高樓火災會威脅到現代都市的生活安全品質，若火災發生在較高樓層，消防人員無法確切掌握火勢和受災人的位置，故我們提出透過無人機裝載多模態感測器，自動探索高樓環境，提供消防人員所需的資訊，在過去已經有一些研究關於無人機群的工作和路線安排，但他們並沒有考慮到抵達一個偵測點之後，應該如何做資料搜集才能達到最好的準確率，我們的論文專注於補足這一塊的缺失，當無人機抵達一個待偵測點時，提供給他一個偵測資訊串，告訴它該在哪些位子進行拍攝，在每一個位子又該用哪個感測器和選擇哪一個分類器來分析感測器搜集的資料。為了更加具體討論我們的方法，在我們的論文中主要偵測的事件為窗戶開關和每扇窗戶後面是否有受災人，其他消防人員所需資訊仍可運用相同的方法提供偵測資訊串給無人機。總結來說，在這篇論文當中，我們搜集了第一個用多模態感測器拍攝而來的窗戶資料庫，並將我們的選擇問題公式化，提出兩個演算法來解決我們的問題，最後我們實作了一個事件驅動模擬器搭配虛擬城市環境評估我們演算法的表現，也設計了顯示資料的儀表板展現我們具體將如何提供狀況認知資訊給消防員。從實驗數據中可知我們的方法優於沒有產生偵測資訊串的方法，在偵測得準確度上提升了 50%，在眾多窗戶的測試中，成功達到預設的偵測時間限制和偵測準確率的比例比沒有產生偵測資訊串的方法高 100%，同時也降低了 6.78 倍的能源消耗。

High-rise fires are among the most significant threats to safety in modern cities, and autonomous drones with multi-modal sensors can be employed to enhance situational awareness in such unfortunate disasters. In this thesis, we study the fine-grained measurement selection problem for drones being dispatched to perform situation monitoring tasks in high-rise fires. Our problem considers multiple sensor/media types, classifier designs, and measurement locations, which were overlooked in prior waypoint scheduling studies. For concrete discussion, we adopt window openness and human detection as the target situations, while other situations can be readily supported by our solution. More specifically, we: (i) collect a very first multi-modal window dataset, (ii) mathematically formulate the fine-grained measurement selection problem and solve it using two algorithms, and (iii) create an event-driven simulator to evaluate our algorithms and a mock-up dashboard to demonstrate the detection results. The evaluation results from the event-driven simulator demonstrate that our proposed algorithms achieve higher classification accuracy (up to 50% improvement), deliver more feasible solutions (up to 100% improvement), and reduce energy consumption (up to 6.78 times reduction), compared to the current practices. Our dashboard demonstrates how we provide situational awareness in real high-rise firefighting.

中文摘要 i
Abstract ii
致謝 iii
Acknowledgments iv
1 Introduction 1
1.1 Contributions ................................ 4
1.2 Limitations ................................. 4
1.3 Organizations................................ 5
2 Background 6
2.1 SmartCity.................................. 6
2.2 High-RiseFirefighting ........................... 6
2.3 Drone-BasedApplications ......................... 7
2.4 SensorFusion................................ 8
2.5 Classifiers and Regressors for Multi-Modal Analytics . . . . . . . . . . . 9
3 Related Work 11
3.1 HeterogeneousSensorsonDrones ..................... 11
3.2 FirefightingDrones............................. 12
3.3 Coarse-Grained Waypoint Scheduling for Drones . . . . . . . . . . . . . 12
3.4 WindowDataset............................... 13
4 Drone-Based High-Rise Firefighing 14
4.1 Coarse-GrainedWaypointScheduling ................... 14
4.2 Fine-GrainedMeasurementSelection ................... 14
5 Real Dataset Collection 16
5.1 CollectionProcedure ............................ 17
5.2 DatasetFormat ............................... 19
5.3 SampleUsageScenarios .......................... 21
6 Synthesized Dataset Collection 37
6.1 AirSim.................................... 37
6.2 SensorImplementations........................... 38
6.3 CollectionProcedure ............................ 39
6.4 DatasetFormat ............................... 40
7 Classifier Designs and Implementations 42
7.1 WindowOpennessClassifiers........................ 42
7.2 HumanDetectionClassifiers ........................ 44
7.3 ClassifierCertaintyandAccuracy ..................... 45
8 Measurement Selection Problems 46
8.1 Notations .................................. 46
8.2 FusingtheMeasurementResults ...................... 47
8.3 Formulation................................. 48
8.4 ProposedAlgorithms ............................ 50
9 Performance Evaluations 52
9.1 Implementations .............................. 52
9.2 Setup .................................... 54
9.3 Results.................................... 55
10 Dashboard Design 61
11 Conclusion 63
Bibliography 65

[1] A. Alshbatat. Fire extinguishing system for high-rise buildings and rugged mountainous terrains utilizing quadrotor unmanned aerial vehicle. MECS Press International Journal of Image, Graphics and Signal Processing, 11(1):23, January 2018.
[2] A. Amin, F. Al-Obeidat, B. Shah, A. Adnan, J. Loo, and S. Anwar. Customer churn prediction in telecommunication industry using data certainty. Elsevier Journal of Business Research, 94:290–301, January 2019.
[3] H. Ando, Y. Ambe, A. Ishii, M. Konyo, K. Tadakuma, S. Maruyama, and S. Ta- dokoro. Aerial hose type robot by water jet for fire fighting. IEEE Robotics and Automation Letters, 3(2):1128–1135, April 2018.
[4] D. Anthony, S. Elbaum, A. Lorenz, and C. Detweiler. On crop height estimation with UAVs. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 4805–4812, Chicago, IL, September 2014.
[5] J. Bai, S. Lian, Z. Liu, K. Wang, and D. Liu. Smart guiding glasses for visually im- paired people in indoor environment. IEEE Transactions on Consumer Electronics, 63(3):258–266, August 2017.
[6] A.BaraldiandF.Panniggiani.Aninvestigationofthetexturalcharacteristicsassociated with gray level cooccurrence matrix statistical parameters. IEEE Transactions on Geoscience and Remote Sensing, 33(2):293–304, March 1995.
[7] R. Beard, T. McLain, M. Goodrich, and E. Anderson. Coordinated target assignment and intercept for unmanned air vehicles. IEEE Transactions on Robotics and Automation, 18(6):911–922, December 2002.
[8] K. Benson, G. Bouloukakis, C. Grant, V. Issarny, S. Mehrotra, I. Moscholios, and N. Venkatasubramanian. FireDex: A prioritized IoT data exchange middleware for emergency response. In Proc. of ACM International Middleware Conference (Mid- dleware’18), pages 279–292, Rennes, France, December 2018.
[9] K. Benson, G. Wang, N. Venkatasubramanian, and Y. Kim. Ride: A resilient IoT data exchange middleware leveraging SDN and edge cloud resources. In Proc. of IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI’18), pages 72–83, Orlando, FL, April 2018.
[10] E. Bondi, D. Dey, A. Kapoor, J. Piavis, S. Shah, F. Fang, B. Dilkina, R. Hannaford, A. Iyer, L. Joppa, et al. Airsim-W: A simulation environment for wildlife conservation with UAVs. In Proc. of ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS’18), pages 1–12, Menlo Park and San Jose, CA, June 2018.
[11] Central Programme Office, National Fire Chiefs Council, UK. Hazard - Fires in tall buildings, 2020. https://www.ukfrs.com/guidance/search/fires-tall-buildings.
[12] D. Ceylan, N. Mitra, Y. Zheng, and M. Pauly. Coupled structure-from-motion and 3D symmetry detection for urban facades. ACM Transactions on Graphics (TOG’14), 33(1):1–15, January 2014.
[13] O. Chapelle, P. Haffner, and V. N. Vapnik. Support vector machines for histogram-based image classification. IEEE Transactions on Neural Networks, 10(5):1055– 1064, 1999.
[14] C. Chen, R. Jafari, and N. Kehtarnavaz. A survey of depth and inertial sensor fusion for human action recognition. Springer Multimedia Tools and Applications, 76(3):4405–4425, 2017.
[15] H.ChengandG.V.Hadjisophocleous.Dynamicmodelingoffirespreadinbuilding. Fire Safety Journal, 46(4):211–224, 2011.
[16] S. Daftry, C. Hoppe, and H. Bischof. Building with drones: Accurate 3D facade reconstruction using MAVs. In Proc. of IEEE International Conference on Robotics and Automation (ICRA’15), pages 3487–3494, Seattle, WA, May 2015.
[17] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In
Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 1, pages 886–893, San Diego, CA, June 2005.
[18] H. Dang-Ngoc and H. Nguyen-Trung. Aerial forest fire surveillance - evaluation of forest fire detection model using aerial videos. In Proc. of IEEE International Conference on Advanced Technologies for Communications (ATC), pages 142–148, Hanoi, Vietnam, October 2019.
66

[19] B. V. Dasarathy. Sensor fusion potential exploitation-innovative architectures and illustrative applications. Proceedings of the IEEE, 85(1):24–38, January 1997.
[20] C. DelBello. High-rise and mid-rise firefighting: Lobby control basics, 2020. https : / / www . firerescue1 . com / high-rise / articles / high-rise-and-mid-rise-firefighting-lobby-control-basics-kDUyBVO8Z25vgJUm/.
[21] Department of Economic and Social Affairs, United Nations. 68% of the world population projected to live in urban areas by 2050, says UN, 2018. https : / / www. un . org / development / desa / en / news / population / 2018-revision-of-world-urbanization-prospects.html.
[22] DJI. Dji AGRAS MG-1P sprayer drone. https://talosdrones.com/product/ dji-agras-mg1-p-sprayer-drone/.
[23] W. Elmenreich. An introduction to sensor fusion. Vienna University of Technology, Austria, 502:1–28, 2002.
[24] Epic Games. Unreal Engine, 2019. https://www.unrealengine.com.
[25] M. et al. Fire fighting tactics under wind driven conditions: laboratory experiments. Fire Protection Research Foundation, 2009.
[26] C. Ezequiel, M. Cua, N. Libatique, G. Tangonan, R. Alampay, R. Labuguen, C. Favila, J. Honrado, V. Canos, C. Devaney, et al. Uav aerial imaging applications for post-disaster assessment, environmental management and infrastructure development. In Proc. of IEEE International Conference on Unmanned Aircraft Systems (ICUAS’14), pages 274–283, Orlando, FL, May 2014.
[27] T.-Y. Fan, F. Liu, J.-W. Fang, N. Venkatasubramanian, and C.-H. Hsu. Enhancing situational awareness with adaptive firefighting drones: Leveraging diverse media types and classifiers. In Proc. of ACM Multimedia Systems Conference (MMSys’22), Athlone, Ireland, 2022.
[28] T.-Y. Fan, T.-C. Tsai, C.-H. Hsu, F. Liu, and N. Venkatasubramanian. WinSet: the first multi-modal window dataset for heterogeneous window states. In Proc. of ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys’21), pages 192–195, Coimbra, Portugal, November 2021.
[29] M. Fishlock. A new set of tactical options to assist incident commanders and firefighters at high-rise incidents., 2013. http://www.highrisefire.co.uk/tactic.html.
[30] R. Gadde, R. Marlet, and N. Paragios. Learning grammars for architecture-specific facade parsing. Springer International Journal of Computer Vision, 117(3):290– 316, March 2016.
[31] Groupgets. LeptonModule, 2019. https://github.com/groupgets/LeptonModule.
[32] Q. Ha, K. Watanabe, T. Karasawa, Y. Ushiku, and T. Harada. MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’17), pages 5108–5115, Vancouver, Canada, September 2017.
[33] J.-W. Hu, B.-Y. Zheng, and W. et al. A survey on multi-sensor fusion based obstacle detection for intelligent ground vehicles in off-road environments. Springer Frontiers of Information Technology & Electronic Engineering, 21:675–692, 2020.
[34] Y. Huang, W. C. Hoffmann, Y. Lan, W. Wu, and B. K. Fritz. Development of a spray system for an unmanned aerial vehicle platform. Applied Engineering in Agriculture, 25(6):803–809, 2009.
[35] Z. Huang, K. Wang, K. Yang, R. Cheng, and J. Bai. Glass detection and recognition based on the fusion of ultrasonic sensor and RGB-D sensor for the visually impaired. In Proc. of SPIE Target and Background Signatures IV, pages 118–125, Berlin, Germany, October 2018.
[36] Intel. Intel Realsense SDK, 2021. https://github.com/IntelRealSense/librealsense.
[37] M. Jarzabek, D. Lin, and H. Maas. Supervised detection of facade openings in 3D point clouds with thermal attributes. MDPI Remote Sensing, 12(3):543, February 2020.
[38] Y. Kim, D.-W. Gu, and I. Postlethwaite. Real-time optimal mission scheduling and flight path selection. IEEE Transactions on Automatic Control, 52(6):1119–1123, June 2007.
[39] Kitware and Velodyne. VeloView, 2014. https://www.paraview.org/VeloView.
[40] W. Krull, R. Tobera, and et al. Early forest fire detection and verification using optical smoke, gas and microwave sensors. Procedia Engineering, 45:584–594, 2012.
[41] N. Kumar, D. Acharya, and D. Lohani. An IoT-based vehicle accident detection and classification system using sensor fusion. IEEE Internet of Things Journal, 8(2):869–880, 2020.
[42] K. K. Ladha. The Condorcet jury theorem, free speech, and correlated votes. American Journal of Political Science, pages 617–634, 1992.
[43] S. Leary, M. Deittert, and J. Bookless. Constrained UAV mission planning: A comparison of approaches. In Proc. of IEEE International Conference on Computer Vision Workshops (ICCV’11 Workshops), pages 2002–2009, Barcelona, Spain, November 2011.
[44] T. Lewicki and K. Liu. Aerial sensing system for wildfire detection: Demo abstract. In Proc. of the ACM Conference on Embedded Networked Sensor Systems (SenSys’20), pages 595–596, Yokohama, Japan, November 2020.
[45] D. Lin, Z. Dong, X. Zhang, and H. Maas. Unsupervised window extraction from photogrammetric point clouds with thermal attributes. ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences, 4:10–14, June 2019.
[46] J.Lin, A.Morse, and B.Anderson.The multi-agent rendezvous problem. In Proc. of IEEE International Conference on Decision and Control, pages 1508–1513, Maui, HI, December 2003.
[47] F. Lippoldt. Window detection in facades for aerial texture files of 3D CityGML models. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR’19), pages 11–19, Long Beach, CA, June 2019.
[48] F. Liu, T.-Y. Fan, C. Grant, C.-H. Hsu, and N. Venkatasubramanian. DragonFly: Drone-Assisted High-Rise Monitoring for Fire Safety. In Proc. of IEEE International Symposium on Reliable Distributed Systems (SRDS’21), Virtual, September 2021.
[49] H. Liu, Y. Xu, J. Zhang, J. Zhu, Y. Li, and S. C. H. Hoi. DeepFacade: A deep learning approach to facade parsing with symmetric loss. IEEE Transactions on Multimedia, 22(12):3153–3165, December 2020.
[50] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg. SSD: Single shot multibox detector. In Proc. of Springer European conference on computer vision (ECCV’16), pages 21–37, Amsterdam, Netherlands, October 2016.
[51] Y. Liu, Y. Yin, and S. Zhang. Hand gesture recognition based on hu moments in interaction of virtual reality. In Proc. of the IEEE International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC’12), volume 1, pages 145–148, Nanchang, China, August 2012.
[52] M. A. Lopez Medina, M. Espinilla, C. Paggeti, and J. Medina Quero. Activity recognition for IoT devices using fuzzy spatio-temporal features as environmental sensor fusion. Sensors, 19(16):3512, 2019.
[53] J. M. MacDonald, P. Korb, and R. A. Hoppe. Farm size and the organization of us crop farming. Technical report, 2013.
[54] S. Malihi, M. Valadan Zoej, M. Hahn, and M. Mokhtarzade. Window detection from UAS-derived photogrammetric point cloud employing density-based filtering and perceptual organization. MDPI Remote Sensing, 10(8):1320, August 2018.
[55] D. M. McGrail. Firefighting operations in high-rise and standpipe-equipped buildings. PennWell Books, 2007.
[56] T. McLain and R. Beard. Coordination variables, coordination functions, and co-operative timing missions. AIAA Journal of Guidance, Control, and Dynamics, 28(1):150–161, November 2005.
[57] J. J. A. Mendes Jr, M. E. M. Vieira, M. B. Pires, and S. L. Stevan Jr. Sensor fusion and smart sensor in sports and biomedical applications. Sensors, 16(10):1569, 2016.
[58] U. R. Mogili and B. Deepak. Review on application of drone systems in precision agriculture. Procedia computer science, 133:502–509, 2018.
[59] M. Moore Bick. Grenfell tower inquiry: Phase 1 report overview - report of the public inquiry into the fire at Grenfell tower on 14 June 2017, 2019. https://www. grenfelltowerinquiry.org.uk/phase-1-report.
[60] S. Mustapha, A. Kassir, K. Hassoun, Z. Dawy, and H. Abi-Rached. Estimation of crowd flow and load on pedestrian bridges using machine learning with sensor fusion. Automation in Construction, 112:103092, 2020.
[61] A. S. Natu and S. Kulkarni. Adoption and utilization of drones for advanced precision farming: A review. International Journal on Recent and Innovation Trends in Computing and Communication, 4(5):563–565, 2016.
[62] M. Neuhausen, C. Koch, and M. Konig. Image-based window detection: an overview. 2016.
[63] M. Neuhausen, A. Martin, M. Obel, P. Mark, and M. Konig. A cascaded classifier approach to window detection in facade images. In Proc. of IAARC International Symposium on Automation and Robotics in Construction (ISARC’17), pages 690– 697, Taipei, Taiwan, July 2017.
[64] H. P. D. Nguyen and D. D. Nguyen. Drone application in smart cities: The general overview of security vulnerabilities and countermeasures for data communication. Springer Development and Future of Internet of Drones (IoD): Insights, Trends and Road Ahead, pages 185–210, 2021.
[65] W. S. Noble. What is a support vector machine? Nature biotechnology, 24(12):1565–1567, 2006.
[66] S. Ogawa, S. Kudo, M. Koide, H. Torikai, and Y. Iwatani. Development and control of an aerial extinguisher with an inert gas capsule. In Proc. of IEEE International Conference on Robotics and Biomimetics (ROBIO’14), pages 1320–1325, Bali, Indonesia, December 2014.
[67] M. Pal. Random forest classifier for remote sensing classification. International journal of remote sensing, 26(1):217–222, 2005.
[68] J. Primicerio, S. F. Di Gennaro, E. Fiorillo, L. Genesio, E. Lugato, A. Matese, and F. P. Vaccari. A flexible unmanned aerial vehicle for precision agriculture. Springer Precision Agriculture, 13(4):517–523, 2012.
[69] QuadArt. Modular house, 2017. https : / / www. unrealengine . com / marketplace / en-US/product/modular-houses.
[70] C. Reardon and J. Fink. Air-ground robot team surveillance of complex 3D environments. In Proc. of IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR’16), pages 320–327, Lausanne, Switzerland, October 2016.
[71] S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 2015.
[72] Renderpeople. Scanned 3d people pack, 2019. https://www.unrealengine.com/ marketplace/en-US/product/9c3fab270dfe468a9a920da0c10fa2ad.
[73] A. Restas et al. Drone applications for supporting disaster management. World Journal of Engineering and Technology, 3(03):316, 2015.
[74] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski. ORB: An efficient alternative to sift or surf. In Proc. of IEEE International Conference on Computer Vision (ICCV’11), pages 2564–2571, Barcelona, Spain, November 2011.
[75] S. Safavi, T. Iqbal, W. Wang, P. Coleman, and M. Plumbley. Open-window: A sound event data set for window state detection and recognition. In Proc. of International Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE’20), Tokyo, Japan, August 2020.
[76] O. Safety, H. Administration, et al. Fire service features of buildings and fire protection systems. Occupational Safety and Health Administration US Department of Labor, 2015.
[77] C. Schweier and M. Markus. Classification of collapsed buildings for fast damage and loss assessment. Springer Bulletin of earthquake engineering, 4(2):177–192, 2006.
[78] V. Sea, A. Sugiyama, and T. Sugawara. Frequency-based multi-agent patrolling model and its area partitioning solution method for balanced workload. In Proc. of Springer International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, pages 530–545, June 2018.
[79] C. Seifert. TSG-20: Tourist sights graz 20, 2004. http://dib.joanneum.at/cape/ TSG-20/.
[80] S. Shah, D. Dey, C. Lovett, and A. Kapoor. AirSim: High-fidelity visual and physical simulation for autonomous vehicles. In Proc. of Springer Field and Service Robotics, pages 621–635. November 2018.
[81] B. Sirmacek, L. Hoegner, and U. Stilla. Detection of windows and doors from thermal images by grouping geometrical features. In Proc. of IEEE Joint Urban Remote Sensing Event (JURSE’11), pages 133–136, Munich, Germany, April 2011.
[82] S. Smith and D. Rus. Multi-robot monitoring in dynamic environments with guaranteed currency of observations. In Proc. of IEEE Conference on Decision and Control (CDC’10), pages 514–521, Atlanta, GA, December 2010.
[83] B. Srikudkao, T. Khundate, C. So-In, P. Horkaew, C. Phaudphut, and K. Rujirakul. Flood warning and management schemes with drone emulator using ultrasonic and image processing. In Proc. of Springer Recent Advances in Information and Communication Technology, pages 107–116. 2015.
[84] K. Su, J. Li, and H. Fu. Smart city and the applications. In Proc. of IEEE international conference on electronics, communications and control (ICECC’11), pages 1028–1031, Ningbo, China, November 2011.
[85] R. Suganya and S. Rajaram. Feature extraction and classification of ultrasound liver images using haralick texture-primitive features: Application of SVM classifier. In Proc. of IEEE International Conference on Recent Trends in Information Technology (ICRTIT’13), pages 596–602, Chennai, India, July 2013.
[86] L. Sun, R. K. Sheshadri, W. Zheng, and D. Koutsonikolas. Modeling WiFi active power/energy consumption in smartphones. In Proc. of IEEE International Conference on Distributed Computing Systems (ICDCS’14), pages 41–51, Madrid, Spain, June 2014.
[87] O. Teboul. Ecole centrale paris facades database, 2008. http://vision.mas.ecp.fr/ Personnel/teboul/data.php.
[88] C. Thiel. Multiple classifier fusion incorporating certainty factors. PhD thesis, Verlag nicht ermittelbar, 2004.
[89] R. Tylecek and R. Sara. Spatial pattern templates for recognition of objects with regular structure. In Proc. of Springer Pattern Recognition, pages 364–374, Berlin, Heidelberg, 2013.
[90] K. Valavanis and G. Vachtsevanos. In Proc. of Springer Handbook of Unmanned Aerial Vehicles. 2015.
[91] B. Vergouw, H. Nagel, G. Bondt, and B. Custers. Drone technology: Types, payloads, applications, frequency spectrum issues and future developments. In Proc. of Springer The Future of Drone Use, pages 21–45. 2016.
[92] K. Wada. labelme: Image Polygonal Annotation with Python, 2016. https://github. com/wkentaro/labelme.
[93] A. Wallar, E. Plaku, and D. Sofge. Reactive motion planning for unmanned aerial surveillance of risk-sensitive areas. IEEE Transactions on Automation Science and Engineering, 12(3):969–980, July 2015.
[94] J. Wang and H. Wang. Tunable fiber laser based photoacoustic gas sensor for early fire detection. Infrared Physics & Technology, 65:1–4, 2014.
[95] R. Wang, J. Bach, and F. Ferrie. Window detection from mobile lidar data. In Proc. of IEEE Workshop on Applications of Computer Vision (WACV’11), pages 58–65, Kona, Hawaii, January 2011.
[96] Z. Wang, Y. Wu, and Q. Niu. Multi-sensor fusion in automated driving: A survey. IEEE Access, 8:2847–2868, 2019.
[97] C. Zhao, W. S. Lee, and D. He. Immature green citrus detection based on colour feature and sum of absolute transformed difference (SATD) using colour images in the citrus grove. Elsevier Computers and Electronics in Agriculture, 124:243–253, 2016.
[98] H. Zheng, F. Li, H. Cai, and K. Zhang. Non-intrusive measurement method for the window opening behavior. Elsevier Energy and Buildings, 197:171–176, August 2019.
[99] A. Ziebinski, R. Cupek, H. Erdogan, and S. Waechter. A survey of ADAS technologies for the future perspective of sensor fusion. In Proc. of Springer International Conference on Computational Collective Intelligence, pages 135–146, 2016.