A novel 3D measurement of RFID multi‐tag network based on MWCNN and ELM

Autor: Zhimin Zhao, Wenjie Zhang, Xiao Zhuang, Zhenlu Liu, Xiaolei Yu, Lin Li
Rok vydání: 2021
Předmět:
Zdroj: IET Science, Measurement & Technology, Vol 16, Iss 1, Pp 15-27 (2022)
ISSN: 1751-8830
1751-8822
DOI: 10.1049/smt2.12078
Popis: In the field of RFID, the reading performance of tags is an important performance indicator for measuring tag. Related studies have shown that the tags’ geometrical distribution has an important influence on the tags’ reading performance. In order to optimize the tags’ geometrical distribution and improve the tags’ reading performance, this paper proposes a tag distribution optimization method based on multi‐level wavelet‐CNN (MWCNN) and extreme learning machine (ELM). First, this paper designs a tag distribution optimization system based on stereo‐vision. Second, the stereo‐cameras are used to capture the images of the tags. Aiming at the degradation phenomenon in the acquired images, MWCNN is used to recover the degraded tag images. On the basis of the image restoration, the template matching method is used to obtain the 3D coordinates of the tags. Then, ELM is used to model and predict the nonlinear relationship between 3D coordinates of the tags and the corresponding reading distance. The results show that the average prediction relative error is 0.56% and the time cost is 2.0 s. The average prediction relative error of ELM is smaller than GA‐BP and PSO‐BP. The time cost of ELM is smaller than the wavelet neural network.
Databáze: OpenAIRE
Externí odkaz: