本篇論文提出了一套針對小型室內空間的定位系統，該系統基於從使用者攜帶的多個鏡頭收集的影像和來自使用者裝置的無線信號來進行定位。我們提出的系統將無線信號的接收信號強度（Received Signal Strength Indicator, RSSI）轉換為無線指紋，並提出了一種基於物件辨識模型將影像中的資訊轉換為影像指紋的方法。然後透過本文提出的多模態數據融合演算法將兩種類型的指紋相結合，以提高小型室內環境中的定位精準度。我們在一間辦公室進行了一系列實驗，並與現有的2種基於無線指紋的定位方法進行了比較。結果表明，我們提出的方法在實驗中至少比其他 2 個方法好 31.7%。此外，根據實驗結果，我們的系統可以減少部分物件被遮擋、較少Beacon部署或裝置封包接收能力不同等對準確性造成的影響。

In this paper, we propose a positioning system focus on small-scale indoor environment based on images collected from multiple cameras carried by user and wireless signal from user's devices. Our proposed system convert received signal strength indicator(RSSI) of wireless signal into wireless fingerprint and propose a method that convert images' information into image fingerprints based on object detection model. Then our proposed system combine the 2 types of fingerprint by a proposed multi-modal data fusion algorithm to improve the position accuracy in small-scale indoor environment. We performed a series of experiments in an office and compare with 2 existing positioning method based on wireless fingerprint. The results show that our proposed method is at least 31.7% better than the other 2 baseline methods in the experiments. Also, according to the experimental results, our system can reduce the impact on accuracy of problems such as blocked objects, less beacon deployment, and device heterogeneity.

[1] C.-W. Lee, P. Chondro, S.-J. Ruan, O. Christen, and E. Naroska, “Improving
mobility for the visually impaired: A wearable indoor positioning system based
on visual markers,” IEEE Consumer Electronics Magazine, vol. 7, no. 3, pp. 12–20,
2018.
[2] Y. Bai, W. Jia, H. Zhang, Z.-H. Mao, and M. Sun, “Landmark-based indoor positioning for visually impaired individuals,” in 2014 12th International Conference on Signal Processing (ICSP). IEEE, 2014, pp. 668–671.
[3] T. A. Heya, S. E. Arefin, A. Chakrabarty, and M. Alam, “Image processing based indoor localization system for assisting visually impaired people,” in 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS). IEEE, 2018, pp. 1–7.
[4] C.-H. Huang, L.-H. Lee, C. C. Ho, L.-L. Wu, and Z.-H. Lai, “Real-time rfid indoor positioning system based on kalman-filter drift removal and heron-bilateration location estimation,” IEEE Transactions on Instrumentation and Measurement, vol. 64, no. 3, pp. 728–739, 2014.
[5] S. Yang and B. Wang, “Residual based weighted least square algorithm for bluetooth/uwb indoor localization system,” in 2017 36th Chinese Control Conference (CCC). IEEE, 2017, pp. 5959–5963.
[6] L. Chen, K. Yang, and X.Wang, “Robust cooperative wi-fi fingerprint-based indoor localization,” IEEE Internet of Things Journal, vol. 3, no. 6, pp. 1406–1417, 2016.
[7] C. Park and S. H. Rhee, “Indoor positioning using wi-fi fingerprint with signal clustering,” in 2017 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 2017, pp. 820–822.
[8] S.-I. Sou, W.-H. Lin, K.-C. Lan, and C.-S. Lin, “Indoor location learning over wireless fingerprinting system with particle markov chain model,” IEEE Access, vol. 7, pp. 8713–8725, 2019.
[9] W.-C. Wu, Multi-Device Indoor Positioning System based on wireless fingerprinting system, Unpublished master’s thesis, National Cheng Kung University, Tainan, Taiwan, 2020.
[10] F. Campana, A. Pinargote, F. Dominguez, and E. Pelaez, “Towards an indoor navigation system using bluetooth low energy beacons,” in 2017 IEEE second ecuador technical chapters meeting (ETCM). IEEE, 2017, pp. 1–6.
[11] A. Xiao, R. Chen, D. Wu, and Y. Chen, “Positioning in large indoor spaces using smartphone camera based on static objects,” in 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS). IEEE, 2018, pp. 1–7.
[12] Y. Xia, C. Xiu, and D. Yang, “Visual indoor positioning method using image database,” in 2018 Ubiquitous Positioning, Indoor Navigation and Location Based Services (UPINLBS). IEEE, 2018, pp. 1–8.
[13] M. Werner, M. Kessel, and C. Marouane, “Indoor positioning using smartphone camera,” in 2011 international conference on indoor positioning and indoor navigation. IEEE, 2011, pp. 1–6.
[14] G. Huang, Z. Hu, J. Wu, H. Xiao, and F. Zhang, “Wifi and vision-integrated fingerprint for smartphone-based self-localization in public indoor scenes,” IEEE Internet of Things Journal, vol. 7, no. 8, pp. 6748–6761, 2020.
[15] Z.Wang, P. Sokliep, C. Xu, J. Huang, L. Lu, and Z. Shi, “Indoor position algorithm based on the fusion of wifi and image,” in 2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI). IEEE, 2019, pp. 212 216.
[16] Y. Zhao, J. Xu, J.Wu, J. Hao, and H. Qian, “Enhancing camera-based multimodal indoor localization with device-free movement measurement using wifi,” IEEE Internet of Things Journal, vol. 7, no. 2, pp. 1024–1038, 2019.
[17] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.