With the development of history, some folk dances are annihilated and lost in the inheritance. In order to protect and inherit national intangible cultural heritage and promote the construction of advanced socialist c...
详细信息
With the development of history, some folk dances are annihilated and lost in the inheritance. In order to protect and inherit national intangible cultural heritage and promote the construction of advanced socialist culture, this paper uses information fusion technology, combines national aesthetic personality, and refers to multi-factor theory, construction theory, and distillation theory to design and reform the art practice model of folk dance education. The data of dancers' skeletal joint points are collected by using multiple Kinect sensors, and the kalman filter algorithm is selected to establish the human skeletal motion model and fuse the data information of each joint point. Taking the hand_right and elbow_right joints as examples, it was found that the mean value of the error between the testers' joint trajectory and the template movement was reduced from 10mm to 4mm, and the mean value of the error between the joint angle and the template movement was reduced from 90 degrees to 35 degrees. Comparing the dance movement training effects and scores of the experimental group and the control group, it was found that the experimental group kicked the front and side legs an average of 70 times/minute, the middle jump height was improved by 10cm, and the average score was 3.33 points higher. This indicates that the integration of information fusion technology in the art practice of dance education can realize the practical innovation of college folk dance education and improve the comprehensive level of folk dance.
Recently, distributed coordination function（DCF） protocol, standardized by IEEE 802.11 group, has played a dominant role in medium access control（MAC） layer of mobile ad hoc network（MANET）. However, due to nodes...
详细信息
Recently, distributed coordination function（DCF） protocol, standardized by IEEE 802.11 group, has played a dominant role in medium access control（MAC） layer of mobile ad hoc network（MANET）. However, due to nodes mobility and topology dynamics, theoretical analysis models of DCF are limited to single-hop network. Unfortunately, mobility of neighbor nodes contended to access idle channel is unconsidered as well. Thus extension of throughput analysis model to multi-hop network and number evaluation algorithm design of neighbor nodes associated with mobility become two critical issues in MANETs. In this paper, we attempt to address the improvement of analysis model by integrating the Euclidean-Real-Ratio（ERR） and kalman filter algorithm into 2-dismension discrete time markov chain（DTMC）. The contribution of this paper is threefold. First, we established a novel model to analyze throughput in multi-hop MANET based on definition of Euclidean-Real-Ratio（ERR）. Second, we qualitatively show that 10% deviation occurs between theoretical analysis and simulation, reason of which is number variation of neighbor nodes. Third, we propose a real-time estimation methodology of neighbor nodes based on kalman filter algorithm coupled with redefinition of status update and measurement rules in poisson network（PN）. Simulation results demonstrate the effectiveness and efficiency of our approach although it brings computation delay about 0.13 s.
Real-time detection and tracking of vehicles is very important in the field of automatic *** this paper,a YOLOv3 network based on pruning algorithm is proposed to solve the problem of real-time vehicle *** reducing th...
详细信息
Real-time detection and tracking of vehicles is very important in the field of automatic *** this paper,a YOLOv3 network based on pruning algorithm is proposed to solve the problem of real-time vehicle *** reducing the number of channels and layers in the backbone network,the computation of the model is *** thus,the rate of detection is greatly *** the basis of vehicle detection,the real-time tracking of multiple vehicle targets is completed by using kalman filter algorithm for prediction and Hungarian algorithm for data *** experimental results show that compared with the original YOLOv3 network,the model size is compressed by 95% to11.25 MB and the detection rate is doubled to 128.1 frames/s while the average accuracy is basically *** detection and tracking frame rate of the whole algorithm is 18 fps,and the recall is 98.5%.The algorithm also has strong robustness on complex traffic roads,and can basically realize real-time detection and tracking of road vehicles.
In order to improve the measurement precision of the laser displacement ***,the cause of the error caused by the measured surface features is analyzed from the measurement principle of laser ***,according to the resul...
详细信息
In order to improve the measurement precision of the laser displacement ***,the cause of the error caused by the measured surface features is analyzed from the measurement principle of laser ***,according to the result of error analysis,the kalman filter algorithm is applied to the sensor data to carry out error ***,the experiments were carried out with LS-100 CP laser displacement sensor and *** experimental results show that the kalman filter algorithm in the application of laser triangula tion measurement is feasible,effective and have a good practical value.
The purpose of this study is to optimize the observation condition on the inverse problem for estimating the real and imaginary parts of the concrete conductivity and the impedance of the steel-concre
The purpose of this study is to optimize the observation condition on the inverse problem for estimating the real and imaginary parts of the concrete conductivity and the impedance of the steel-concre
In order to solve the problem of geocoordinate measurement and trajectory distribution of buried long oil and gas pipelines, the positioning accuracy of pipeline is improved. In this paper, the data fusion of the mile...
详细信息
In order to solve the problem of geocoordinate measurement and trajectory distribution of buried long oil and gas pipelines, the positioning accuracy of pipeline is improved. In this paper, the data fusion of the mileage data by kalmanfiltering algorithm is used to solve the segmented trajectories of gyroscope and accelerometer observation data collected by inertial navigation system. Calculating the total mileage of 49.902 km, each position error with checkpoint contrast are controlled to less than 1 m. The overall trend with map match exactly, integrated positioning accuracy is 0.928 ‰. It has a certain reference for using inertial navigation technology buried long distance oil and gas pipeline geographic coordinates measurement.
暂无评论