Classical Video Research Articles

Robust Mixed-Rate Region-of-Interest-Aware Video Compressive Sensing for Transmission Line Surveillance Video

Classic video compression methods usually suffer from long encode time and requires large memories, making it hard to deploy on edge devices; thus, video compressive sensing, which requires less resources during encoding, is receiving more attention. We propose a robust mixed-rate ROI-aware video compressive sensing algorithm for transmission line surveillance video compression. The proposed method compresses foreground targets and background frames separately and uses reversible neural network to reconstruct original frames. The result on transmission line surveillance video data shows that the proposed compressive sensing method can achieve 26.47, 34.71 PSNR and 0.6839, 0.9320 SSIM higher than existing methods on 1.5% and 15% measurement rates, and the proposed ROI extraction net can precisely retrieve regions under high noise levels. This research not only demonstrates the potential for a more efficient video compression technique in resource-constrained environments, but also lays a foundation for future advancements in video compressive sensing techniques and their applications in various real-time surveillance systems.

Automata concepts over game design process

Discrete states linked together by events can describe a series of classical video game scenarios. Therefore, the formal concept of automata seems appropriate for describing such games. However, as simple finite automata need to keep track of past events, they are less appropriate for complex designs. By contrast, push-down automata featuring a stack present better capabilities in this context. This paper discusses an enhanced version of the classic PAC-MAN game with push-down automata. The modular design of this game allows the extraction of discrete states, and its minimalist concept enables various approaches and new versions without sacrificing its original essence. Using push-down automata expanded the game with new features, allowing an enhanced game experience. The automaton controls all aspects of the game, ensuring a consistent gameplay. The presented project demonstrates the capabilities of push-down automata in the gaming industry and their potential in future game development projects.

Videogames as Interactive Cinema - New Perspectives

The concept of interactive cinema has been explored in depth since the first incipient manifestations of (non-interactive) cinema. If our first attempts at creating interactive experiences out of narrative, linear film objects have been notoriously clunky and awkward, with the birth of videogames new attempts have been made, bringing fresh ideas and possibilities unto the table. Interactive works that include films as objects are common today. However, interactive cinema as a concept appears to have been abandoned.Cinema continues to be largely non interactive, this dimension seemingly relegated to videogames, apps and websites. We consider that some videogames can be considered interactive cinema. The Last of Us is an example that set the trend of mostly linear, narrative games. Other games have explored this model, achieving better and worse results. We propose that these games could be categorized as interactive cinema.In this paper we aim to continue an exploration of this idea - that there can be interesting, elegantly implemented creations we can name interactive cinema - distinguishing them from video games. We analyze two video games in this light, ‘Pentiment and Everything, trying to understand how they relate to, and differ from, classic cinema and the classic video game experience. We will also discuss the exhibition “Mundos Paralelos” (Parallel Worlds), on display at the the 25th edition of the Avanca Film Festival, to understand the cinematic characteristics of the artworks presented. We conclude by proposing that, perhaps, closed categories might not serve us when creating new objects, and that hybridization is beneficial, creative, and should occur.

An End-to-End Video Coding Method via Adaptive Vision Transformer

Deep learning-based video coding methods have demonstrated superior performance compared to classical video coding standards in recent years. The vast majority of the existing deep video coding (DVC) networks are based on convolutional neural networks (CNNs), and their main drawback is that since CNNs are affected by the size of the receptive field, they cannot effectively handle long-range dependencies and local detail recovery. Therefore, how to better capture and process the overall structure as well as local texture information in the video coding task is the core issue. Notably, the transformer employs a self-attention mechanism that captures dependencies between any two positions in the input sequence without being constrained by distance limitations. This is an effective solution to the problem described above. In this paper, we propose end-to-end transformer-based adaptive video coding (TAVC). First, we compress the motion vector and residuals through a compression network built on the vision transformer (ViT) and design the motion compensation network based on ViT. Second, based on the requirement of video coding to adapt to different resolution inputs, we introduce a position encoding generator (PEG) as adaptive position encoding (APE) to maintain its translation invariance across different resolution video coding tasks. The experiment shows that for multiscale structural similarity index measurement (MS-SSIM) metrics, this method exhibits significant performance gaps compared to conventional engineering codecs, such as [Formula: see text], [Formula: see text], and VTM-15.2. We also achieved a good performance improvement compared to the CNN-based DVC methods. In the case of peak signal-to-noise ratio (PSNR) evaluation metrics, TAVC also achieves good performance.

Research on Marketing Strategy of Genshin Impact in Asia

As one of the most popular forms of entertainment, video games have become a major relaxation method for people nowadays. Genshin Impact is one of the game people play most rapidly. The performance is extremely remarkable and significant; within two years, its popularity has exceeded many classic video games like a counter strike or League of Legends. Thus, in this paper, It is worth investigating the marketing strategy behind this game as the number of players this game has attracted is enormous. Nevertheless, despite all these performances, many problems also existed in the mechanism and mode of the game. The analysis of problems will discuss complex and tedious plots, shortage of resources, and low rates of getting certain characters. The following paper has suggestions corresponding to the 3 problems: adding interactions between the game and the players, periodic resources refreshing mode, and adding more ways for players to get the five-star characters. In this study, the author will use the CAS method to discuss the abovementioned things.

Rethinking two-dimensional camera motion estimation assessment for digital video stabilization: A camera motion field-based metric

Digital video stabilization aims to remove camera motion jitters through software implementation. The first step of the classical video stabilization methodology is called camera motion estimation, which is usually performed using only RGB frames of the unstable video. Despite recent advances in camera motion estimation strategies, methods classified as two-dimensional are still not properly evaluated, even though it is well known that motion estimation is a crucial step for classical approaches to video stabilization. The main purpose of this work is to draw attention to two-dimensional camera motion estimation assessment and reinforce its importance on video stabilization progress. We proposed a new approach to perform this evaluation using camera motion fields in a pixel-by-pixel comparison and demonstrated through experimental results that our metrics are reliable for diverse scenarios comparing them to image similarity metrics. In addition, we showed and analyzed the results of our metrics for a global and a local method of camera motion estimation. We believe that our assessment and study presented in this work is an important starting point for a more rigorous analysis of this task. In addition, this can be a foundation for coming 2D camera motion estimation methods based on deep learning.

Heart Rate Estimation using Hermite Transform Video Magnification and Deep Learning

Abstract: Monitoring of heart rate can be used in many medical and sports applications. Lack of portability and connection problems make traditional monitoring methods difficult to use outside of clinical environments. The computer vision techniques have shown that some physiological variables as heart rate can be measured without contact. Video magnification is one of these approaches used for the detection of the pulse signal. In this paper we propose a new strategy to magnify motion in a video sequence using the Hermite transform. In addition, a deep learning technique is implemented to estimate the beat-by-beat pulse signal. We trained the system and validated our results using an electronic pulse monitoring device. Our approach is compared with the classical video magnification using a Gaussian pyramid. The results show a better enhancement of spectral information from the color changes allowing an accurate estimation of the instantaneous beat by beat pulse than the Gaussian approach.

Learning-Based Video Compression Framework With Implicit Spatial Transform for Applications in the Internet of Things

The rapid development of big data and network technology demands more secure and efficient video transmission for surveillance and video analysis applications. Classical video transmission relies on spatial-frequency transformation for compressing with loss but with limited coding efficiencies. The deep learning-based approach exceeds such limitations. In this work, we push the limit further by proposing an implicit spatial transform parameters method, which models the inter-frame redundancy to efficiently provide information for frame compression. Specifically, our method comprises a transform estimation module, which estimates the conversion from decoded frame to the current frame, and a context generator. The transform compensation and context generator produce a condensed high-dimensional context. Furthermore, we propose a P frame CoDec for more efficient frame compression by removing the inter-frame redundancy. The proposed framework is extensible with a flexible context module. We demonstrate experimentally that our method outperforms previous methods by a large margin. Our method brings 34.817% more saved bit rate than H.265/HEVC. We also demonstrate 17.500% more bit rate saving and 0.490dB gains in PSNR compared with the current state-of-the-art learning-based method[1].

A review of video action recognition based on 3D convolution

Video action recognition is one of the topics for video understanding. Over the past decade, video action recognition has made great progress due to the emergence of deep learning, especially, the application of 3D convolution, which further improves the accuracy of recognition. However, three challenges remain: difficulty in capturing long video features, high computational costs, and difficulty in comparing methods due to different benchmarks. Therefore, in view of the above three challenges, this paper summarizes and analyzes existing video action recognition methods based on 3D convolution to help new researchers understand this field. Our contributions include 3 parts. Firstly, we introduce the classical video action recognition methods based on 3D convolution and point out two problems of the methods. Then, we summarize the existing improved methods based on 3D convolution and the popular datasets and compare and analyze the experimental results of these methods on the benchmark. Finally, we discuss current challenges for video action recognition and analyze future development trends.

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase (< 0.02%). To verify our method, we densely integrate it into two classical video network backbones and conduct extensive experiments on several standard video classification benchmarks. The source code of our AIA is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/haoyanbin918/Attention-in-Attention</uri> .

Fusion Attention Mechanism for Foreground Detection Based on Multiscale U-Net Architecture.

Foreground detection is a classic video processing task, widely used in video surveillance and other fields, and is the basic step of many computer vision tasks. The scene in the real world is complex and changeable, and it is difficult for traditional unsupervised methods to accurately extract foreground targets. Based on deep learning theory, this paper proposes a foreground detection method based on the multiscale U-Net architecture with a fusion attention mechanism. The attention mechanism is introduced into the U-Net multiscale architecture through skip connections, causing the network model to pay more attention to the foreground objects, suppressing irrelevant background regions, and improving the learning ability of the model. We conducted experiments and evaluations on the CDnet-2014 dataset. The proposed model inputs a single RGB image and only utilizes spatial information, with an overall F-measure of 0.9785. The input of multiple images is fused, and the overall F-measure can reach 0.9830 by using spatiotemporal information. Especially in the Low Framerate category, the F-measure exceeds the current state-of-the-art methods. The experimental results demonstrate the effectiveness and superiority of our proposed method.

Psychometric study of a scale on the use of video games for the initial training of teachers

The present study is focused on analyzing the properties and psychometric characteristics of the Questionnaire about the use of video games in Higher Education. Specifically, in this work we focus on the use of a classic video game, such as Lemmings, to work on the curriculum of the Early Childhood Education stage. The instrument was created ad hoc, based on a Likert scale of 5 response options and three dimensions: student/player profile, quality of the video game and assessment of the video game as a teaching resource. Regarding validity, two studies have been carried out, one with an exploratory nature with half of the sample, 131 participants; and another confirmatory with the total number of the participants, 261 students from the Early Childhood Education Degree at the University of Córdoba (Spain), considering the convergent and discriminant validity coefficients. Lastly, a correlational study was also carried out to clarify the relationships established between the different dimensions of the questionnaire. The results achieved demonstrate that the instrument obtained had a coherent and adequate internal structure with the theoretical assumptions initially raised, as the goodness-of-fit indexes of the confirmed model were high, at the same time showing high validity and reliability.

Monkey plays Pac-Man with compositional strategies and hierarchical decision-making.

Humans can often handle daunting tasks with ease by developing a set of strategies to reduce decision-making into simpler problems. The ability to use heuristic strategies demands an advanced level of intelligence and has not been demonstrated in animals. Here, we trained macaque monkeys to play the classic video game Pac-Man. The monkeys' decision-making may be described with a strategy-based hierarchical decision-making model with over 90% accuracy. The model reveals that the monkeys adopted the take-the-best heuristic by using one dominating strategy for their decision-making at a time and formed compound strategies by assembling the basis strategies to handle particular game situations. With the model, the computationally complex but fully quantifiable Pac-Man behavior paradigm provides a new approach to understanding animals' advanced cognition.

Deep Residual Architecture Using Pixel and Feature Cues for View Synthesis and Temporal Interpolation

In this paper, we propose a deep residual architecture that can be used both for synthesizing high quality angular views in light fields and temporal frames in classical videos. The proposed framework consists of an optical flow estimator optimized for view synthesis, a trainable feature extractor and a residual convolutional network for pixel and feature-based view reconstruction. Among these modules, the fine-tuning of the optical flow estimator specifically for the view synthesis task yields scene depth or motion information that is well optimized for the targeted problem. In cooperation with the end-to-end trainable encoder, the synthesis block employs both pixel-based and feature-based synthesis with residual connection blocks, and the two synthesized views are fused with the help of a learned soft mask to obtain the final reconstructed view. Experimental results with various datasets show that our method performs favorably against other state-of-the-art (SOTA) methods with a large gain for light field view synthesis. Furthermore, with a little modification, our method can also be used for video frame interpolation, generating high quality frames compared with SOTA interpolation methods.

Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review.

Video object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is more challenging than image detection, since video frames are often more blurry than images. Moreover, video detection often has other difficulties, such as video defocus, motion blur, part occlusion, etc. Nowadays, the video detection technology is able to implement real-time detection, or high-accurate detection of blurry video frames. In this paper, various video object and human action detection approaches are reviewed and discussed, many of them have performed state-of-the-art results. We mainly review and discuss the classic video detection methods with supervised learning. In addition, the frequently-used video object detection and human action recognition datasets are reviewed. Finally, a summarization of the video detection is represented, e.g., the video object and human action detection methods could be classified into frame-by-frame (frame-based) detection, extracting-key-frame detection and using-temporal-information detection; the methods of utilizing temporal information of adjacent video frames are mainly the optical flow method, Long Short-Term Memory and convolution among adjacent frames.

Видеоигровые изобразительные стили

The article examines the graphic styles that have arisen in the video game industry due to the technical features and development of this media. These styles are widely used and starting to go beyond the industry into the field of contemporary art. Despite the fact that pixel art is mainly used in the creation of video games, it has already become an independent form of visual style. Contemporary artists such as the Russian digital artist and designer under the pseudonym Uno Morales and the artist Natalya Struchkova turn to the pixel style when creating their works. Like the pixel art, voxel graphics has moved into the category of the game visual style, which employs an impressive community of digital artists. Low рoly graphics have modified from the main graphics of three-dimensional games, which look technically imperfect, into the category of an artistic style that forms a recognizable, attractive and unique geometric aesthetics of the image. We can trace the transformation of video game graphics, which have arisen as a result of technical constraints, into separate art styles: pixel art, voxel art, low рoly style, the minimalist style of the first classic video games. These styles are gradually becoming an independent visual unit that does not depend on the video game product as a whole.

An Approach to Domain Transfer in Procedural Content Generation of Two-Dimensional Videogame Levels

Statistical models, such as Markov Chains, have been recently studied in the context of procedural content generation (PCG). These models can capture statistical regularities of a set of training data and use them to sample new content. However, these techniques assume the existence of sufficient training data with which to train the models. In this paper we study the setting in which we might not have enough training data from the target domain, but we have ample training data from another, similar domain. We propose an algorithm to discover a mapping between domains, so that out-of-domain training data can be used to train the statistical model. Specifically, we apply this to two-dimensional level generation, and experiment with three classic video games: Super Mario Bros., Kid Icarus and Kid Kool.

Video Surveillance System of Target Contour

The paper considers the problem of object detection and recognition, namely, its solution without the use of expensive, resource-intensive and complex data collection and processing systems, with the possibility of its mobility, ease of installation and initial setup. The available ways and methods of solving the problem, their advantages and disadvantages are given. The operation of the system according to an algorithm developed on the basis of the method of object recognition, namely the selection of contours by a filter based on the Canny operator, is presented. The article presents intermediate and final illustrations of the system algorithm at each step, which gives an opportunity to get acquainted with its advantages over classical video surveillance systems and some disadvantages. Elements such as a webcam with a video frame rate of 25 frames per second, a mobile phone and a personal computer with the MatLab2021 programming environment installed (chosen due to the ease of use and the presence of built-in image processing functions) were used to demonstrate the system's performance.

FourierCam: a camera for video spectrum acquisition in a single shot

The novel camera architecture facilitates the development of machine vision. Instead of capturing frame sequences in the temporal domain as traditional video cameras, FourierCam directly measures the pixel-wise temporal spectrum of the video in a single shot through optical coding. Compared to the classic video cameras and time-frequency transformation pipeline, this programmable frequency-domain sampling strategy has an attractive combination of characteristics for low detection bandwidth, low computational burden, and low data volume. Based on the various temporal filter kernel designed by FourierCam, we demonstrated a series of exciting machine vision functions, such as video compression, background subtraction, object extraction, and trajectory tracking.

Desafíos de la videovigilancia automatizada

Automated and semi-automated video surveillance, with facial and behavioral recognition algorithms, is generating international debates which are important to delve into without rushing to quick, but neither slow, conclusions. Unlike other countries in America and Europe, in 2020 Argentina still does not have a national regulatory law for classic video surveillance, and the most populated district with the most cameras in the country, the Province of Buenos Aires, does not have its own integral regulatory framework either. The fragile institutional foundations that receive this advanced technology should not be overlooked if negative effects are to be avoided, not only in the protection of privacy, but also in terms of strengthening the right to security, which is the reason that legitimizes its implementation. The main intention of this paper, framed in the field of surveillance studies and public policies, is contribute from a Social Sciences perspective to unravel some conceptual knots that, in addition to generating recurrent misunderstandings, have normative effects that collaborate in naturalizing certain practices that require further thought. Among them, we can mention the imprecise and mechanical assimilation of surveillance and security; the relative effectiveness of video surveillance systems in terms of security and judicial functions; the relationship between the rights to privacy and intimacy with public space; the links between the techno-logical and the ideo-logical; etc. These aspects will be exemplified through the case of the implementation of this technology in the City of Buenos Aires, through the documentary analysis of regulations and official documents.