Figure 7 - available via license: CC BY-NC
Content may be subject to copyright.
Source publication
In military organization, the synchronization in the parade is important for showing their majesty. However, we do not have any quantitative evaluation methods for the parade. In this research, as a first step of the quantitative evaluation for the parade, we propose an evaluation method focusing on the synchronization level of “Marking Time”, in w...
Contexts in source publication
Context 1
... in Experiment 1, we analyzed the marking time of two persons. We experimented with 6 pairs of two cadets in the National Defense Academy, which have parade training every day (Figure 7). ...
Context 2
... Experiment 2, we have three types of arm swing: Phase Synchro nization, Phase Difference and Phase Opposition. Figure 7 shows a snapshot of Phase Opposition. Both cadet arm swing is opposite in Figure 7. Figure 8 shows the average of the synchronization level r of marking time. ...
Similar publications
The analysis of the interplay between structural and functional networks require experiments where both the specific structure of the connections between nodes and the time series of the underlying dynamical units are known at the same time. However, real datasets typically contain only one of the two ways (structural or functional) a network can b...
Citations
... Individual identification with gait data using Kinect has been reported (Mori & Kikuchi, 2017;Mori & Kikuchi, 2018). Okugawa et al. (2019) reported that clustering using Openpose and Kmeans methods could evaluate arm movement synchronization in parade dances. It might be possible to apply these methods to assess movement similarities with easily captured 2D images. ...
Currently, with the rising energy consumption bringing about the greenhouse effect, the proposed “double carbon” strategy has significant value. Traditional building temperature control solutions have resulted in a certain amount of wasted energy, but the construction of real-time non-contact human thermal comfort detection can effectively alleviate this situation and realise a ‘people-centred’ intelligent building. Accurate and effective determination of human thermal comfort in intelligent buildings is significant. Human behavioral actions can provide important feedback signals to building heating, ventilation, and air conditioning systems. However, there is a lack of effective methods for real-time, low-cost, non-contact human thermal discomfort state detection. In this paper, a contactless thermal comfort prediction method based on skeletal keypoints was proposed, which is intended to avoid overcooling and overheating and to improve indoor human environmental satisfaction. The experiment used a questionnaire to select six actions with high confidence levels to produce a dataset on thermal discomfort.The concept of action sequences was proposed and corresponding dataset and pose recognition algorithms were produced. The final experimental results show that the method can improve the robustness of the model and effectively estimate thermal discomfort.
Children’s motor coordination is an important component of physical fitness test for young children. The development of children’s motor coordination occurs throughout children’s motor development, and it is not only limited by the maturity of children’s neurodevelopment, but also plays an important role in promoting children’s neurodevelopment. This study proposes an automatic assessment method based on deep learning to improve assessment efficiency and reduce costs. The method combines human posture estimation, similarity calculation and time series feature extraction for the assessment of children’s movements. The results showed that the accuracy rate and redundancy rate of the fine action coin toss keyframes finding algorithm are 89.8% and 7.5%; the accuracy rate of the dynamic action standing long jump keyframes finding algorithm is 74.3%; the accuracy rate, precision rate and recall rate of the fine action coin toss assessment algorithm are 74.4%, 72.5% and 90.0%; the accuracy rate, precision rate and recall rate of the static action single-leg balance assessment algorithm are 87.1%, 73.5% and 87.1%; the accuracy rate, precision rate and recall rate of the dynamic action standing long jump assessment algorithm are 71.6%, 73.5% and 71.4%; the results of the three actions generally matched the expert assessment results. The method provides a good auxiliary tool for determining the motor development level of young children, and provides a good technical support for achieving the goal of “promoting the early comprehensive development of young children through actions”.KeywordsHuman Posture EstimationSimilarityAction AssessmentTime Series Features
A research is designed to comprehensively study the dynamic trends and characteristics of dance movements recognition approaches, providing a valuable reference for the scientific research and development of dance art in China. Based on previous studies, a dance movements recognition model is proposed based on DL biological image visualization technology against the current problems in high-level dance movements. This model consists of the convolutional neural network (CNN)-based dance movements recognition algorithm that can recognize body movements, the dance movements recognition algorithm involving videos in the database, and the algorithm that analyzes image feature similarities of the dance movements. The Open Pose algorithm is adopted for human posture recognition. A high-precision human body pose movement state is finally obtained to judge the body changes of high-level dance movements through the division of human bones. Students with excellent dancing skills are invited to participate in the experiment, for whom specific dance movements are designed. The movement characteristics of bodies’ joint points are extracted and compared with standard movements demonstrated by teachers to obtain the differences between students’ movements and standard movements. The results review that the proposed dance movements recognition model based on biological video images has high accuracy. Within 6–8 s, the swing amplitude of the subjects’ left arm is quite different from the standard dance movements. The movements of the left arms, right arms, left legs, and right legs of experimental objects are quite different from the standard dance movements, which proves the model’s effectiveness. The results can provide a valuable reference for the research and development of dance in China and a practical basis for teaching dance movements.
The highly synchronized parade can impress audiences how strong the troops seem to be, whereas it is difficult to train for the good parade because of its complex collective behavior. However, there is no scientific research about the important factor to train and produce a good parade is. One of the bottlenecks to the scientific approach is the difficulty of measurement of the quality of a group as same as other swarm researches. In this paper, we measured the posture data of members in the parade with OpenPose, which is a cutting-edge pose estimation technology of deep learning. By this measurement, we propose a numerical evaluation for the quality of the parade, and it is confirmed by the questionnaire. In conclusion, our evaluation method is applicable for the quantitative evaluation, and it was suggested that the variation level of the arm swing angles was related to the quality of the parade. This paper is based on the paper presented at the proceedings of the 3rd International Symposium on Swarm Behavior and Bio-Inspired Robotics [1].
