An intelligent stage light-based actor identification and positioning system
by Jianqing Gao; Haiyang Zou; Fuquan Zhang; Tsu-Yang Wu
International Journal of Information and Computer Security (IJICS), Vol. 18, No. 1/2, 2022

Abstract: At this stage, the lighting control method of the stage actor is still in the stage of manual adjustment, so that the follow-up light cannot accurately and timely track the actors. In order to solve the above problems, an intelligent stage light-based actor identification and positioning system using tracking algorithm based on deep convolutional neural network is proposed, which can control the lighting system to automatically track actors. Firstly, the framework of the intelligent stage light-based actor identification and positioning system was analysed, and the process of actor identification and positioning function was designed. The particle filter is then used to generate the candidate target image and input as a rectangle. Finally, the deep neural network structure is constructed by combining the feature pre-training process and the convolutional neural network, and the real-time target tracking is completed. Performance verification was performed with multiple video test sets. The test results show that compared with other algorithms, this tracking algorithm can complete rectangular target tracking with strong real-time performance and exhibits high accuracy and robustness.

Online publication date: Tue, 17-May-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Information and Computer Security (IJICS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com