoiding the need for any extensions to image or tile border pixels and is hence superior to the DCT based low latency scheme (used in the current MPEG-4 verification model), (2) mapping the in place computed wavelet coefficients into a zero tree structure without actually rearranging them, thereby saving allocation of additional memory. The proposed solutions provide efficient implementation of the sprite coder making possible a VLSI realization with a reduced real estate.

Protecting information on various communication media is considered an essential requirement in the present information transmission technology. So, there is a continuous search around different modern techniques that may be used to protect the data from the attackers. Steganography is one of those techniques that can be used to maintain the copyright by employing it to cover the publisher logo image inside the video frames. Nowadays, most of the popular known of the Video-Steganography methods become a conventional technique to the attacker, so there is a requirement for a modern and smart strategy to protect the copyright of the digital video file. Where this proposed system goal to create a hybrid system that combines the properties of Cryptography and Steganography work to protect the copyright hidden data from different attack types with maintaining of characteristics of the original video (quality and resolution). In this article, a modern Video-Steganography method is presented by employing the benefits of TC (Turbo code) to encrypt the pixels of logo image and Least two Significant Bit Technique procedure to embed the encryption pixels inside the frames of the video file. The insertion is performed in the frequency domain by applying the Fast Fourier Transform (FFT)on the video frames. The examination of the suggested architecture is done by terms of Structural Similarity Index, MSE (mean squared error), and PSNR (peak signal-to-noise ratio) by comparing between an original and extracted logo as well as between original and Steganographic video (averaged overall digital frames in the video). The simulation results show that this method proved high security, robustness, capacity and produces a substantial performance enhancement over the present known ways with fewer distortions in the quality of the video

Many animal species, including mice, form societies of numerous individuals for survival. Understanding the interactions between individual animals is crucial for elucidating group behavior. One such behavior in mice is huddling, yet its analysis has been limited. In this study, we propose a cost‐effective method for monitoring long‐term huddling behavior in mice using online image processing with OpenCV. This method treats a single mouse or a group of mice as a cluster of pixels (a ‘blob’) in video images, extracting and saving only essential information such as areas, coordinates, and orientations. This approach reduces data storage needs to 1/200000th of what would be required if the video were recorded in its compressed form, thereby enabling long‐term behavioral analysis. To validate the performance of our algorithm, ~2000 video frames were randomly chosen. We manually counted the number of clusters of mice in these frames and compared them with the number of blobs automatically detected by the algorithm. The results indicated a high level of consistency, exceeding 90% across the selected video frames. Initial observations of both male and female groups suggested some variations in huddling behavior among male and female groups; however, these results should be interpreted cautiously due to a small sample. Group behavior is known to be disrupted in several neuropsychiatric disorders, such as autism. Various mouse models of these disorders have been proposed. Our measurement system, when combined with drug or genetic modification screening, could provide a valuable tool for high‐throughput analyses of huddling behavior.

One of the most important studies is the identification of face from videos in case of low resolution. This article looks at the effect of a mean filter on facial pictures. The mean filter measures the number of pixels in successive images using the intensities of neighbouring pixels and temporal neighbouring pixels. The pixels of the original high-resolution image were used as reference values to measure the effect of the suggested technique on the picture peak signal noise ratio (PSNR) and mean square error (MSE) levels by calculating the noise and error figure of the pixels of the filtered low-resolution pictures. Outcomes indicate major impact on successive face video record frames from the suggested filter.

Most high-capacity, 3D data-hiding schemes introduce irreversible changes into the host model. For artistic or technical models, not modifying the original mesh models is sometimes very important. This work describes a novel, multi-layer, reversible data-hiding scheme for 3D mesh models. The proposed scheme starts with finding an independent set of vertices for embedding data. The prediction residues of the vertices and the secret bit string are then encoded using the arithmetic coding method. The embedding procedure is done by substituting part of the mantissa of these vertices with the coded arithmetic decimal numbers. A maximum distortion constraint is set for each embedding vertex, such that the distortion on the cover model is controlled to be imperceptible. Users can construct a multi-layer embedding scheme by repeatedly applying the single-layer embedding procedure until the secret bit string is completely embedded. By integrating the arithmetic encoder and the substitution operation, the proposed method achieves 4-8 bits/vertex embedding capacity while reserving the ability of rebuilding the original model. Experimental results show that the proposed scheme can successfully reconstruct the original model while extracting the secret bit string.

Engaging the “Clutch” to Move Forward

In the video application, slow motion is visually attractive and gets more attention in video super resolution. To generate the high-resolution (HR) slow motion video frames from the low-resolution (LR) frames, two sub-tasks are required, including video super-resolution (VSR) and video frame interpolation (VFI). However, the interpolation approach is not successful to extract low level feature attention to get the maximum advantage from the property of space-time relation. To this extent, we propose a deep consecutive attention network-based method. The multi-head attention and an attentive temporal feature module are designed to achieve better prediction of interpolation feature frame. Bi-directional deformable ConvLSTM module aggregates and aligns with the information from the multi-head attention and temporal feature block to improve the quality of video frames. This method synthesizes the HR video frames from LR video frames. The experimental results in terms of PSNR show the proposed method of deep consecutive attention outperforms 0.27 dB and 0.31 dB for Vid4 and SPMC datasets respectively, in average of PSNR compared to state-of-the-art baseline method.

Resolution ‘scaling law’ in MRI of articular cartilage

In this paper, a proposal of a new and unusual framework to detect and extract the text from the images and video frames have been presented. In the past various methods have been presented for detection and localization of text in images and video frames. In this paper, a comparison has been made between several text detection methods and proposed method for text detection in images and video frames. The proposed method is carried out by edge detection, and the projection profile method is used to localize the text region better. Various experiments have been carried out to evaluate and compare the performance of the proposed algorithm. Experimental results tested from a large dataset have demonstrated that the proposed method is effective and practical. Various parameters like average time, precision and recall rates and analyzed for both existing and proposed method to determine the success and limitation of our method.