RFID tag group recognition based on motion blur estimation and YOLOv2 improved by Gaussian algorithm

• Autorzy: Li Lin , Yu Xiao-Lei , Liu Zhen-Lu , Zhao Zhi-Min , Zhang Ke , Zhou Shan-Hao

Identyfikatory

DOI

10.24425/mms.2022.138548

• Języki publikacji: EN

Abstrakty

EN

Effective recognition of tags in the dynamic measurement system would significantly improve the reading performance of the tag group, but the blurred outline and appearance of tag images captured in motion seriously limit the effectiveness of the existing tag group recognition. Thus, this paper proposes passive tag group recognition in the dynamic environment based on motion blur estimation and improved YOLOv2. Firstly, blur angles are estimated with a Gabor filter, and blur lengths are estimated through nonlinear modelling of a Generalized Regression Neural Network (GRNN). Secondly, tag recognition based on YOLOv2 improved by a Gaussian algorithm is proposed. The features of the tag group are analyzed by the Gaussian algorithm, the region of interest of the dynamic tag is effectively framed, and the tag foreground is extracted; Secondly, the data set of tag groups are trained by the end-to-end YOLOv2 algorithm for secondary screening and recognition, and finally the specific locations of tags are framed to meet the effective identification of tag groups in different scenes. A considerable number of experiments illustrate that the fusion algorithm can significantly improve recognition accuracy. Combined with the reading distance, the research presented in this paper can more accurately optimize the three-dimensional structure of the tag group, improve the reading performance of the tag group, and avoid the interference and collision of tags in the communication channel. Compared with the previous template matching algorithm, the tag group recognition ability put forward in this paper is improved by at least 13.9%, and its reading performance is improved by at least 6.2% as shown in many experiments.

Słowa kluczowe

EN

RFID; YOLOv2; neural network; GRNN

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2022
• Tom: Vol. 29, nr 1
• Strony: 53--74
• Opis fizyczny: Bibliogr. 32 poz., rys., tab., wykr., wzory

Twórcy

autor

Li Lin

• College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
• National Quality Supervision and Testing Center for RFID Product Jiangsu, Nanjing 210029, China

autor

Yu Xiao-Lei

• College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
• National Quality Supervision and Testing Center for RFID Product Jiangsu, Nanjing 210029, China

autor

Liu Zhen-Lu

• College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

autor

Zhao Zhi-Min

• College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

autor

Zhang Ke

• College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

autor

Zhou Shan-Hao

• College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Bibliografia

• [1] Jankowski-Mihułowicz T., & Węglarski M. (2016). A Method for Measuring the Radiation Pattern of UHF RFID Transponders. Metrology and Measurement Systems, 23(2), 163-172. https://doi.org/10.1515/mms-2016-0018
• [2] Grover A., & Berghel H. (2011). A survey of RFID deployment and security issues. Journal of Information Processing Systems, 7(4), 561-580. https://doi.org/10.3745/JIPS.2011.7.4.561
• [3] Rehman, K., & Nawaz, F. (2020). Localization of Static Passive RFID Tags with Mobile Reader in Two Dimensional Tag Matrix. Wireless Personal Communications, 114(1), 609-628. https://doi.org/10.1007/s11277-020-07384-1
• [4] Athalye, A., Savic, V., Bolic, M. & Djuric, P. M. (2012). Novel semi-passive RFID system for indoor localization. IEEE Sensors Journal, 13(2), 528-537. htlps://doi.org/10.1109/JSEN.2012.2220344
• [5] Ni, L. M., Liu, Y., Lau, Y. C. & Patil, A. P. (2003, March). LANDMARC: Indoor location sensing using active RFID. In Proceedings of the First IEEE International Conference on Pervasive Computing and Communications (PerCom 2003) (pp. 407-415). IEEE, https://doi.org/10.1109/PERCOM.2003.1192765
• [6] Zhao, Y., Liu, Y., & Ni, L. M. (2007, September). VIRE: Active RFID-based localization using virtual reference elimination. In 2007 International Conference on Parallel Processing (ICPP 2007) (pp. 56-56). IEEE. https://doi.org/10.1109/ICPP.2007.84
• [7] Jin, G. Y., Lu, X. Y., & Park, M. S. (2006, June). An indoor localization mechanism using active RFID tag. In IEEE International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing (SUTC’06) (Vol. 1, pp. 4-pp). IEEE. https://doi.org/10.1109/SUTC.2006.1636157
• [8] Shen, L., Zhang, Q., Pang, J., Xu, H., Li, P., & Xue, D. (2019). ANTspin: Efficient Absolute Localization Method of RFID Tags via Spinning Antenna. Sensors, 19(9), 2194. https://doi.org/10.3390/s19092194
• [9] Li, M., Chen, Y., Zhang, Y., Yang, J., & Du, H. (2019, June). Fusing RFID and computer vision for occlusion-aware object identifying and tracking. In International Conference on Wireless Algorithms, Systems, and Applications (pp. 175-187). Springer, Cham. https://doi.org/10.1007/978-3-030-23597-0_14
• [10] Duan, C., Rao, X., Yang, L., & Liu, Y. (2017, May). Fusing RFID and computer vision for fine-grained object tracking. In IEEE INFOCOM 2017-IEEE Conference on Computer Communications (pp. 1-9). IEEE. https://doi.org/10.1109/INFOCOM.2017.8057161
• [11] Wang, Z., Xu, M., Ye, N., Wang. R., & Huang, H. (2019). RF-Focus: Computer vision-assisted region-of-interes RFID tag recognition and localization in multipath-prevalent environments. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 3(1), 1-30. https://doi.org/10.1145/3314416
• [12] Zhuang, X., Yu, X., Zhou, D., Zhao, Z., Zhang, W., Li, L., & Liu, Z. (2019). A novel 3D position measurement and structure prediction method for RFID tag group based on deep belief network. Measurement, 136, 25-35. https://doi.org/10.1016/j.measurement.2018.12.071
• [13] Li, L., Yu, X., Jin, Z., Zhao, Z., Zhuang, X., & Liu, Z. (2020). FDnCNN-based image denoising for multi-label localization measurement. Measurement, 152, 107367. https://doi.org/10.1016/j.measurement.2019.107367
• [14] Li, L., Yu, X. L., Zhuang, X., Zhao, Z. M., Zhu, X. Y., Liu, Z. L., & Dong, D. B. (2020). Optimization of Radio-frequency Identification (RFID) Multi-tag Topology Based on Laser Ranging and Mind Evolutionary Algorithm (MEA). Lasers in Engineering, 45(1-3), 15-34.
• [15] Yu, Y., Yu, X., Zhao, Z., Qian, K., & Wang, D. (2018). Image analysis system for optimal geometric distribution of RFID tags based on flood fill and DLT. IEEE Transactions on Instrumentation and Measurement, 67(4), 839-848. https://doi.org/10.1109/TIM.2017.2789122
• [16] Zhuang, X., Yu, X., Zhao, Z., Wang, D., Zhang, W., Liu, Z., Lu, D. & Dong, D. (2018). A novel method for 3D measurement of RFID multi-tag network based on matching vision and wavelet. Measurement Science and Technology, 29(7), 075001. https://doi.org/10.1088/1361-6501/aabcac
• [17] Yu, Y., Yu, X., Zhao, Z., Liu, J., & Wang, D. (2017). Optimal Distribution of Radio Frequency Identification (RFID) Multiple Tags Based on a Support Vector Machine (SVM) and Laser Ranging. Lasers in Engineering, 38(1-2), 109-124.
• [18] Dobeš, M., Machala, L., & Fürst, T. (2010). Blurred image restoration: A fast method of finding the motion length and angle. Digital Signal Processing, 20(6), 1677-1686. https://doi.org/10.1016/j.dsp.2010.03.012
• [19] Zhuo, H. B., Bai, F. Z., & Xu, Y. X. (2020). Machine vision detection of pointer features in images of analog meter displays. Metrology and Measurement Systems, 27(4), 589-599. https://doi.org/10.24425/mms.2020.134840
• [20] Ta, Q. B., & Kim, J. T. (2020). Monitoring of Corroded and Loosened Bolts in Steel Structures via Deep Learning and Hough Transforms. Sensors, 20(23), 6888. https://doi.org/10.3390/s20236888
• [21] Shu, Y., & Gao, M. C. (2004). Restoration of the Image Blurred by Motion at Arbitrary Direction. Computer Engineering and Applications Journal, 31, 361-368.
• [22] Dash, R., & Majhi, B. (2014). Motion blur parameters estimation for image restoration. Optik, 125(5), 1634-1640. https://doi.org/10.1016/j.ijleo.2013.09.026
• [23] Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-lime object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 779-788). https://doi.org/10.1109/CVPR.2016.91
• [24] Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 7263-7271). https://doi.org/10.1109/CVPR.2017.690
• [25] Kessentini, Y., Besbes, M. D., Ammar, S., & Chabbouh, A. (2019). A two-stage deep neural network for multi-norm license plate detection and recognition. Expert Systems with Applications, 136, 159-170. https://doi.org/10.1016/j.eswa.2019.06.036
• [26] Wang, X., Yang, L. T., Li, H., Lin, M., Han, J., & Apduhan, B. O. (2019). NQA: A nested anti-collision algorithm tor RFID systems. ACM Transactions on Embedded Computing Systems, 18(4), 1-21. https://doi.org/10.1145/3330139
• [27] Alilou, V. K., & Yaghmaee, F. (2015). Application of GRNN neural network in non-texture image inpainting and restoration. Pattern Recognition Letters. 62, 24-31. https://doi.org/10.1016/j.patrec.2015.04.020
• [28] Li, A., Yang, X., Xic, Z., & Yang, C. (2019). An optimized GRNN-enabled approach for power transformer fault diagnosis. IEEJ Transactions on Electrical and Electronic Engineering, 14(8), 1181-1188. https://doi.org/10.1002/tee.22916
• [29] Wang, J., Chen, R, Zheng, N., Chen, B., Principe, J. C., & Wang, F. Y. (2021). Associations between MSE and SSIM as cost functions in linear decomposition with application to bit allocation for sparse coding. Neurocomputing, 422, 139-149. https://doi.org/10.1016/j.neucom.2020.10.018
• [30] Haouassi, S., & Wu, D. (2020). Image dehazing based on (CMTnet) cascaded multi-scale convolutional neural networks and efficient light estimation algorithm. Applied Sciences, 10(3), 1190. https://doi.org/10.3390/app10031190
• [31] Yu, X., Zhou, Y., Liu, Z., & Zhao, Z. (2019). An optimal measurement method for spatial distribution of radio frequency identification multi-tag based on image analysis and PSO. Transactions of the Institute of Measurement and Control, 41(12), 3331-3339. https://doi.org/10.1177%fo2F0142331218823864
• [32] Stauffer, C., & Grimson, W. E. L. (1999, June). Adaptive background mixture models for real-time tracking. In Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149) (Vol. 2, pp. 246-252). IEEE. https://doi.org/10.1109/CVPR.1999.784637

Uwagi

1. This work was supported by the National Natural Science Foundation of China (NNSFC) (61771240) and the Six Talent Peaks Project in Jiangsu Province of China (XYDXX-058).

2. Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).