進階搜尋


下載電子全文  
系統識別號 U0026-1308201817225400
論文名稱(中文) 基於電腦視覺及卷積神經網路進行行人航位未對準改正以改善手機行人導航
論文名稱(英文) Misalignment correction with computer vision and CNN for smartphone PDR
校院名稱 成功大學
系所名稱(中) 測量及空間資訊學系
系所名稱(英) Department of Geomatics
學年度 106
學期 2
出版年 107
研究生(中文) 蘇梓喬
研究生(英文) Tz-Chiau Su
學號 P66054141
學位類別 碩士
語文別 英文
論文頁數 138頁
口試委員 指導教授-張秀雯
口試委員-詹紹勳
口試委員-呂學展
中文關鍵字 未對準角  室內定位  行人航位推算  電腦視覺  深度學習 
英文關鍵字 Misalignment  Indoor Positioning  Pedestrian Dead Reckoning  Computer Vision  Convolutional Neural Network 
學科別分類
中文摘要 基於衛星定位的發展成熟,其優缺點已逐漸廣為人知,達到公分級的定位精度令衛星定位技術廣泛地應用於測繪領域以及導航領域。然而,環境結構遮蔽衛星訊號的影響成為其誤差不穩定的因素,尤其當使用者長時間待在室內環境時,衛星定位顯然無法給予穩定的位置解。在諸多室內定位技術發展的時代,如何整合不同的技術以及銜接室內外導航已變成主要的課題,本研究所使用的行人航位推算(PDR)即為其中一種常見的室內定位技術。此外,近年來微機電技術的快速發展使得智慧裝置之體積大幅縮小且價格低廉,多種以智慧裝置為主體的室內定位技術逐漸地普及化,然而低精度的特性亦成為使用低成本感測器定位的硬傷。PDR的原理為根據慣性感測器特性來進行導航,相較於慣性導航系統利用積分原理的方式,PDR演算法能大幅減少低成本感測器所帶來誤差快速累積的影響,然而,PDR所需克服的問題為如何達到精密的姿態計算以及未對準角改正,前者主要著重於裝置的方位計算,以利坐標系統間的轉換以及裝置水平航向的推算,後者則著重於計算手機以及行人航向之間的未對準角,藉此將裝置航向改正為行人行進方向,上述兩者計算的準確度、自由度以及即時性大大的影響了PDR成果的穩定性以及使用上的方便性。鑒於如今深度學習以及電腦視覺的蓬勃發展,對於大量影像的處理越趨快速,本研究發現將其應用於計算手機未對準角的潛能,因此於本研究中提出多種基於電腦視覺以及深度學習進行未對準角校正的方式,期望即使於手持模式下仍能達到高準確行人導航。除了提出多種未對準角改正方法外,本研究也針對多種未對準角計算方式進行比較與分析,從而推得最佳的整合模式以優化行人導航。
英文摘要 Being an indoor positioning technique used in GNSS-denied environment, Pedestrian Dead Reckoning (PDR) is well-known for its building independent positioning algorithm. It effectively refrains from the influence due to surrounding environment, and locates the device using only self-contained sensors such as tri-axis accelerometer, tri-axis gyroscope and tri-axis magnetometer. By applying behavior recognition, step detection, step length estimation and heading estimation, the user’s walking dynamic will be modeled; then, the user’s location and the travelled trajectory can be calculated. In most researches related to PDR, the attitude of portable devices embedded with various sensors are assumed to be fixed with respect to the user. However, this assumption will be reasonable only when the device is placed in pocket, fixed on foot, fixed on belt, etc. For above situation, the misalignment between sensor frame and pedestrian frame should be constant or merely regularly varying. However, when the handheld mode PDR is applied, there will be various unpredictable behaviors and vibrations cause irregular misalignment. Thus, how to effectively and precisely estimate the misalignment in high hand dynamic situation forms the target of this research. Thanks to the development of technology, computer vision and Convolutional Neural Network (CNN) have become popular in recent years. These technologies have been successfully and widely implemented in many applications such as image recognition, obstacle detection and motion tracking. To enable the usage of sensors in non-constrained ways, computer vision-based and CNN-based methods are used for misalignment correction in this research. In the result, the analysis of misalignment estimation will be provided. Besides, the corrected PDR trajectory is also given for validating the effectiveness of misalignment correction.
論文目次 摘要 I
Abstract II
Acknowledgements IV
Table of Contents V
List of Tables IX
List of Figures X
Glossary of Abbreviations XVI
Chapter 1 Introduction 1
1.1 Motivation and Problem Statement 1
1.2 Objectives and Contributions 6
1.3 Thesis Outline 7
Chapter 2 Background 8
2.1 Background to Building Dependent Navigation 8
2.1.1 RFID 9
2.1.2 UWB 9
2.1.3 Infrared 10
2.1.4 Ultrasonic 10
2.1.5 ZigBee 11
2.1.6 WLAN 11
2.1.7 Cellular Based 12
2.1.8 Bluetooth 12
2.1.9 Summary 13
2.2 Background to Inertial Navigation 15
2.2.1 MEMS-based IMU 16
2.2.2 INS Mechanization 17
2.3 Background to Image-based Positioning System 22
2.4 Background to Kalman Filter 23
Chapter 3 Methodology of PDR 25
3.1 Step Detection 26
3.2 Step Length Estimation 30
3.3 Attitude and Heading Estimation 32
3.3.1 Rotational Matrix 35
3.3.2 Sensor Signal Modelling 37
3.3.3 State Vector and Kalman Predict 40
3.3.4 Kalman Update 41
Chapter 4 Methodology of Misalignment Correction 44
4.1 Existing Correction Methods 45
4.2 Computer Vision 47
4.2.1 Optical Flow Method 48
4.2.2 MHI Method 54
4.2.3 Feature-based Method 63
4.2.4 Summary 67
4.3 CNN method 68
4.3.1 CNN and Deep Learning 69
4.3.2 Training Dataset 75
4.3.3 Network Structure 79
Chapter 5 Result and Analysis 83
5.1 Smartphone Specification 83
5.2 Software and App 84
5.3 Angle Misalignment Estimation Result 86
5.3.1 Normal Test and Computational Time Analysis 87
5.3.2 Tilt Test 89
5.3.3 Illumination Test 95
5.3.4 Moving speed Test 97
5.3.5 Ground Texture Test 99
5.3.6 Different Users Test 101
5.3.7 Switch Plan 102
5.3.8 CNN Method Test 104
5.4 PDR Trajectory Result 106
5.4.1 Outdoor Environment with Misalignment Correction 107
5.4.2 Indoor Environment with Misalignment Correction 114
5.4.3 A Comprehensive Experiment 120
Chapter 6 Conclusions and Recommendations 125
6.1 Conclusions 125
6.2 Thesis Contributions 127
6.3 Recommendations 127
Appendix A: Coordinate Frame 129
Reference 134

參考文獻 1.ABI research: BLE Tags and the Location of Things
2.Al-Ammar, Mai A., et al. "Comparative survey of indoor positioning technologies, techniques, and algorithms." Cyberworlds (CW), 2014 International Conference on. IEEE, 2014.
3.Ayub, Shahid, et al. "Indoor pedestrian displacement estimation using Smart phone inertial sensors." International Journal of Innovative Computing and Applications 4.1 (2012): 35-42.
4.Basso, Michele, et al. "Pedestrian dead reckoning based on frequency self-synchronization and body kinematics." IEEE Sensors Journal 17.2 (2017): 534-545.
5.Barron, John L., David J. Fleet, and Steven S. Beauchemin. "Performance of optical flow techniques." International journal of computer vision 12.1 (1994): 43-77.
6.Bay, Herbert, Tinne Tuytelaars, and Luc Van Gool. "Surf: Speeded up robust features." European conference on computer vision. Springer, Berlin, Heidelberg, 2006.
7.Beauregard, Stephane, and Harald Haas. "Pedestrian dead reckoning: A basis for personal positioning." Proceedings of the 3rd Workshop on Positioning, Navigation and Communication. 2006.
8.Bobick, Aaron F., and James W. Davis. "The recognition of human movement using temporal templates." IEEE Transactions on pattern analysis and machine intelligence 23.3 (2001): 257-267.
9.Bolles, Robert C., and Martin A. Fischler. "A RANSAC-Based Approach to Model Fitting and Its Application to Finding Cylinders in Range Data." IJCAI. Vol. 1981. 1981.
10.Bottou, Léon. "Large-scale machine learning with stochastic gradient descent." Proceedings of COMPSTAT'2010. Physica-Verlag HD, 2010. 177-186.
11.Brox, Thomas, et al. "High accuracy optical flow estimation based on a theory for warping." European conference on computer vision. Springer, Berlin, Heidelberg, 2004.
12.Bylemans, I., Weyn, M., &Klepal, M. (2009). Mobile phone-based displacement estimation for opportunistic localisation systems. 3rd International Conference on Mobile Ubiquitous Computing, Systems, Services, and Technologies, UBICOMM 2009, 113–118. https://doi.org/10.1109/UBICOMM.2009.23
13.Combettes, Christophe, and Valerie Renaudin. "Comparison of misalignment estimation techniques between handheld device and walking directions." Indoor Positioning and Indoor Navigation (IPIN), 2015 International Conference on. IEEE, 2015.
14.Davidson, Pavel, and Robert Piché. "A survey of selected indoor positioning methods for smartphones." IEEE Communications Surveys & Tutorials 19.2 (2017): 1347-1370.
15.De Angelis, Alessio, et al. "Design and characterization of a portable ultrasonic indoor 3-D positioning system." IEEE Transactions on Instrumentation and Measurement 64.10 (2015): 2616-2625.
16.Dhar, Subhankar, and Upkar Varshney. "Challenges and business models for mobile location-based services and advertising." Communications of the ACM 54.5 (2011): 121-128.
17.Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., ... & Brox, T. (2015). Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2758-2766).
18.Godha, Saurabh. "Performance evaluation of low cost MEMS-based IMU integrated with GPS for land vehicle navigation application." UCGE report 20239 (2006).
19.Gu, Yanying, Anthony Lo, and Ignas Niemegeers. "A survey of indoor positioning systems for wireless personal networks." IEEE Communications surveys & tutorials 11.1 (2009): 13-32.
20.Hightower, Jeffrey, Roy Want, and Gaetano Borriello. "SpotON: An indoor 3D location sensing technology based on RF signal strength." (2000).
21.Horn, Berthold KP, and Brian G. Schunck. "Determining optical flow." Artificial intelligence 17.1-3 (1981): 185-203.
22.Jin, Yunye, et al. "A robust dead-reckoning pedestrian tracking system with low cost sensors." Pervasive Computing and Communications (PerCom), 2011 IEEE International Conference on. IEEE, 2011.
23.Kazemipur, Bashir. Computer Vision Aiding Smartphone Sensors for Indoor Location Applications. Diss. University of Calgary, 2015.
24.Kim, Jeong Won, et al. "A step, stride and heading determination for the pedestrian navigation system." Positioning 1.08 (2004): 0.
25.Lee, Jun-Young, and Sun-Nam Hwang. "A high-gain boost converter using voltage-stacking cell." The Transactions of The Korean Institute of Electrical Engineers 57.6 (2008): 982-984.
26.Liu, Hui, et al. "Survey of wireless indoor positioning techniques and systems." IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 37.6 (2007): 1067-1080.
27.Liu, Ji-Gang, Da-Ming Shi, and Maylor Karhang Leung. "Indoor navigation system based on omni-directional corridorguidelines." Machine Learning and Cybernetics, 2008 International Conference on. Vol. 3. IEEE, 2008.
28.Liu, Shu, Yingxin Jiang, and Aaron Striegel. "Face-to-face proximity estimationusing bluetooth on smartphones." IEEE Transactions on Mobile Computing 13.4 (2014): 811-823.
29.Lowe, David G. "Distinctive image features from scale-invariant keypoints." International journal of computer vision 60.2 (2004): 91-110.
30.Lucas, Bruce D., and Takeo Kanade. "An iterative image registration technique with an application to stereo vision." (1981): 674-679.
31.Mautz, Rainer, and Sebastian Tilch. "Survey of optical indoor positioning systems." Indoor Positioning and Indoor Navigation (IPIN), 2011 International Conference on. IEEE, 2011.
32.Mautz, Rainer. "Indoor positioning technologies." (2012).
33.Nair, Vinod, and Geoffrey E. Hinton. "Rectified linear units improve restricted boltzmann machines." Proceedings of the 27th international conference on machine learning (ICML-10). 2010.
34.Ni, Lionel M., et al. "LANDMARC: indoor location sensing using active RFID." Wireless networks 10.6 (2004): 701-710.
35.Pascale, D.: A review of RGB color spaces. Technical Report. The Babel Color Company (2003)
36.Pratama, Azkario Rizky, and Risanuri Hidayat. "Smartphone-based pedestrian dead reckoning as an indoor positioning system." System Engineering and Technology (ICSET), 2012 International Conference on. IEEE, 2012.
37.Renaudin, Valérie, Muhammad Haris Afzal, and Gérard Lachapelle. "New method for magnetometers based orientation estimation." Position Location and Navigation Symposium (PLANS), 2010 IEEE/ION. IEEE, 2010.
38.Renaudin, Valérie, Melania Susi, and Gérard Lachapelle. "Step length estimation using handheld inertial sensors." Sensors 12.7 (2012): 8507-8525.
39.Renaudin, Valérie, and Christophe Combettes. "Magnetic, acceleration fields and gyroscope quaternion (MAGYQ)-based attitude estimation with smartphone sensors for indoor pedestrian navigation." Sensors 14.12 (2014): 22864-22890.
40.Rosten, Edward, and Tom Drummond. "Machine learning for high-speed corner detection." European conference on computer vision. Springer, Berlin, Heidelberg, 2006.
41.Ryschka, Stephanie, Matthias Murawski, and Markus Bick. "Location-based services." Business & Information Systems Engineering 58.3 (2016): 233-237.
42.Sabatini, Angelo M. "Quaternion-based extended Kalman filter for determining orientation by inertial and magnetic sensing." IEEE Transactions on Biomedical Engineering 53.7 (2006): 1346-1356.
43.Scaramuzza, Davide, and Friedrich Fraundorfer. "Visual odometry [tutorial]." IEEE robotics & automation magazine 18.4 (2011): 80-92.
44.Jimenez, Antonio R., et al. "A comparison of pedestrian dead-reckoning algorithms using a low-cost MEMS IMU." Intelligent Signal Processing, 2009. WISP 2009. IEEE International Symposium on. IEEE, 2009.
45.Shin, Eun-Hwan. Accuarcy improvement of low cost INS/GPS for land applications. University of Calgary, 2001.
46.S. H. Shin, C. G. Park, J. W. Kim, H. S. Hong, J. M. Lee, “Adaptive Step Length Estimation Algorithm Using Low-Cost MEMS Inertial Sensors,” in IEEE Sensors Applications Symposium, 2007.
47.Singh, Balaram, Soumya Pallai, and Susil Kumar Rath. "A Survey of Cellular Positioning Techniques in GSM Networks." National Conference in Mobile Computing-NCMC'12. 2012.
48.Song, Zhenlong, Gangyi Jiang, and Chao Huang. "A survey on indoor positioning technologies." Theoretical and Mathematical Foundations of Computer Science. Springer, Berlin, Heidelberg, 2011. 198-206.
49.Steinhoff, Ulrich, and Bernt Schiele. "Dead reckoning from the pocket-an experimental study." Pervasive Computing and Communications (PerCom), 2010 IEEE International Conference on. IEEE, 2010.
50.Svalastog, Mari Saua. Indoor positioning-technologies, services and architectures. MS thesis. 2007.
51.Teunissen, P.J.G. Adjustment Theory: An Introduction; Series on Mathematical Geodesy and Positioning; University of Delft: Delft, The Netherlands, 2003.
52.Thompson, William B., and H. Pick Jr. "Vision-based navigation." Proceedings: Image Understanding Workshop. 1993.
53.Triggs, Bill, et al. "Bundle adjustment—a modern synthesis." International workshop on vision algorithms. Springer, Berlin, Heidelberg, 1999.
54.Ureña, Jesús, et al. "Ultrasonic local positioning system for mobile robot navigation: From low to high level processing." Industrial Technology (ICIT), 2015 IEEE International Conference on. IEEE, 2015.
55.Wikipedia contributors. "Activation function." Wikipedia, The Free Encyclopedia. Wikipedia, The Free Encyclopedia, 6 Jun. 2018. Web. 13 Jun. 2018.
56.Valenti, Roberto G., Ivan Dryanovski, and Jizhong Xiao. "Keeping a good attitude: A quaternion-based orientation filter for IMUs and MARGs." Sensors 15.8 (2015): 19302-19330.
57.Yadav, Nagesh, and Chris Bleakley. "Accurate orientation estimation using AHRS under conditions of magnetic distortion." Sensors 14.11 (2014): 20008-20024.
58.Yayan, Ugur, and Hikmet Yucel. "A low cost ultrasonic based positioning system for the indoor navigation of mobile robots." Journal of Intelligent & Robotic Systems 78.3-4 (2015): 541-552.
59.Zhang, X.; Li, Y.; Mumford, P.; Rizos, C. Allan variance analysis on error characters of MEMS inertial sensors for an FPGA-based GPS/INS system. In proceedings of the International Symposium on GPS/GNNS, Tokyo, Japan, 11-14 November 2008; pp. 127-133.
60.Zhang, Hemin, et al. "A handheld inertial pedestrian navigation system with accurate step modes and device poses recognition." IEEE Sensors Journal 15.3 (2015): 1421-1429.
61.Zhao, Xiaojie, et al. "Does btle measure up against wifi? a comparison of indoor location performance." European Wireless 2014; 20th European Wireless Conference; Proceedings of. VDE, 2014.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2018-08-21起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2018-08-21起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw