Skeleton-based action recognition is a typical classification problem which plays a significant role in human-computer interaction and video understanding. Since a human skeleton has natural graphic features, methods based on graph convolutional networks (GCN) are widely applied in skeleton-based action recognition. Previous studies mainly focus on structural links in GCN to generate high-level features of human skeleton. However, low-level features are also important in many applications. For instance, lowlevel edge gradient and color information are important for image classificaion. This paper introduces a multi-branches structure to capture different low-level features of human skeleton. We combine both highlevel and low-level features to recognize human action. We validate our method in action recognition with two skeleton datasets, NTU-RGB+D and Kinetics. Experiment results indicate that the proposed method achieves considerable improvement over some state-of-the-art methods.

Traditionally, the recognition of sound mainly focuses on the source of sound, such as level and quality. Now, the sound, the environment, and the listeners have begun to study the landscape structure, composition, and characteristics of the acoustic environment. The purpose of this paper is to study the simulation design of virtual reality voice landscape quantification based on cloud computing. Firstly, the definition and characteristics of cloud computing are described, and the key technologies of cloud computing are analyzed. Combined with the basic principles of technology selection, the virtualization technology is emphatically analyzed. By selecting 7 acoustic elements, such as traffic sound, water flow sound, fountain sound, birdsong, wind sound, rippling sound, beach sound, and seabird sound, the possible acoustic elements in a given park environment are simulated for subjective evaluation. The experimental results show that when the traffic sound is 60 dB, the evaluation result of the superimposed sound type is the same as that when the traffic sound is 50 dB. For the superimposed sound level, 30 dB and 40 dB are significantly different from 60 dB and 70 dB, respectively, 50 dB is only significantly different from 70 dB, while 60 dB is only not significantly different from 50 dB, and 70 dB evaluation is significantly different from each sound level. However, 60 dB can be regarded as the turning point of the evaluation result. When the sound level of the added sound is greater than 60 dB, the evaluation result is obviously worse.

The TVPS146’s digital video processor is used for digital video processing and image output on digital signal processing (DSP) ports. The following is a summary of the field programmable gate array (FPGA) features and programming principles. FPGA is designed by the ping-pong operation, including serial to parallel conversion design, pipeline operation, and data interface synchronization. A dance video screenshot analysis microsystem is composed of it and video dynamic image processing. Finally, according to the number of dance culture performance institutions based on the internet from 2014 to 2018, the development strategy of dance culture and creativity based on the internet is put forward. The results show that the image sharpness of the video screenshots processed by the system is improved, and the effect of enhanced processing is achieved compared to the unprocessed video screenshots. In addition, after the video screenshot processed by the system is compressed, some details are lost and the outline of the image is blurred. The combination of internet immediacy, mass, grassroots, and interactivity can accelerate the development of China’s dance culture and creative industry and provide an effective practical foundation for innovation in the development of art and culture.

No abstract

No abstract