Search

The three-dimensional (3D) coordinate measurement of radio frequency identification (RFID) multi-tag networks is one of the important issues in the field of RFID, which affects the reading performance of RFID multi-tag networks. In this paper, a novel method for 3D coordinate measurement of RFID multitag networks is proposed. A dual-CCD system (vertical and horizontal cameras) is used to obtain images of RFID multi-tag networks from different angles. The iterative threshold segmentation and the morphological filtering method are used to process the images. The template matching method is respectively used to determine the two-dimensional (2D) coordinate and the vertical coordinate of each tag. After that, the 3D coordinate of each tag is obtained. Finally, a back-propagation (BP) neural network is used to model the nonlinear relationship between the RFID multi-tag network and the corresponding reading distance. The BP neural network can predict the reading distances of unknown tag groups and find out the optimal distribution structure of the tag groups corresponding to the maximum reading distance. In the future work, the corresponding in-depth research on the neural network to adjust the distribution of tags will be done. [ABSTRACT FROM AUTHOR]

In the field of radio frequency identification (RFID), the three-dimensional (3D) distribution of RFID multi-tag networks has a significant impact on their reading performance. At the same time, in order to realize the anti-collision of RFID multi-tag networks in practical engineering applications, the 3D distribution of RFID multi-tag networks must be measured. In this paper, a novel method for the 3D measurement of RFID multi-tag networks is proposed. A dual-CCD system (vertical and horizontal cameras) is used to obtain images of RFID multi-tag networks from different angles. Then, the wavelet threshold denoising method is used to remove noise in the obtained images. The template matching method is used to determine the two-dimensional coordinates and vertical coordinate of each tag. The 3D coordinates of each tag are obtained subsequently. Finally, a model of the nonlinear relation between the 3D coordinate distribution of the RFID multi-tag network and the corresponding reading distance is established using the wavelet neural network. The experiment results show that the average prediction relative error is 0.71% and the time cost is 2.17 s. The values of the average prediction relative error and time cost are smaller than those of the particle swarm optimization neural network and genetic algorithm–back propagation neural network. The time cost of the wavelet neural network is about 1% of that of the other two methods. The method proposed in this paper has a smaller relative error. The proposed method can improve the real-time performance of RFID multi-tag networks and the overall dynamic performance of multi-tag networks. [ABSTRACT FROM AUTHOR]