scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Human Motion Recognition in Dance Video Images Based on Attitude Estimation

TL;DR: Zhang et al. as discussed by the authors studied human motion recognition in dance video images based on an attitude estimation algorithm, which can be used not only for professional dancers' movement correction, dance self-help teaching, and other application scenarios but also for athletes' movement analysis.
Abstract: With the deep integration of science and technology and culture, the estimation of human movements in dance video images will become an important application field of computer vision technology, which can be used not only for professional dancers’ movement correction, dance self-help teaching, and other application scenarios but also for athletes’ movement analysis. Therefore, it will greatly promote the implementation of teaching students in accordance with their aptitude by applying information technology to estimate dancers’ movements and postures in real time and obtaining information of classroom dance teaching status in time. In this paper, human motion recognition in dance video images is studied based on an attitude estimation algorithm. When the number of experiments reaches 20, the average value of deep learning algorithm and particle swarm optimization algorithm is 76.23 and 75.23, respectively, while the average value of attitude estimation algorithm in this paper is 77.95. Therefore, the average results of attitude estimation algorithm in this paper are slightly higher than those of other algorithms.

Content maybe subject to copyright    Report

References
More filters
TL;DR: In this article , a large number of core observations, casting slices, scanning electron microscopy, and X-ray diffraction methods were analyzed for the Carboniferous volcanic rocks in Xiquan block, Beisantai Oilfield, Junggar Basin as the research target.
Abstract: In recent years, petroleum exploration in the Carboniferous volcanic rock reservoirs in the Junggar Basin has been the focus of important petroleum energy development in western China. The lithologic identification of volcanic rock reservoirs seriously restricts the accuracy of reservoir prediction and affects the success rate of oil exploration. Different types of volcanic rocks have different petrological characteristics and mineral assemblages, especially affected by the depositional environment. The volcanic rocks in different regions have their own uniqueness. This paper takes the Carboniferous volcanic reservoirs in Xiquan block, Beisantai Oilfield, Junggar Basin as the research target. Through a large number of core observations, casting slices, scanning electron microscopy, and X-ray diffraction methods, the Carboniferous volcanic rocks are analyzed. The petrology, pore characteristics, physical properties, and diagenetic evolution history of the reservoir are analyzed. The study shows that the volcanic facies in the Xiquan block can be divided into explosive facies, overflow facies, and volcanic sedimentary facies, among which the explosive facies is subdivided into empty subfacies (volcanic breccia-breccia tuff combination) and thermal base wave subfacies (tuff). The lithology of the reservoir is pyroclastic rock and volcanic lava, belonging to medium-porous and ultralow permeability reservoirs, and the storage space can be divided into three types: primary pores, secondary pores, and fractures. The lithology of key exploration is breccia tuff, followed by breccia tuff and volcanic breccia.

56 citations

01 Jan 1999
TL;DR: Applications to dance and theater which augment the traditional performance stage with images, video, music, text, able to respond to movement and gesture in believable, esthetical, and expressive manners are shown.
Abstract: This paper describes motivations and techniques to extend the expressive grammar of dance and theatrical performances. We first give an outline of previous work in performance, which has inspired our research, and explain how our technology can contribute along historical directions of exploration. We then present real-time computer vision based body tracking and gesture recognition techniques which is used in conjunction with a Media Actors software architecture to choreograph digital media together with human performers. We show applications to dance and theater which augment the traditional performance stage with images, video, music, text, able to respond to movement and gesture in believable, esthetical, and expressive manners. Finally, we describe a scenario and work in progress, which allow us to apply our artistic and technological advances to street performance.

46 citations

Journal ArticleDOI
TL;DR: In this article , the authors summarized the development history and status quo of intelligent stratified water injection technology at home and abroad and pointed out that there are technical bottlenecks and development limitations in the development of water injection technologies at present.
Abstract: As the driving energy to deal with the decrease of interlayer pressure caused by continuous oil production, the layered water injection technology has the characteristics of inhibiting the decrease of oil production and slowing down the increase of oil/gas ratio. In engineering, water injection technology is often used to improve the properties of crude oil, such as excessive viscosity, weak liquidity, and depleted storage, to avoid the formation of dead oil. Injecting appropriate amount of water into different production horizons can effectively maintain the formation water injection pressure, improve the sustainable development speed of the oilfield, ensure the oil production and effectively control the production cost. It is of great value to petroleum engineering and has been widely concerned by the industrial and academic circles at home and abroad. With the continuous development of oilfields over the years, most oilfields have become high-water-cut oilfields. Through the existing layered water injection technology, there are defects such as high labor cost, low operating efficiency, and long commissioning cycle. The ratio of water injection cost to constant increase gradually decreases, and the technical shortcomings become more and more obvious, which is difficult to meet production needs. It is urgent to study and optimize water injection technology scheme to meet oilfield production and technology iteration. In recent years, electronic technology, communication technology, automatic control technology, and other advanced production technology applied to geological exploration, logging technology fields such as engineering, oilfield development is towards integration and intelligent direction, which makes the advanced control and real-time communication intelligent power precision, and the layered water injection technology is possible. This paper summarizes the development history and status quo of oil recovery stratified water injection technology at home and abroad and points out that there are technical bottlenecks and development limitations in the development of water injection technology at present. Focusing on the current hot spots of intelligent oil recovery stratified water injection technology, the advantages and disadvantages of various intelligent water injection technology are compared and analyzed. It provides a certain theoretical reference value for the theoretical research and engineering application of intelligent stratified water injection technology to the equipment design and production of oilfield production and oil recovery technology research institutes and technology and equipment manufacturers.

41 citations

Journal ArticleDOI
TL;DR: Interactive video dance game is an effective and enjoyable exercise program for adults who wish to decrease their BMI and improve components of cardiorespiratory fitness.
Abstract: Purpose The purpose of this study was to determine the effects of a 6-week interactive video dance game (IVDG) program on adult participants' cardiorespiratory status and body mass index (BMI). Methods Twenty-seven healthy adult participants attended IVDG sessions over a 6-week period. Participants completed pre- and post-testing consisting of a submaximal VO(2) treadmill test, assessment of resting heart rate (RHR) and blood pressure (BP), BMI, and general health questionnaires. Data were analyzed using descriptives, paired t-tests to assess pre-to post-testing differences, and one-way ANOVAs to analyze variables among select groups of participants. Questionnaire data was manually coded and assessed. Results Twenty participants attended at least 75% of available sessions and were used in data analysis. Mean BMI decreased significantly (from 26.96 kg/m(2) to 26.21 kg/m(2); 2.87%) and cardiorespiratory fitness measured by peak VO(2) increased significantly (from 20.63 ml/kg/min to 21.69 ml/kg/min; 5.14%). Most participants reported that the IVDG program was a good workout, and that they were encouraged to continue or start an exercise routine. Forty percent reported improvements in sleep, and nearly half stated they had or were considering purchasing a home version of a video dance game. Conclusions Interactive video dance game is an effective and enjoyable exercise program for adults who wish to decrease their BMI and improve components of cardiorespiratory fitness.

34 citations

Journal ArticleDOI
TL;DR: A new descriptor vector for expressive human motions inspired from the Laban movement analysis method (LMA), a descriptive language with an underlying semantics that allows to qualify human motion in its different aspects is proposed.
Abstract: The purpose of this paper is to describe human motions and emotions that appear on real video images with compact and informative representations. We aimed to recognize expressive motions and analyze the relationship between human body features and emotions. We propose a new descriptor vector for expressive human motions inspired from the Laban movement analysis method (LMA), a descriptive language with an underlying semantics that allows to qualify human motion in its different aspects. The proposed descriptor is fed into a machine learning framework including, random decision forest, multi-layer perceptron and two multiclass support vector machines methods. We evaluated our descriptor first for motion recognition and second for emotion recognition from the analysis of expressive body movements. Preliminary experiments with three public datasets, MSRC-12, MSR Action 3D and UTkinect, showed that our model performs better than many existing motion recognition methods. We also built a dataset composed of 10 control motions (move, turn left, turn right, stop, sit down, wave, dance, introduce yourself, increase velocity, decrease velocity). We tested our descriptor vector and achieved high recognition performance. In the second experimental part, we evaluated our descriptor with a dataset composed of expressive gestures performed with four basic emotions selected from Russell’s Circumplex model of affect (happy, angry, sad and calm). The same machine learning methods were used for human emotions recognition based on expressive motions. A 3D virtual avatar was introduced to reproduce human body motions, and three aspects were analyzed (1) how expressed emotions are classified by humans, (2) how motion descriptor is evaluated by humans, (3) what is the relationship between human emotions and motion features.

26 citations