Abstract
Smart cultural tourism is the development trend of the future tourism industry. Virtual reality is an important tool to realize smart tourism. The reality of virtual reality mainly comes from human-computer interaction, which is closely related to human action recognition technology. Therefore, the research takes human action recognition as the research direction, uses a self-organizing mapping network (SOM) neural network to extract the key frame of action video, combines it with multi-feature vector method to recognize human action, and compares the recognition rate and user satisfaction of different recognition methods. The results show that the recognition rate of multi-feature voting human action recognition algorithm based on SOM neural network is 93.68% on UT-Kinect action, 59.06% on MSRDailyActivity3D, and the overall action recognition time is only 3.59 s. Within six months, the total profit of human-computer interactive virtual reality tourism project with SOM neural network multi-eigenvector as the core algorithm reached 422,000 yuan, and 88% of users expressed satisfaction after use. It shows that the proposed method has a good recognition rate and can give users effective feedback in time. It is hoped that this research has a certain reference value in promoting the development of human motion recognition technology.
Highlights
Virtual reality technology lays the foundation for the development of smart cultural tourism, provides tourists with a new perspective, gives tourism users a sense of reality, and, at the same time, greatly reduces the resources consumed in building a variety of scenes in reality [1]
Methods proposed in the study total profit of 371,000 yuan; the human-computer interactive virtual reality tourism project integrated with joint vector naive Bayesian action recognition algorithm made a total profit of 407,000 yuan; and the human-computer interactive virtual reality tourism project integrated with machine learning made a total profit of 356,000 yuan, e humancomputer interactive virtual reality tourism project with
Evaluation and grading grade IV, accounting for 17%, 42%, 30%, and 11%, respectively. e proportion of user rating of human-computer interaction based on machine learning is 35%, 46%, 15%, and 4%, respectively. e user rating of humancomputer interactive virtual reality tourism project with self-organizing mapping network (SOM) neural network and other feature vectors as the core algorithm is 12%, 34%, 40%, and 14%, respectively
Summary
Virtual reality technology lays the foundation for the development of smart cultural tourism, provides tourists with a new perspective, gives tourism users a sense of reality, and, at the same time, greatly reduces the resources consumed in building a variety of scenes in reality [1]. Smart cultural tourism combined with virtual reality technology broadens the inherent thinking of tourists, breaks the limitations of traditional cultural tourism, breaks through the space and time limitations of tourism in real life, and enables tourists to obtain more free interaction through three-dimensional information space [2]. Erefore, this paper focuses on human action behavior recognition technology, aiming to provide some help for the development of smart cultural tourism. A self-organizing mapping network (SOM) is a kind of low-dimensional discrete mapping generated by learning the data in the input space, which gradually optimizes the network with a competitive learning strategy. It has the self-organizing characteristics of the human brain and can identify the intrinsic related characteristics in a problem [4]. This paper studies how to extract the key frames of human action video through the competitive learning characteristics of the SOM network and uses the voting strategy of multifeature classification results to carry out the final recognition of human action
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
