Visual Scheme Research Articles

Pimo: memory-efficient privacy protection in video streaming and analytics

Video streaming from cameras to backend cloud or edge servers for neural-based analytics has gained significant popularity. However, the transmission of data from cameras to a backend raises substantial privacy concerns, particularly regarding sensitive information like facial data. To offer privacy protection, visual processing techniques, such as Generative Adversarial Networks (GANs), have been employed on cameras to blur and safeguard such data intelligently. However, these techniques frequently face memory challenges, particularly when dealing with high-resolution videos. In this paper, we propose PIMO, a memory-efficient visual privacy protection scheme designed to effectively blur video content leveraging adaptive slicing of frames and resolution degradation. Our extensive experimental evaluations validate that PIMO’s adaptive mechanism proficiently navigates fluctuating memory constraints. Furthermore, utilizing a content-based blur scheme, our approach can maintain an impressive mean precision of 95.2%, as compared to the original, non-blurred images.

Target location method of intelligent deicing robot based on nonlinear auto disturbance rejection neural network

A visual navigation scheme for intermittent walking deicing robots was designed to address the issues of multiple iterations, long computation time, and poor real-time performance in the nonlinear optimization of the original SLAM system. A computer image acquisition unit, a computer image processing module, and a visual navigation parameter extraction algorithm were also designed. Implemented a visual navigation system for deicing robots based on image processing. It can meet the navigation requirements of the deicing robot. Simulation and experiments have shown that the method proposed in this paper can quickly and accurately identify abnormal point clouds. The visual servo control scheme constructed in this paper is aimed at robot task operations with unknown system calibration and target depth information. By calibrating the robot vision system, the conversion between camera pixel coordinates and robot base coordinates is achieved, with a transmission frame rate of 53.65 per second; The maximum error in positioning accuracy in space is 10.6 mm. The feature trajectory of visual space is smooth and stable within the camera's field of view, and the end movement of Cartesian space robots is stable without rebound, resulting in high grasping and positioning accuracy.

Predicting clinical endpoints and visual changes with quality-weighted tissue-based renal histological features.

Two common obstacles limiting the performance of data-driven algorithms in digital histopathology classification tasks are the lack of expert annotations and the narrow diversity of datasets. Multi-instance learning (MIL) can address the former challenge for the analysis of whole slide images (WSI), but performance is often inferior to full supervision. We show that the inclusion of weak annotations can significantly enhance the effectiveness of MIL while keeping the approach scalable. An analysis framework was developed to process periodic acid-Schiff (PAS) and Sirius Red (SR) slides of renal biopsies. The workflow segments tissues into coarse tissue classes. Handcrafted and deep features were extracted from these tissues and combined using a soft attention model to predict several slide-level labels: delayed graft function (DGF), acute tubular injury (ATI), and Remuzzi grade components. A tissue segmentation quality metric was also developed to reduce the adverse impact of poorly segmented instances. The soft attention model was trained using 5-fold cross-validation on a mixed dataset and tested on the QUOD dataset containing PAS and SR biopsies. The average ROC-AUC over different prediction tasks was found to be , significantly higher than using only ResNet50 ( ), only handcrafted features ( ), and the baseline ( ) of state-of-the-art performance. In conjunction with soft attention, weighting tissues by segmentation quality has led to further improvement . Using an intuitive visualisation scheme, we show that our approach may also be used to support clinical decision making as it allows pinpointing individual tissues relevant to the predictions.

A Mathematica-Based Interface for the Exploration of Inter- and Intra-Regional Financial Flows

This work surveys the use of directed weighted graphs in conducting comparative static analyses. The paper discusses the implementation of a computer-aided process for building spreadsheet-based graph models for inter- and intra-regional financial flows. The graph-theoretic techniques are programmed to enable the interactive visualization and analysis of financial data using Wolfram technologies (i.e., Mathematica software v. 11.3 or later, Wolfram player v. 12 or later). The paper describes the workflow for several interactive visualizations applicable to financial networks. The author provides four programs, written in the Wolfram language, that customize input–output financial models by combining the Manipulate command with built-in Mathematica functions and functions of the IGraph package (IGraph/M). The study is a tutorial article for the generation of a suite of visual schemes that provide patterns, practices, and roadmaps of the financial markets across the globe.

A Study on Robust Finite-Time Visual Servoing with a Gyro-Stabilized Surveillance System

This article presents the design and validation of a novel visual servoing scheme for a surveillance system. In this system, a two-axis gimbal mechanism operates the rotation of a camera which is able to provide visual information on the tracked target for the control system. The control objective is to bring the target’s projection to the center of the image plane with the smallest steady-state error and a smooth transient response, even with the unpredictable motion of the target and the influence of external disturbances. To fulfill these tasks, the proposed control scheme is designed consisting of two parts: (1) an observer estimates simultaneously the matched and unmatched disturbances; and (2) a motion control law guarantees the finite-time stability and visual servoing performance. Finally, experiments are conducted for validation and evaluation. The proposed control system shows its consistency and ought to perform better than previous approaches.

Design and Implementation of Data Management and Visualisation Module in Financial Digital Management

Enterprise financial data is the key indicator of enterprise development, which provides the important basis for management to analyse and make decisions. Therefore, the provision of reliable and effective information services to enterprises through visualisation technology has become an urgent problem to be solved in the construction of enterprise informatisation. At present, the common data statistics and visualisation tools in the market are difficult to meet the needs of specialised financial enterprises for data analysis. Additionally, the current financial management system has several issues, including an abundance of data and lack of observation suitability. Aiming at the deficiency of data management function in the system, this paper studies the improvement design of data management and visualisation module in financial digital management. First, [Formula: see text]-means clustering algorithm and C4.5 decision tree algorithm are selected to improve the financial data management system. Then, through the existing hierarchical data visualisation scheme, the node link method, space filling method and Sankey chart are proposed to display the changes of financial data. Finally, the data management and visualisation module and the corresponding algorithm flow are designed. The experiment indicates a contour coefficient of 0.53 for the performance evaluation model based on the [Formula: see text]-means algorithm, indicating a satisfactory clustering result. The employee violation prediction model, based on the C4.5 decision tree algorithm, exhibits a high prediction accuracy of 92.35% for the training dataset, demonstrating its effectiveness in predicting employee violations. The data rendering accuracy of the visualised tool is 98.46%, significantly surpassing that of traditional visualisation tools. At the same time, its visual effect and operation are better than traditional tools. Compared with the traditional data visualisation system, this research method improves the efficiency of enterprise financial data management, converts complicated financial data into graphics that are easier for people to understand, realises visualisation, and effectively reduces the management cost of financial operations.

Visual-triggered contextual guidance for lithium battery disassembly: a multi-modal event knowledge graph approach

Lithium battery disassembly is a complex task that presents numerous challenges, including the wide variety of battery types, intricate manufacturing processes, and the absence of standardised procedures. These challenges pose significant obstacles in achieving efficient and accurate disassembly operations. Consequently, there is a clear need for guidance and support throughout the disassembly process. Conventional strategies for providing disassembly guidance often struggle to adapt to the dynamic changes that occur during the process. Therefore, it is essential to develop an approach that offers flexibility, efficiency, and adaptability to real-time visual cues in order to effectively address these challenges. This paper introduces a novel real-time visual guidance scheme that utilises a sophisticated multi-modal event knowledge graph. By leveraging outputs from computer vision models, the proposed scheme monitors the disassembly process in real-time and provides visually triggered, context-sensitive guidance through the multi-modal event knowledge graph. Additionally, this paper presents an auxiliary training method for visual state detection, guided by the large-scale visual model known as the Segment Anything Model (SAM), which helps mitigate the costs associated with data annotation during model development. The efficacy of the proposed framework is validated through experimental evaluations, demonstrating its potential in enhancing disassembly efficiency.

Integrated Application and Optimized Design Strategies of Automatic and Servo Control Systems for Industrial Robots

Abstract At present, industrial robots have been widely used in industrial fields. This topic focuses on optimizing the system of servo control technology for the automatic control of industrial robots. Taking the optimization of robot automatic grasping technology with visual servo as an example, image-based and position-based visual servo control schemes are designed, respectively, and adaptive gain and first-order non-singular linear equations are used for visual servo performance enhancement. Open-loop control and closed-loop control are combined to create the visual servo-based automatic robot grasping docking method. The dynamic tracking effect of visual servo technology and the grasping performance of automatic grasping technology are evaluated through test experiments. The results can be obtained that the image-based and position-based visual servo control schemes can realize better dynamic tracking of objects, and the tracking accuracy is kept within 1.1mm and 8mm in the uniform and variable speed experiments, respectively. The robot’s automatic target grasping error gradually decreases to about 0 with the increase in the number of steps, and the system exhibits high grasping accuracy (over 96.67%) and speed (within 0.80s) at an operating speed lower than 20 m/s. Dynamic tracking performance and target grasping accuracy are certain features of the automatic robot grasping method based on the visual servo in this paper.

Research on the optimization of interior design visual elements and art design innovation method under the deep convolutional network framework

Abstract As data science and computer science continue to advance, the application of deep learning methods to address technological innovation and optimize interior design has emerged as a significant area of research. In this paper, we propose a VR matching algorithm that utilizes deep convolutional networks to match the appropriate visual elements of the room layout, thereby realizing a panoramic scheme for interior design. A method of automatic extraction of features and labels of room layout based on a convolutional neural network is designed, trained, and tested with the help of a convolutional deep confidence network, and the labeled room layout feature map is classified using the Softmax classifier. A fast retrieval algorithm is being investigated with input in the form of images and combining text and content. Firstly, we input the room layout feature image, extract the feature vector using a convolutional neural network model, and then calculate the similarity between the feature vector in the visual element decorative design drawing and the feature vector of the input room layout image. The maximum similarity is selected as the visual element design scheme of the feature, and then the picture of the panoramic scheme is realized in order to let the designer get the customer’s feedback on the design effect in a more timely manner. The classification models developed in this paper achieve an accuracy rate exceeding 90%, effectively fulfilling the task of classifying images of room layout features. The user’s satisfaction with the interior design methodology experience projects proposed in this paper is also all higher than 70%, and the feedback from both designers and users is very good, which shows the excellent effect of deep convolutional networks in the optimization of interior design visual elements.

SVB: Self-supervised Real CT Denoising via Similarity-based Visual Blind-spot Scheme

SVB: Self-supervised Real CT Denoising via Similarity-based Visual Blind-spot Scheme

Visualization Design and Implementation of Teaching Content in Dalian Shellfish Sculpture Art Colleges and Universities Based on Computer Vision Technology

Abstract As a traditional culture, Dalian shell carving art is facing a huge survival crisis. The problem of non-heritage culture and art protection can be effectively solved by teaching based on computer visualization technology in such a situation. This paper examines the characteristics of shell carving art as an entry point, determines the basic direction of teaching shell carving art, and develops a visualization scheme for teaching the content. Based on the WEB platform, an online teaching platform for shell carving art design based on computer vision technology has been built. Using the perspective method under computer vision technology to automate the imaging of shell carving art, complete the data visualization mapping of shell carving art, and evaluate the teaching results and feedback. The mean intervals of importance and satisfaction of the teaching effect of shellfish sculpture art are [2.2953, 4.2652] and [3.9485, 4.5636], respectively, and the satisfaction score is higher than the importance, and the students are more satisfied with the design of the course. The S-T curve of Teacher 1 demonstrates the teacher-student interaction. Teacher 1 has more interaction with students in 500s with good classroom scope, but after the 9th minute, the teacher’s lecture dominates it, and there is a lack of communication between teachers and students.

3D Communication of Animated Character Image Visualization Based on Digital Media Perspectives

Abstract In this study, we initiate the process by pre-processing the character image data and establishing coordinate axes. Utilizing the parallax principle, we construct a three-dimensional model of the animated character image and design a multidimensional, time-sequential visualization scheme based on clustering techniques. To enhance the effectiveness of cluster visualization, we incorporate color and transparency into the model and develop a three-dimensional communication framework to facilitate user interaction and improve animated image visualization. Subsequently, we evaluate the advantages and feasibility of this three-dimensional communication approach, focusing on user experience and user engagement. We also explore the visual perception capabilities of this method against contrasting background colors of light and dark. The findings demonstrate a credible expression of animated video images, with a credibility index of 4.690. Additionally, user perception is quantified at an average of 4.895, which not only exceeds the four-point benchmark but also outperforms alternative methods. This research offers a substantial reference for the advancement of visual communication studies concerning animated character images.

User Experience Techniques Adopted by Brazilian Game Development Studios: An Exploratory Study

Game development studios deal with numerous challenges to achieve the publication of games that are acclaimed by the public. The difficulties range from a simple choice of color for a particular object within the game to mechanics and narratives. In this way, user experience (UX) techniques provide a better perception of the player’s experience. UX techniques are consolidated in the context of software engineering industries and literature. However, few works in the literature (which will be presented in this work) address this knowledge and treat digital games as a specific type of software. In this sense, we aim to explore and present innovative approaches and best techniques adopted by game development studios to integrate UX into their processes. The research included the participation of 41 digital game development studios from all regions of Brazil, of which 31 were interviewed and 10 chose to participate via questionnaire. The analysis revealed that many participants work in small companies (up to five employees) and apply UX techniques intuitively without formal knowledge and justification for using them. Furthermore, we noticed that many studios are unclear about their techniques and confuse them with game design. However, most understand that UX is fundamental for designing a successful game with community support and buy‐in. In addition, most of the justifications for not using UX techniques converged on a lack of knowledge. Finally, we developed a visual scheme to assist studios and future research, capable of consolidating the information extracted from participants about the UX techniques adopted, the benefits and challenges of applying them to the development process, the justifications for not adopting UX techniques (when not adopted), the test instruments implemented, and the UX dimensions evaluated by them.

An Assessment of the Biological Significance of a Visual Clutch Staging Scheme for Ovigerous Female American Lobster (Homarus americanus).

Qualitative visual clutch staging is a useful tool for rapidly and non-invasively assessing the developmental stage of American lobster, Homarus americanus, embryos. While such a scheme has been used in fisheries monitoring strategies in Canada since the 1980s, the biological relevance of its four visually distinguishable stages is poorly understood. We conducted a laboratory experiment in which 10 ovigerous females were housed and the development of their embryos regularly assessed, both qualitatively and quantitatively, from November until hatching in July/August. We confirmed the biological relevance of the qualitative staging scheme by showing clear quantitative differences in the duration and rate of embryonic development of stages 2-4 (stage 1 was not assessed as the precise spawning date was unknown). Stage 2 represents winter-spring "dormancy". Stage 3 represents a shorter period of rapid development preceding hatch. Stage 4 represents hatching. We also recommend some improvements to the qualitative staging scheme, specifically (1) adding criteria related to the portion of eggs that are occupied by yolk to increase the accuracy of staging, (2) slightly redefining stage 3 to ensure it encompasses the full period of rapid embryonic development pre-hatch, and (3) adding the presence of pre-zoeae as a key indicator of hatching to avoid the misclassification of clutches in the early stages of hatching or those that are completely spent but still have adhesive substance.

Resilient adaptive trajectory tracking control for uncalibrated visual servoing systems with unknown actuator failures

A resilient adaptive tracking control scheme for uncalibrated visual servoing system with unknown actuator failures is proposed, where the camera parameters, the robotic physical parameters, and the position information of end-effector cannot be measured accurately. For our scheme, the nonlinear composite Jacobian matrix involving unknown parameters is estimated by an adaptive algorithm based on the depth-independent interaction matrix frame so that the image feature with time-varying depth can be tackled effectively. With the use of projection technique in the adaptive algorithm, the possible singularity of the estimated composite Jacobian matrix can be well circumvented without any stringent assumption, which is critical for establishing the closed-loop stability. Moreover, a novel adaptive resilient control scheme based on dynamic decoupling is developed to separate the design of visual servoing controller and fault compensation, improving the visual servoing system resilience against unknown actuator failures in uncalibrated environment. Through a rigorous Lyapunov argument, the asymptotic convergence of image tracking error to zero is established successfully regardless of the occurrence of unknown actuator failures. The effectiveness of the proposed visual tracking control scheme is confirmed by simulation results.

Visualization with Prediction Scheme for Early DDoS Detection in Ethereum.

Blockchain technologies have gained widespread use in security-sensitive applications due to their robust data protection. However, as blockchains are increasingly integrated into critical data management systems, they have become attractive targets for attackers. Among the various attacks on blockchain systems, distributed denial of service (DDoS) attacks are one of the most significant and potentially devastating. These attacks render the systems incapable of processing transactions, causing the blockchain to come to a halt. To address the challenge of detecting DDoS attacks on blockchains, existing visualization schemes have been developed. However, these schemes often fail to provide early DDoS detection since they typically display only past and current system status. In this paper, we present a novel visualization scheme that not only portrays past and current values but also forecasts future expected system statuses. We achieve these future predictions by utilizing polynomial regression with blockchain data. Additionally, we offer an alternative DDoS detection method employing statistical analysis, specifically the coefficient of determination, to enhance accuracy. Through our experiments, we demonstrate that our proposed scheme excels at predicting future blockchain statuses and anticipating DDoS attacks with minimal error. Our work empowers system managers of blockchain-based applications to identify and mitigate DDoS attacks at an earlier stage.

A novel visual tracking scheme for unstructured indoor environments

In the ever-expanding sphere of assistive robotics, the pressing need for advanced methods capable of accurately tracking individuals within unstructured indoor settings has been magnified. This research endeavours to devise a realtime visual tracking mechanism that encapsulates high performance attributes while maintaining minimal computational requirements. Inspired by the neural processes of the human brain’s visual information handling, our innovative algorithm employs a pattern image, serving as an ephemeral memory, which facilitates the identification of motion within images. This tracking paradigm was subjected to rigorous testing on a Nao humanoid robot, demonstrating noteworthy outcomes in controlled laboratory conditions. The algorithm exhibited a remarkably low false detection rate, less than 4%, and target losses were recorded in merely 12% of instances, thus attesting to its successful operation. Moreover, the algorithm’s capacity to accurately estimate the direct distance to the target further substantiated its high efficacy. These compelling findings serve as a substantial contribution to assistive robotics. The proficient visual tracking methodology proposed herein holds the potential to markedly amplify the competencies of robots operating in dynamic, unstructured indoor settings, and set the foundation for a higher degree of complex interactive tasks.

Comprehensive application system of BIM technology in MULTIBAY project

With the rapid development of urbanization, the number of super high-rise buildings with increased building volume and scale is gradually increasing. At present, there are still problems such as inconsistent engineering information transmission and low efficiency of collaborative management among various participants in the construction of international super high-rise buildings. Because of this, based on engineering practice, using the advantages of BIM technology such as visualization, simulation, and collaboration, this article explores the application process of BIM technology in the design stage of super high-rise buildings, such as multi-disciplinary detailed design and drawing collision inspection, as well as in the construction stage, such as visual technical disclosure and scheme selection. It also constructs a BIM whole process management system, enabling BIM technology to better participate in the whole process of project construction, improving the level of project information technology, and providing engineering reference for the application of BIM technology in similar super high-rise buildings.

A Brief Discussion on the Development and Research of Original Interactive Children's Picture Books in China

With the development of global research on child education, the benefits of reading for children's cognitive development have been widely recognized. Children's picture books serve as important vehicles for children to understand the world around them, establish values, and develop life beliefs. They can also be powerful tools in strengthening parent-child relationships. Currently, an increasing variety of children's picture books are emerging in the public eye. In the children's market in China, there is strong inclusivity toward picture books from different countries, cultures, and artistic styles. Chinese child readers and parents have shown a strong interest in and acceptance of diverse picture book content. This inclusivity provides children with a wider range of reading choices and enriches their learning experiences. In order to better stimulate children's interest in reading and assist parents without parenting or educational experience, it is essential to provide them with better guidance and confidence during parent-child reading sessions. Therefore, in the design process of children's picture books, there are several aspects that designers need to consider comprehensively. Firstly, there should be a clear understanding of the psychological needs of children at different age stages. Secondly, careful consideration should be given to the visual pairing of illustrations and text, visual colour schemes, interactivity, and educational value, as well as the quality and safety aspects of the picture book. The process of reading together with parents and young children is not only a journey for children to understand the world but also a process for parents to understand the world of their children. It is a growth experience for both children and parents, providing them with high-quality bonding time and valuable companionship throughout their lives. Research on children's picture books has been initiated earlier and achieved significant accomplishments in developed countries abroad. Countries such as the United States, the United Kingdom, and Japan have made significant contributions to the development of children's literature through active exploration and innovation in the research and publishing of children's picture books. They pay attention to children's developmental needs and psychological growth, emphasising the quality of content, artistic expression, and educational value. They have set benchmarks in the global children's picture book market and have had a profound impact on the creation and research of children's picture books in other countries. Compared to other countries, China had a relatively late start in the field of children's picture books. However, over the past few decades, the children's picture book market in China has experienced rapid development and transformation. With the growth of the market and the support of policies, there has been continuous progress in content creation, publishing quality, and artistic expression of children's picture books. With increasing attention and support, the creation and research of children's picture books in China are bound to further develop and expand. This article first expounds on the research background and current situation of children's picture books, laying a practical foundation for the purpose and significance of the study. It explores the concept of interactive children's picture books and investigates the interactive forms of excellent children's picture books from abroad. It also examines the direction and forms of interactive design in original children's picture books in China, aiming to establish a new connection between children and picture books. This will better cater to children's curiosity, activity, and engagement needs, and provide a more diverse, interesting, and personalised reading experience.

Mind maps as an effective tool in “Practical English language course”

The article considers the issue of using mind maps in the Practical English course. It is emphasised that they help to structure, analyse, understand and memorise the necessary material. With their help, teachers can explain a new topic, systematise information, exercise control, summarise what they have learned, encourage communication, and create supports. This study aimed to consider the concept of “mind maps” and to highlight the possibility of their application in the study of the educational component “Practical English Language Course”. Research methods includes analysis, systematization, and generalization of scientific research, as well as abstraction, idealization, and logical-structural analysis of the use of mind maps in the educational process. It is noted that this tool is also effective for a student, in particular, for systematizing knowledge, for preparing for classes, for test control, etc. The student can actively participate in the educational process, participating together with the teacher in the development of mind maps. The article states that one of the main uses of mind maps is to create visual schemes or diagrams to represent and organize ideas, vocabulary, grammatical structures, or thematic concepts. In the “Practical English Language” classes, students of higher education can use mind maps to create a schematic representation of the studied material, to activate speaking skills, to work with lexical material, with grammatical material, with text material, to present the results of project activities, to conduct brainstorming storming, discussion, debate, etc. Teachers adapt the use of mind maps according to the specific needs and preferences of their students, which promotes active learning, development of critical thinking and effective communication in the classes. The article emphasizes that in classes you can use ready-made mind maps presented in textbooks or on posters, prepare your own samples for class in the form of presentations or reference notes, in the process of presenting the material, build them in class, organize various types of individual and group activities of students with using ready-made mind maps. Their advantages in use by both teachers and students of higher education are indicated. The practical significance of the research is that its results can be used in the process of professional training of future philologists and English language teachers in higher education institutions, as well as for the preparation of scientific and methodological support using mind maps and in the self-educational activities of students