隨著室內空間規模不斷擴展，具備低硬體門檻且高精準度的導航系統成為發展關鍵。然而，長廊等室內場景常伴隨感知混淆與特徵重複的挑戰，且純 CPU 架構難以負荷深度學習模型的即時運算。為克服單目視覺在複雜場域中的定位不穩定性，本研究針對靜態環境進行研究進而設計拓撲(Topology)約制視覺地點辨識（Visual Place Recognition, VPR）之室內導航（TopoVPR），其核心在於無縫融合階層化定位機制與空間拓撲網路。
基準測試確認了AKAZE (Accelerated KAZE)演算法在純 CPU 條件下能達到運算效率與匹配精度的最佳平衡。配合全景分區檢索策略，系統不僅將檢索時間大幅壓縮至 6.18 秒，更維持了高達 96.20% 的 Top-5 準確率，表現足以媲美複雜神經網路。系統進一步導入階層化動態解算架構，涵蓋高信心度直接鎖定、動態特徵過濾及盲區退化模式，成功突破室內定位的亞米級（Sub-meter）門檻，締造出平均誤差 0.99 公尺、標準差 0.73 公尺的表現。
面對重複紋理引發的坐標瞬移現象，空間拓撲約制邏輯發揮了關鍵的過濾作用，將全局誤匹配引發的定位跳變率由 42.1% 徹底降至零，確保了導航軌跡的絕對連貫。此外，整合 A* 最短路徑搜尋與三次樣條曲線（Cubic Spline）平滑技術後，系統能於 30 毫秒內快速生成契合人類步行習慣的導引路徑，大幅提升整體流暢度與舒適性。
綜合上述技術體系，建構出的視覺導航系統完美兼具低延遲、高穩健與精準度。實地於政大綜院進行的交叉驗證，充分印證了階層化架構搭配空間先驗資訊的實證價值，為未來室內導航技術的大型應用部署確立了極具參考價值的技術範式。

The geometric complexity of expanding indoor environments exposes a critical need for GNSS-denied tracking methodologies that balance low computational overhead with rigorous positional precision. Monocular observation algorithms frequently encounter trajectory drift in static scenes, a vulnerability exacerbated by geometric feature homogeneity in corridor-like structures and the latency of deep learning inferences on CPU-bound hardware. To mitigate these inherent sensory ambiguities and algorithmic limitations, the TopoVPR architecture enforces spatial connectivity constraints intertwined with a stratified registration framework, securing robust spatial orientation for complex indoor mapping operations.
Leveraging the AKAZE algorithm alongside a panoramic zonal retrieval strategy optimizes CPU execution, curtailing retrieval latency to 6.18 seconds while sustaining a deep-learning-comparable 96.20% Top-5 accuracy. Furthermore, a dynamic hierarchical resolution framework—incorporating adaptive filtering and blind-spot mitigation—achieves sub-meter tracking precision, yielding a mean localization error of 0.99 meters (SD = 0.73m).
Applying spatial topological constraints eradicates coordinate teleportation caused by global visual ambiguities, reducing the localization jump rate from 42.1% to zero to ensure seamless trajectory coherence. Combining A* pathfinding with cubic spline smoothing rapidly generates natural guidance curves within 30 milliseconds. Cross-validated at the National Chengchi University complex, this low-latency architecture establishes a robust blueprint for scalable indoor visual navigation.

A, Y. L., Kuushalie, A., Yerukola, G., & K, A. M. (2024). Efficiency Analysis of Conventional and Weighted Grid-Based Pathfinding Algorithms: A Performance Comparative Study. 2024 Third International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), 1–6. https://doi.org/10.1109/ICEEICT61591.2024.10718412
AL-Taharwa. (2008). A Mobile Robot Path Planning Using Genetic Algorithm in Static Environment. Journal of Computer Science, 4(4), 341–344. https://doi.org/10.3844/jcssp.2008.341.344
Ansar, E., Sewil, S., Maksood, F. Z., & Feo-Flushing, E. (2024). Performance Evaluation of Feature Detectors and Descriptors with Close-Range Solar Panel Images. 2024 IEEE International Conference on Visual Communications and Image Processing (VCIP), 1–5. https://doi.org/10.1109/VCIP63160.2024.10849783
Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2018). NetVLAD: CNN Architecture for Weakly Supervised Place Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1437–1451. https://doi.org/10.1109/TPAMI.2017.2711011
Arshad, S., & Park, T.-H. (2024). SVS-VPR: A Semantic Visual and Spatial Information-Based Hierarchical Visual Place Recognition for Autonomous Navigation in Challenging Environmental Conditions. Sensors, 24(3), 906. https://doi.org/10.3390/s24030906
Bencak, P., Hercog, D., & Lerher, T. (2022). Indoor Positioning System Based on Bluetooth Low Energy Technology and a Nature-Inspired Optimization Algorithm. Electronics, 11(3), 308. https://doi.org/10.3390/electronics11030308
Borenstein, J., & Koren, Y. (1991). The vector field histogram-fast obstacle avoidance for mobile robots. IEEE Transactions on Robotics and Automation, 7(3), 278–288. https://doi.org/10.1109/70.88137
Chen, S., Guo, X., Li, Y., Zhang, T., Lin, M., Kuang, D., Zhang, Y., Ming, L., Zhang, F., Wang, Y., Xu, J., Zhou, Z., & Chen, W. (2025). Ocean-OCR: Towards General OCR Application via a Vision-Language Model (arXiv:2501.15558). arXiv. https://doi.org/10.48550/arXiv.2501.15558
Chun, B.-G., Ihm, S., Maniatis, P., Naik, M., & Patti, A. (2011). CloneCloud: Elastic execution between mobile device and cloud. Proceedings of the Sixth Conference on Computer Systems, 301–314. https://doi.org/10.1145/1966445.1966473
Cioffi, G., & Scaramuzza, D. (2020). Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry (arXiv:2003.04159). arXiv. https://doi.org/10.48550/arXiv.2003.04159
Daniel, K., Nash, A., Koenig, S., & Felner, A. (2010). Theta*: Any-Angle Path Planning on Grids. Journal of Artificial Intelligence Research, 39, 533–579. https://doi.org/10.1613/jair.2994
Dingfu Zhou, Dai, Y., & Hongdong Li. (2016). Reliable scale estimation and correction for monocular Visual Odometry. 2016 IEEE Intelligent Vehicles Symposium (IV), 490–495. https://doi.org/10.1109/IVS.2016.7535431
Enqvist, O., Kahl, F., & Olsson, C. (2011). Non-sequential structure from motion. 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 264–271. https://doi.org/10.1109/ICCVW.2011.6130252
Fajrianti, E. D., Funabiki, N., Haz, A. L., & Sukaridhoto, S. (2023). A Proposal of OCR-based User Positioning Method in Indoor Navigation System Using Unity and Smartphone (INSUS). Proceedings of the 2023 12th International Conference on Networks, Communication and Computing, 99–105. https://doi.org/10.1145/3638837.3638852
Fan, Y., & Sun, H. (2024). Environmental causality calibration: Advancing WLAN RF fingerprinting for precise indoor localization. PLOS ONE, 19(2), e0297108. https://doi.org/10.1371/journal.pone.0297108
Feghali, J. M., Feng, C., Majumdar, A., & Ochieng, W. Y. (2024). Comprehensive Review: High-Performance Positioning Systems for Navigation and Wayfinding for Visually Impaired People. Sensors, 24(21), 7020. https://doi.org/10.3390/s24217020
Feng, C., Han, P., Zhang, X., Yang, B., Liu, Y., & Guo, L. (2022). Computation offloading in mobile edge computing networks: A survey. Journal of Network and Computer Applications, 202, 103366. https://doi.org/10.1016/j.jnca.2022.103366
Galvez-López, D., & Tardos, J. D. (2012). Bags of Binary Words for Fast Place Recognition in Image Sequences. IEEE Transactions on Robotics, 28(5), 1188–1197. https://doi.org/10.1109/TRO.2012.2197158
Handy Permana, S. D., Yogha Bintoro, K. B., Arifitama, B., & Syahputra, A. (2018). Comparative Analysis of Pathfinding Algorithms A *, Dijkstra, and BFS on Maze Runner Game. IJISTECH (International Journal Of Information System & Technology), 1(2), 1. https://doi.org/10.30645/ijistech.v1i2.7
Hart, P., Nilsson, N., & Raphael, B. (1968). A Formal Basis for the Heuristic Determination of Minimum Cost Paths. IEEE Transactions on Systems Science and Cybernetics, 4(2), 100–107. https://doi.org/10.1109/TSSC.1968.300136
Hartley, R., & Zisserman, A. (2018). Multiple view geometry in computer vision (2. edition, 17.printing). Cambridge Univ. Press.
Hu, J., Nie, J., Ning, Z., Feng, C., Wang, L., Li, J., & Cheng, S. (2024). Enhancing Visual Place Recognition With Hybrid Attention Mechanisms in MixVPR. IEEE Access, 12, 159847–159859. https://doi.org/10.1109/ACCESS.2024.3487171
Isik, M. (2024). Comprehensive empirical evaluation of feature extractors in computer vision. PeerJ Computer Science, 10, e2415. https://doi.org/10.7717/peerj-cs.2415
Jegou, H., Douze, M., Schmid, C., & Perez, P. (2010). Aggregating local descriptors into a compact image representation. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 3304–3311. https://doi.org/10.1109/CVPR.2010.5540039
Jing, J., Liu, S., Wang, G., Zhang, W., & Sun, C. (2022). Recent advances on image edge detection: A comprehensive review. Neurocomputing, 503, 259–271. https://doi.org/10.1016/j.neucom.2022.06.083
Jondhale, S. R., Jondhale, A. S., Deshpande, P. S., & Lloret, J. (2021). Improved trilateration for indoor localization: Neural network and centroid-based approach. International Journal of Distributed Sensor Networks, 17(11), 15501477211053997. https://doi.org/10.1177/15501477211053997
Khoshelham, K., & Zlatanova, S. (2016). Sensors for Indoor Mapping and Navigation. Sensors, 16(5), 655. https://doi.org/10.3390/s16050655
Kwok, C. Y. T., Wong, M. S., Griffiths, S., Wong, F. Y. Y., Kam, R., Chin, D. C. W., Xiong, G., & Mok, E. (2020). Performance Evaluation of iBeacon Deployment for Location-Based Services in Physical Learning Spaces. Applied Sciences, 10(20), 7126. https://doi.org/10.3390/app10207126
Lan, D. T., & Yoon, S. (2023). Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement. Sensors, 23(6), 3318. https://doi.org/10.3390/s23063318
Lewis, R. (2023). A Comparison of Dijkstra’s Algorithm Using Fibonacci Heaps, Binary Heaps, and Self-Balancing Binary Trees (arXiv:2303.10034). arXiv. https://doi.org/10.48550/arXiv.2303.10034
Likhachev, M., Gordon, G., & Thrun, S. (n.d.). ARA*: Anytime A* with Provable Bounds on Sub-Optimality.
Liu, H., Darabi, H., Banerjee, P., & Liu, J. (2007). Survey of Wireless Indoor Positioning Techniques and Systems. IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 37(6), 1067–1080. https://doi.org/10.1109/TSMCC.2007.905750
Liu, J., Mao, Y., Zhang, J., & Letaief, K. B. (2016). Delay-optimal computation task scheduling for mobile-edge computing systems. 2016 IEEE International Symposium on Information Theory (ISIT), 1451–1455. https://doi.org/10.1109/ISIT.2016.7541539
Liu, Y., Ma, L., Wang, X., & Meng, W. (2019). An Epipolar Geometry-Based Approach for Vision-Based Indoor Localization. In Q. Liang, J. Mu, M. Jia, W. Wang, X. Feng, & B. Zhang (Eds.), Communications, Signal Processing, and Systems (Vol. 463, pp. 2643–2652). Springer Singapore. https://doi.org/10.1007/978-981-10-6571-2_320
Lowe, D. G. (2004). Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60(2), 91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
Lowry, S., Sünderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., & Milford, M. J. (2016). Visual Place Recognition: A Survey. IEEE Transactions on Robotics, 32(1), 1–19. https://doi.org/10.1109/TRO.2015.2496823
Łukasik, S., Szott, S., & Leszczuk, M. (2024). Multimodal Image-Based Indoor Localization with Machine Learning—A Systematic Review. Sensors, 24(18), 6051. https://doi.org/10.3390/s24186051
Mach, P., & Becvar, Z. (2017). Mobile Edge Computing: A Survey on Architecture and Computation Offloading. IEEE Communications Surveys & Tutorials, 19(3), 1628–1656. https://doi.org/10.1109/COMST.2017.2682318
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015). ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics, 31(5), 1147–1163. https://doi.org/10.1109/TRO.2015.2463671
Mustafa, A. (n.d.). A High Fidelity Indoor Navigation System for Users in Motion Using BLE with Beacons.
Nagano, A. (2021). Three-dimensional videography using omnidirectional cameras: An approach inspired by the direct linear transformation method. Journal of Biomechanics, 128, 110722. https://doi.org/10.1016/j.jbiomech.2021.110722
Nowicki, M. R., & Skrzypczyński, P. (2019). Leveraging Visual Place Recognition to Improve Indoor Positioning with Limited Availability of WiFi Scans. Sensors, 19(17), 3657. https://doi.org/10.3390/s19173657
Potortì, F., Palumbo, F., & Crivello, A. (2020). Sensors and Sensing Technologies for Indoor Positioning and Indoor Navigation. Sensors, 20(20), 5924. https://doi.org/10.3390/s20205924
Qingqing, L., Queralta, J. P., Gia, T. N., & Westerlund, T. (2019). Offloading Monocular Visual Odometry with Edge Computing: Optimizing Image Quality in Multi-Robot Systems. Proceedings of the 2019 5th International Conference on Systems, Control and Communications, 22–26. https://doi.org/10.1145/3377458.3377467
Rachmawati, D., & Gustin, L. (2020). Analysis of Dijkstra’s Algorithm and A* Algorithm in Shortest Path Problem. Journal of Physics: Conference Series, 1566(1), 012061. https://doi.org/10.1088/1742-6596/1566/1/012061
Salmeron-Garcia, J., Inigo-Blasco, P., Diaz-del-Rio, F., & Cagigas-Muniz, D. (2015). A Tradeoff Analysis of a Cloud-Based Robot Navigation Assistant Using Stereo Image Processing. IEEE Transactions on Automation Science and Engineering, 12(2), 444–454. https://doi.org/10.1109/TASE.2015.2403593
Sarlin, P.-E., Cadena, C., Siegwart, R., & Dymczyk, M. (2019). From Coarse to Fine: Robust Hierarchical Localization at Large Scale (arXiv:1812.03506). arXiv. https://doi.org/10.48550/arXiv.1812.03506
Sheng, D., Yang, A., Rizzo, J.-R., & Feng, C. (2024). NYC-Indoor-VPR: A Long-Term Indoor Visual Place Recognition Dataset with Semi-Automatic Annotation. 2024 IEEE International Conference on Robotics and Automation (ICRA), 14853–14859. https://doi.org/10.1109/ICRA57147.2024.10610564
Shi, Y., Huang, S., & Li, M. (2024). An Improved Global and Local Fusion Path-Planning Algorithm for Mobile Robots. Sensors, 24(24), 7950. https://doi.org/10.3390/s24247950
Song, Y., Li, Q., Li, B., Xu, J., & Zheng, N. (2006). Real-Time Dynamic Display on Spatial Data for Car Navigation Service. 2006 6th International Conference on ITS Telecommunications, 94–97. https://doi.org/10.1109/ITST.2006.288788
Stentz, A. (n.d.-a). The D*Algorithm for Real-Time Planning of Optimal Traverses.
Stentz, A. (n.d.-b). The Focussed D* Algonthm for Real-Time Replanning.
Subhan, F., Khan, A., Saleem, S., Ahmed, S., Imran, M., Asghar, Z., & Bangash, J. I. (2022). Experimental analysis of received signals strength in Bluetooth Low Energy (BLE) and its effect on distance and position estimation. Transactions on Emerging Telecommunications Technologies, 33(2), e3793. https://doi.org/10.1002/ett.3793
Tang, G., Tang, C., Claramunt, C., Hu, X., & Zhou, P. (2021). Geometric A-Star Algorithm: An Improved A-Star Algorithm for AGV Path Planning in a Port Environment. IEEE Access, 9, 59196–59210. https://doi.org/10.1109/ACCESS.2021.3070054
Team, G., Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., Silver, D., Johnson, M., Antonoglou, I., Schrittwieser, J., Glaese, A., Chen, J., Pitler, E., Lillicrap, T., Lazaridou, A., … Vinyals, O. (2025). Gemini: A Family of Highly Capable Multimodal Models (arXiv:2312.11805). arXiv. https://doi.org/10.48550/arXiv.2312.11805
Wang, X., Zhang, H., Yin, X., Du, M., & Chen, Q. (2018). Monocular Visual Odometry Scale Recovery Using Geometrical Constraint. 2018 IEEE International Conference on Robotics and Automation (ICRA), 988–995. https://doi.org/10.1109/ICRA.2018.8462902
Wang, Y., Yu, Z., Zhu, L., & Yang, H. (2022). Trace-Navi: A High-Accuracy Indoor Navigation System Based on Real-Time Activity Recognition and Discrete Trajectory Calibration. In Y. Lai, T. Wang, M. Jiang, G. Xu, W. Liang, & A. Castiglione (Eds.), Algorithms and Architectures for Parallel Processing (Vol. 13155, pp. 288–303). Springer International Publishing. https://doi.org/10.1007/978-3-030-95384-3_19
Wu, B., Chi, X., Zhao, C., Zhang, W., Lu, Y., & Jiang, D. (2022). Dynamic Path Planning for Forklift AGV Based on Smoothing A* and Improved DWA Hybrid Algorithm. Sensors, 22(18), 7079. https://doi.org/10.3390/s22187079
Xu, S., Chen, C.-C., Wu, Y., Wang, X., & Wei, F. (2020). Adaptive Residual Weighted K-Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication. Sensors, 20(16), 4432. https://doi.org/10.3390/s20164432
Yang, Q., Xu, H., Song, M., & Li, M. (2025). Demo: WiMU: Real-time Indoor Localization via Wi-Fi/IMU Fusion with Minimal Site Survey. Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services, 629–630. https://doi.org/10.1145/3711875.3734375
Yang, X., Zheng, Y., Huang, H., & Ma, X. (2023). Research on robot indoor automatic navigation algorithm. 2023 9th International Conference on Computer and Communications (ICCC), 1286–1290. https://doi.org/10.1109/ICCC59590.2023.10507636
Yassin, A., Nasser, Y., Awad, M., Al-Dubai, A., Liu, R., Yuen, C., Raulefs, R., & Aboutanios, E. (2017). Recent Advances in Indoor Localization: A Survey on Theoretical Approaches and Applications. IEEE Communications Surveys & Tutorials, 19(2), 1327–1346. https://doi.org/10.1109/COMST.2016.2632427
Yin, X., Wang, X., Du, X., & Chen, Q. (2017). Scale Recovery for Monocular Visual Odometry Using Depth Estimated with Deep Convolutional Neural Fields. 2017 IEEE International Conference on Computer Vision (ICCV), 5871–5879. https://doi.org/10.1109/ICCV.2017.625
Yuan, W., Poosa, S. R. P., & Dirks, R. F. (2024). Comparative Analysis of Color Space and Channel, Detector, and Descriptor for Feature-Based Image Registration. Journal of Imaging, 10(5), 105. https://doi.org/10.3390/jimaging10050105
Yusuf, Z., Mohamad, S., & Wan Ibrahim, W. S. (2025). Performance Comparison of A* and Dijkstra Algorithms with Bézier Curve in 2D Grid and OpenStreetMap Scenarios. Journal of Applied Engineering Design and Simulation, 5(2), 79–89. https://doi.org/10.24191/jaeds.v5i2.94
Yuzawa, K., & Fujii, T. (2024). Indoor Positioning using BLE Beacons and User Equipments in Factory Environment. 2024 Fifteenth International Conference on Ubiquitous and Future Networks (ICUFN), 28–33. https://doi.org/10.1109/ICUFN61752.2024.10625482
Zafari, F., Gkelias, A., & Leung, K. K. (2019). A Survey of Indoor Localization Systems and Technologies. IEEE Communications Surveys & Tutorials, 21(3), 2568–2599. https://doi.org/10.1109/COMST.2019.2911558
Zhang, B., & Zhu, D. (2021). A new method on motion planning for mobile robots using jump point search and Bezier curves. International Journal of Advanced Robotic Systems, 18(4), 17298814211019220. https://doi.org/10.1177/17298814211019220
Zhang, D., Chen, C., & Zhang, G. (2024). AGV Path Planning Based on Improved A-star Algorithm. 2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 1590–1595. https://doi.org/10.1109/IAEAC59436.2024.10503919
Zhang, H., Wang, X., Yin, X., Du, M., Liu, C., & Chen, Q. (2022). Geometry-Constrained Scale Estimation for Monocular Visual Odometry. IEEE Transactions on Multimedia, 24, 3144–3156. https://doi.org/10.1109/TMM.2021.3093771
Zhang, L., Zhao, C., Wang, Y., & Dai, L. (2020). Fingerprint-based Indoor Localization using Weighted K-Nearest Neighbor and Weighted Signal Intensity. Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture, 185–191. https://doi.org/10.1145/3421766.3421813
Zhao, Z.-Q., Zheng, P., Xu, S., & Wu, X. (2019). Object Detection with Deep Learning: A Review (arXiv:1807.05511). arXiv. https://doi.org/10.48550/arXiv.1807.05511
Zheng, P., Qin, D., Bai, J., & Ma, L. (2023). An Indoor Visual Positioning Method with 3D Coordinates Using Built-In Smartphone Sensors Based on Epipolar Geometry. Micromachines, 14(6), 1097. https://doi.org/10.3390/mi14061097
Zhou, D., Dai, Y., & Li, H. (2020). Ground-Plane-Based Absolute Scale Estimation for Monocular Visual Odometry. IEEE Transactions on Intelligent Transportation Systems, 21(2), 791–802. https://doi.org/10.1109/TITS.2019.2900330
Zhou, X., Chen, T., Guo, D., Teng, X., & Yuan, B. (2018). From one to crowd: A survey on crowdsourcing-based wireless indoor localization. Frontiers of Computer Science, 12(3), 423–450. https://doi.org/10.1007/s11704-017-6520-z
Zhu, X., Yan, B., & Yue, Y. (2021). Path Planning and Collision Avoidance in Unknown Environments for USVs Based on an Improved D* Lite. Applied Sciences, 11(17), 7863. https://doi.org/10.3390/app11177863