Displacement Of Object Research Articles

Typology and Modeling Profiles of Moving-Class Process-Entity Interactions. Framework for Multimodal Route Network

Configuration of routes is a rather comprehensive, necessary and at the same time self-sufficient component of an integrated process that models the displacement of objects. This article is focused on the development of the multimodal route network model that leverages on only the pertinent suite of source abstract object types, which preliminary differentiate according to the open architecture of categorized types. The main emphasis is on the detection of relevant associations, which take place into the transportation domain being modeled, and constraints on its populations. One of these restrictions is the base segment constraint, which guarantees correct instances of the specialization segment relationship. The model contains formal expressions for verifying data reliability in terms of segments specialization, coherence and sequence order of the latter in routes. Another group of constraints encompasses the terminal pool restrictions that comprise constraints of the sequence order, non-redundancy, and unique combinations of source and destination route points. All terminal constraints have been formalized by means of the relational algebra operators. Such decision is capable of supporting integrity constraints by using triggers or stored procedures of database management systems. We have also exploited the universal structural primitive for the multilevel representation of entity lists, as well as have demonstrated the role and function of dedicated datasets under the forming of links between entities.

Numerical calculation of sugarcane crushing process based on Smooth Particle Hydrodynamics

Understanding the dynamic crushing process of sugarcane is very important to improve the juice extraction rate. In this work, we prove the feasibility of using the Smooth Particle Hydrodynamics method to simulate the sugarcane crushing process and explore the milling mechanism and the effects of crushing technological parameters on sugarcane stress. The numerical experiments indicate that the stress and deformation of the milled mixture of sugarcane reach the peak at the maximum opening ratio and the X–direction speed of the milled mixture in contact with the roller is more than that of the internal milled mixture. When the roller diameter, roller speed, and compression ratio of the milled mixture are 1060 mm, 5 rpm, and 3, the maximum stress and speed of the milled mixture are 1.857 MPa and 453.6 mm/s. The stress is related to the compression ratio (1.5–3.5) and roller diameter (940–1060 mm) within a certain range, but is independent of roller speed (4–6 rpm). The study on milling mechanism and sensitivity analysis of parameters can provide a reference for optimizing technological parameters and extraction rate. Our approach may be used to study the large displacement and deformation of objects.

Object-Level Semantic and Velocity Feedback for Dynamic Occupancy Grids

LiDAR-based frameworks combining dynamic occupancy grids and object-level tracking are a popular approach for perception of the environment in autonomous driving applications. This paper presents a novel backchannel from the object-level module to the grid-level module that procures the enhancement of overall performance. This feedback leads to an enhanced grid representation by the inclusion of two new steps that allow semantic classification of the occupied space and the improvement of the dynamic estimation. To this end, objects extracted from the grid are analyzed with respect to potential object classes and displacement. Class likelihoods are filtered over time at cell-level using particles and a naive Bayesian classifier. The displacement information is computed taking into account semantic information and comparing objects in consecutive frames. Then, it is used to obtain velocity measurements that are used to enhance grid's dynamic estimation. In contrast to other approaches in the literature seeking similar objectives, this proposal does not rely on additional sensing technologies or neural networks. The evaluation is conducted with real sensor data in challenging urban scenarios.

Video Event Extraction via Tracking Visual States of Arguments

Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles. Existing methods focus on capturing the overall visual scene of each frame, ignoring fine-grained argument-level information. Inspired by the definition of events as changes of states, we propose a novel framework to detect video events by tracking the changes in the visual states of all involved arguments, which are expected to provide the most informative evidence for the extraction of video events. In order to capture the visual state changes of arguments, we decompose them into changes in pixels within objects, displacements of objects, and interactions among multiple arguments. We further propose Object State Embedding, Object Motion-aware Embedding and Argument Interaction Embedding to encode and track these changes respectively. Experiments on various video event extraction tasks demonstrate significant improvements compared to state-of-the-art models. In particular, on verb classification, we achieve 3.49% absolute gains (19.53% relative gains) in F1@5 on Video Situation Recognition. Our Code is publicly available at https://github.com/Shinetism/VStates for research purposes.

(442) The Importance of Understanding Paraphilias and Paraphilic Disorders (PD) for General Health and Sexology

Abstract Introduction Sexual fantasies and behaviors are crucial dimensions of the human experience. Paraphilias and paraphilic disorders (PD), categorized by modern sexology as corresponding to the unconventional sexual experiences of a given society at a given time, are complex and still affected by stigma and uncertainty concerning epidemiology, etiology, and clinical management. These topics are rarely addressed in health professionals’ training, including in the field of sexology, which can significantly impact the quality of care. Objective To identify inherent problems in the study and dissemination of knowledge on paraphilias and PD; to indicate solutions aiming to reduce stigma and to offer better care. Methods Narrative review and experience report of the committee for paraphilias and PD from a Brazilian association of sexology. Results Even though the quality of sexology training in health providers’ education might be varied, it is frequently claimed that it is insufficient for the identification and management of sexual health issues. According to a Austrian medical university’ study, the topic of human sexuality is almost exclusively addressed in the curricula of gynecology, endocrinology, and psychiatry, often focusing on contents such as anatomy, STIs, sexual dysfunctions, pregnancy, and infertility. On the other hand, topics such as pornography and paraphilias are rarely addressed. Dealing with paraphilic individuals is challenging, both for general practitioners and specialist sexologists, and poor training can lead to stigmatizing attitudes, such as pathologizing of unconventional sexual experiences and moral judgment. The knowledge and skills acquired through supervised training on the field of paraphilias and PD proved to be useful in conducting a careful sexual interview, a complete psychiatric anamnesis and establishing a positive therapeutic relation. For example, patients with these characteristics may initially report complaints related to sexual dysfunctions, such as reduced desire or difficulty in getting an erection. However, once their sexuality is approached holistically, the dysfunction might be better explained by the displacement of the sexual object, a defining condition of the paraphilic experience. In such an occasion, the veiled conception that the study of paraphilias and PD is exclusive to psychiatrists and psychologists can relegate it to a blind spot, resulting in negligence on the part of other health professionals, including sexologists. This situation can lead to misdiagnosis, underdiagnosis and inadequate treatment of PD. Ignoring the possibility that a patient may have a PD might shield the professional from dealing with its ethical difficulties, but it addresses neither the patients’ nor social problems – given the risk of criminal sexual behavior. Conclusions To match their complexity, the approach to paraphilias and PD requires high levels of clinical, ethical, and academic understanding. Educational programs capable of tackling these issues would improve sexual health care. It is of fundamental importance that understanding and practice in paraphilias and PD is improved, and it is up to institutions, such as universities and expert associations, to promote discussion of these topics, despite any moral discomfort or tendency to avoid ethical implications of knowing a patient may engage in criminal behavior. Disclosure No

Теоретическое исследование стабилизатора вибрации с обратной связью по интегралу смещения для энергетического оборудования

Reducing the vessel hull vibration caused by the power equipment is usually obtained by the effective vibration-isolating fastening. Vibration impact on the mechanisms and automation tools greatly reduces their reliability, affects the health of passengers and crew members. Despite the modern vibration-insulating materials and compensators, the problems of eliminating the variable forces transmitted from the vibration source have not been fully solved. Increasing the operational requirements for the vibration safety of water transport requires the scientifically based and technical solutions, improving the designs of vibration isolation supports for mounting the marine power plants. Vibration reduction problems must be solved both at the design stage and at the stage of construction, repair and modernization. The conducted studies of vibrations under the influence of the harmonic force, step load and gradually increasing load have shown high efficiency of the support in all cases of load application under different simulation modes. At stabilization of the position the support was controlled by the integral of the displacement. The results of the studies conducted on the test model for the vibration protection of marine power equipment showed the effectiveness of the stabilizer. There is presented a theoretical study of a stabilizer with feedback on the displacement integral in the MathCAD software package. The numerical experiment is based on the Newton equation. The parameters of the stabilizer are determined, on the basis of which it is possible to design the actuator. It can be an electric motor, the direction of rotation of which depends on the direction of displacement of the protected object. The motor rotates a screw pair that compresses the spring. The spring acts on the clutch, the torque changes and maintains the vibration source. The simulation results helped to infer that it is necessary to stabilize the position of the unit for all load application modes.

Panoramic Digital Image Correlation for 360-Deg Full-Field Displacement Measurement

In full-field 3D displacement measurement, stereo digital image correlation (Stereo-DIC) has strong capabilities. However, as a result of difficulties with stereo camera calibration and surface merging, 360-deg panoramic displacement measurements remain a challenge. This paper proposes a panoramic displacement field measurement method in order to accurately measure the shape and panoramic displacement field of complex shaped objects with natural textures. The proposed method is based on the robust subset-based DIC algorithm and the well-known Zhang’s calibration method to reconstruct the 3D shape and estimate the full-field displacements of a complex surface from multi-view stereo camera pairs. The method is used in the determination of the scale factor of the 3D reconstructed surface and the stitching of multiple 3D reconstructed surfaces with the aid of the laser point cloud data of the object under test. Based on a discussion of the challenges faced by panoramic DIC, this paper details the proposed solution and describes the specific algorithms implemented. The paper tests the performance of the proposed method using an experimental system with a 360-deg six camera setup. The system was evaluated by measuring the rigid body motion of a cylindrical log sample with known 3D point cloud data. The results confirm that the proposed method is able to accurately measure the panoramic shape and full-field displacement of objects with complex morphologies.

How Central Sulawesi Province's Natural Disasters Affect Economic Growth?

Historically, Indonesia is an area prone to natural disasters. Potential losses caused by natural disasters can be death, injury, illness, threatened life, sense of security, displacement, damage or loss of objects, and disruption of daily activities. The impact of natural disasters will indirectly affect output, income, demand for labor, and economic growth. This study aims to calculate the impact of natural disasters in Central Sulawesi Province (which occurred in 2018) on the regional and national economies. The method used is the Interregional Input-Output model measuring 17 sectors and 34 provinces. The findings show that Central Sulawesi Province's Gross Regional Domestic Product is IDR.114.01 trillion, decreased-12.93 percent to IDR.99.27 trillion due to natural disasters. Labor demand decreased by -9.68 percent, and income decreased by -9.58 percent. Natural disasters in Central Sulawesi Province also impacted the decline in National GDP by -0.16 percent. Disaster mitigation programs are essential for anticipating direct and indirect losses caused by natural disasters. Consequently, the government must consider the impact of inflation and economic growth when implementing disaster mitigation programs on the public agenda.

MOBILIDADE ATIVA: UMA POSSIBILIDADE DE MOBILIDADE URBANA

We live in a period of intense displacement of people and objects, for the most varied reasons, mainly social and/or economic, which can be carried out on foot or by means of motorized vehicles or not. The impression is that everything seems to have more movement. Cities are spaces that serve as a stage for constant transformations and present marks of history, reflecting in a perceptible and visible way the socio-spatial inequality that existed and exists, which represents the process of capitalist urbanization. However, we cannot forget that the population needs to enjoy the qualities of urban life, and, for that, urban mobility is an essential component for the existence of a more democratic city. Therefore, it is necessary to think about urban planning, also observing the problems generated by the displacement of people in the territory. One possible solution is active mobility.

Grounding Mental Representations in a Virtual Multi-Level Functional Framework.

According to the associative theory of learning, reactive behaviors described by stimulus-response pairs result in the progressive wiring of a plastic brain. In contrast, flexible behaviors are supposedly driven by neurologically grounded mental states that involve computations on informational contents. These theories appear complementary, but are generally opposed to each other. The former is favored by neuro-scientists who explore the low-level biological processes supporting cognition, and the later by cognitive psychologists who look for higher-level structures. This situation can be clarified through an analysis that independently defines abstract neurological and informational functionalities, and then relate them through a virtual interface. This framework is validated through a modeling of the first stage of Piaget's cognitive development theory, whose reported end experiments demonstrate the emergence of mental representations of object displacements. The neural correlates grounding this emergence are given in the isomorphic format of an associative memory. As a child's exploration of the world progresses, his mental models will eventually include representations of space, time and causality. Only then epistemological concepts, such as beliefs, will give rise to higher level mental representations in a possibly richer propositional format. This raises the question of which additional neurological functionalities, if any, would be required in order to include these extensions into a comprehensive grounded model. We relay previously expressed views, which in summary hypothesize that the ability to learn has evolved from associative reflexes and memories, to suggest that the functionality of associative memories could well provide the sufficient means for grounding cognitive capacities.

Micro-amplitude vibration measurement using vision-based magnification and tracking

A new deep learning-based vision measurement method is proposed to accurately measure the micro-vibration displacements of objects in different illuminations and backgrounds. The measurement method pre-process the video, then the deep learning correlation methods are used to zoom in the target object and track the vibration trajectory, and the pixel displacement is converted to actual displacement by pixel equivalents. By comparing the three sets of experiments, the proposed method has exceptional accuracy. When measuring vibration displacement of 0.1 mm, the Root Mean Square Error (RMSE) and Normalized Root Mean Square Error (NRMSE) are 0.0234 mm and 11.8601 %. By comparing with the Rectangle Detection Algorithm and the Template Matching Algorithm, the proposed algorithm outperforms these two traditional methods, especially for the complex environments. It can be concluded that this method, as a new visual measurement method, can be adapted to a variety of complex environments and can accurately measure micro-amplitude vibrations.

IndustrialEdgeML - End-to-end edge-based computer vision systemfor Industry 5.0

State-of-the-art object detection methods gain increasing attention in various industrial applications. However, current vision systems typically rely on cloud services for data storage and training of AI models. In this work, we present an end-to-end vision system for bin-picking applications at the edge of industrial premises via industrial computers, where bin-picking refers to the dedicated selection and displacement of objects into designated areas. Our system is designed for human-robot collaboration in a range of distinct challenging industrial environments with a focus on automatically learning new objects. To this end, we propose a new approach for automated oriented object detection consisting of three stages: (i) automatic training data labeling for the new object based on autoencoders, (ii) object detection using the YOLOR-S architecture, and (iii) inference of the object's orientation, more precisely, rotated bounding box detection based on attention maps using the TS-CAM algorithm. Our method achieves state-of-the-art performance, without the need for annotations of rotated bounding boxes, when compared to the single-stage architecture S2A-Net for rotated bounding box detection. In particular, the system maintains high-quality performance not only for learning all objects at once but also for incrementally learning one object after another.

Video Frame Prediction by Joint Optimization of Direct Frame Synthesis and Optical-Flow Estimation

Video prediction is the problem of generating future frames by exploiting the spatiotemporal correlation from the past frame sequence. It is one of the crucial issues in computer vision and has many real-world applications, mainly focused on predicting future scenarios to avoid undesirable outcomes. However, modeling future image content and object is challenging due to the dynamic evolution and complexity of the scene, such as occlusions, camera movements, delay and illumination. Direct frame synthesis or optical-flow estimation are common approaches used by researchers. However, researchers mainly focused on video prediction using one of the approaches. Both methods have limitations, such as direct frame synthesis, usually face blurry prediction due to complex pixel distributions in the scene, and optical-flow estimation, usually produce artifacts due to large object displacements or obstructions in the clip. In this paper, we constructed a deep neural network Frame Prediction Network (FPNet-OF) with multiple-branch inputs (optical flow and original frame) to predict the future video frame by adaptively fusing the future object-motion with the future frame generator. The key idea is to jointly optimize direct RGB frame synthesis and dense optical flow estimation to generate a superior video prediction network. Using various real-world datasets, we experimentally verify that our proposed framework can produce high-level video frame compared to other state-of-the-art framework.

Concept of Vector Multicomponent Physical Quantities, Models and Measurement Method

The paper presents a new view of vector physical quantities as multicomponent quantities. Each of the components of the mentioned multicomponent quantities can carry important and even unique information about the sources and causes of their occurrence. Looking at the vector quantity as the multicomponent quantity led to the need to form the corresponding conception. There are three positions of this conception in this paper, which are formulated as follows: vector multicomponent physical quantities are considered as functions of the set of their constituent information components; the communication functions of the specified information components in the models of multicomponent physical quantities are determined by the laws of vector algebra; information models of vector multicomponent physical quantities allow an alternative representation of information components depending on the selected coordinate system.The mathematical model of the vector multicomponent physical quantity is presented. This model is fundamental and directly follows from the positions of the conception formulated above. This model can be applied to describe multicomponent displacements and deformations that both simple and complex objects undergo. An example of the complex object can be the manipulator of the universal industrial robot. The space for modeling multicomponent displacements of simple objects was shown in the paper. Information models of vector multicomponent physical quantities allow one to alternatively represent informative components. And the task of constructing such models is complex and ambiguous. Therefore, the formal apparatus for the synthesis of such models, which is based on certain rules and conventions, was proposed in the paper. The theoretical foundations of the method of optical measurements of informative components of multicomponent displacements and deformations of simple objects, which involves the use of multidimensional test objects, are presented.

Theta and gamma oscillations in the rat hippocampus support the discrimination of object displacement in a recognition memory task.

Episodic memory depends on the recollection of spatial and temporal aspects of past experiences in which the hippocampus plays a critical role. Studies on hippocampal lesions in rodents have shown that dentate gyrus (DG) and CA3 are necessary to detect object displacement in memory tasks. However, the understanding of real-time oscillatory activity underlying memory discrimination of subtle and pronounced displacements remains elusive. Here, we chronically implanted microelectrode arrays in adult male Wistar rats to record network oscillations from DG, CA3, and CA1 of the dorsal hippocampus while animals executed an object recognition task of high and low spatial displacement tests (HD: 108 cm, and LD: 54 cm, respectively). Behavioral analysis showed that the animals discriminate between stationary and displaced objects in the HD but not LD conditions. To investigate the hypothesis that theta and gamma oscillations in different areas of the hippocampus support discrimination processes in a recognition memory task, we compared epochs of object exploration between HD and LD conditions as well as displaced and stationary objects. We observed that object exploration epochs were accompanied by strong rhythmic activity in the theta frequency (6-12 Hz) band in the three hippocampal areas. Comparison between test conditions revealed higher theta band power and higher theta-gamma phase-amplitude coupling in the DG during HD than LD conditions. Similarly, direct comparison between displaced and stationary objects within the HD test showed higher theta band power in CA3 during exploration of displaced objects. Moreover, the discrimination index between displaced and stationary objects directly correlated with CA1 gamma band power in epochs of object exploration. We thus conclude that theta and gamma oscillations in the dorsal hippocampus support the successful discrimination of object displacement in a recognition memory task.

АВТОМАТИЗАЦИЯ РАСЧЕТА ТЕПЛОПОТЕРЬ ЧЕРЕЗ ГОРИЗОНТАЛЬНЫЕ НАРУЖНЫЕ ОГРАЖДАЮЩИЕ КОНСТРУКЦИИ С РАЗБИВКОЙ ПОЛА ПОМЕЩЕНИЯ НА ЗОНЫ

Introduction: The calculation of heat loss of the room is a mandatory part of any project. Most of the information required for calculations is present in the building information model and can be extracted from it automatically. An example that requires the transformation of digital model information is the task of constructing room zones when calculating heat loss through the floor. Existing software products do not have modules that allow you to automatically calculate the heat loss of a room, including through the floor, breaking it down into zones. The object displacement functions built into the software products are not intended for constructing floor zones and cannot be used as a component of the developed module. These reasons determine the need to develop an algorithm for constructing zones that are necessary for calculating heat loss through the floor, and its implementation.
 Materials and methods: An algorithm for the formation of floor zones of a room is presented. The algorithm allows you to build zones for placing an arbitrary layout.
 Results: A plug-in for Autodesk Revit, which implements the proposed algorithm, was tested on the calculation of heat losses in the rooms of the technical floor of the building. As a result of the experiment, a reduction in the time required for the preparation of the initial information and for the calculation, from 4 hours to 2 minutes, was revealed.
 Conclusions: The developed software module, designed to calculate the heat loss of premises through the floor of premises, broken down into zones, is a step in the development of software products that use a digital building model as initial information.

Recognizing human functional patterns in IADLs through hand detection and artificial intelligence.

Cognitive impairment is one of the characteristics shown by patients with Alzheimer's dementia (Montenegro et al., 2020; Kelley & Petersen, 2007). This affects the executive functions of most of these patients from the early stage (Guarino et al., 2019) and consequently, have difficulty in carrying out their daily activities (Dubbelman et al., 2020). These activities require precise coordination of the person's movements and interaction with their environment, so instrumental activities of daily living (IADLs) are predictors of such impairment (Barberger-Gateau & Dartigues, 1993), as several research studies have shown(Brovelli et al., 2017). Therefore, assessing the performance of IADLs by analyzing human biomechanical markers such as hand movements is of great interest. This, together with the application of artificial intelligence techniques, in particular deep learning, will allow the development of technological tools for the creation of an automated model to support the early diagnosis of Alzheimer's disease. This work was inspired by the development of Alejandro Acosta et al, where human biomechanical markers were analyzed throughout the performance of IADL activities to recognize the human functional pattern (Acosta-Franco et al., 2021). To improve the accuracy of the baseline model, we propose a hand detection algorithm based on a probabilistic approach considering skin color as a descriptor. To test the proposed algorithm, we used the dataset of egocentric videos containing the performance of IADL activities, which is organized into four classes, based on the prehensile patterns of the hands: force and precision, and on the kinematics of the instruments: displacement and manipulation. With the improvement made to the base model we obtained an accuracy higher than 74% in recognizing movement patterns of displacement and manipulation of objects, and a good prediction of the depth of the anatomical planes. Our improved model obtained a good percentage of recognition accuracy for the instrument's kinematics, which can help in the development of technological tools for the creation of an automated model to support the diagnosis of early Alzheimer's disease.

An image analysis method for quantifying precision and disorder in nanofabricated photonic structures

Disorder is an essential parameter in photonic systems and devices, influencing phenomena such as the robustness of topological photonic states and the Anderson localization of modes in waveguides. We develop and demonstrate a method for both analyzing and visualizing positional, size, and shape disorder in periodic structures such as photonic crystals. This analysis method shows selectivity for disorder type and sensitivity to disorder down to less than 1%. We show that the method can be applied to more complex shapes such as those used in topological photonics. The method provides a powerful tool for process development and quality control, including analyzing the precision of E-beam lithography before patterns are transferred; quantifying the precision limits of lithography, deposition, or etch processes; and studying the intentional displacement of individual objects within otherwise periodic arrays.

Displacement Measurement Based on UAV Images Using SURF-Enhanced Camera Calibration Algorithm

Displacement is an important parameter in the assessment of the integrity of infrastructure; thus, its measurement is required in a multitude of guidelines or codes for structural health monitoring in most countries. To develop a low-cost and remote displacement measurement technique, a novel method based on an unmanned aerial vehicle (UAV) and digital image correlation (DIC) is presented in this study. First, an auxiliary reference image that meets the requirements is fabricated using the selected first image. Then, the speeded-up robust features (SURF) algorithm is introduced to track the feature points in the fixed areas. The least square algorithm is then employed to resolve the homography matrix of the auxiliary reference image and target images; then, the acquired homography matrices are utilized to calibrate the deviation caused by the UAV wobble. Finally, the integral pixel and sub-pixel matching of the DIC algorithm is employed to calculate the displacement of the target object. The numerical simulation results show that the proposed method has higher calculation accuracy and stability. The outdoor experiment results show that the proposed method has definite practicability.

FastVOD-Net: A Real-Time and High-Accuracy Video Object Detector

Video object detection is a tough task due to the severe appearance degradation caused by rapid motion, sudden occlusion or rare poses. The great challenge facing video object detection is the simultaneous requirements on both accuracy and speed because the pursuit of one aspect usually causes significant expense to the other. Most existing methods mainly focus on improving detection accuracy with little attention to computationally efficient solutions, and thus they are impractical for many real-world applications. This motivates us to develop a real-time and high-accuracy video object detection method. In this paper, we propose a novel video object detector, called FastVOD-Net, which can yield highly accurate detection results at real-time speed. Specifically, we first develop a temporally-cascaded deformable alignment (TCDA) module to model the object displacements induced by video motion. Then, we introduce another two modules, namely spatially-refined temporal aggregation (SRTA) and attention-guided semantic distillation (AGSD), to improve the appearance feature of the currently processed frame and enhance the semantic representation of non-keyframes, respectively. For keyframe scheduling, we design an adaptive keyframe selection scheduler (AKSS) to adjust the keyframe interval online, making the keyframe usage more rational. On one hand, the characteristics of our FastVOD-Net enable it to sparsely perform expensive feature extraction, which significantly reduces the computational cost and thus guarantees real-time speed. On the other hand, the collaboration of the above tightly-coupled modules and adaptive keyframe scheduler makes FastVOD-Net fully exploit inter-frame temporal dependencies and thus guarantees high accuracy. Experiments on the ImageNet VID dataset show that our FastVOD-Net achieves 79.3% mAP at 29.6 fps or 81.2% mAP at 23.0 fps on an Nvidia RTX 2080 Ti GPU, which is the state-of-the-art performance in real time.