臺灣博碩士論文加值系統

車流理論依據觀察角度可分為巨觀與微觀，巨觀車流探討車輛的整體行為，微觀車流探討車輛與車輛之間的行為。在交通資料中，車流軌跡資料為最詳細的資料型式，能夠描述車輛在單位時間上的空間位置。文獻上目前最被認可的軌跡資料是美國聯邦公路管理局的Next Generation SIMulation(NGSIM)資料庫，至今已使用於許多車流研究中。然而，NGSIM資料庫的軌跡資料品質並未有公認的量化方式，因NGSIM的影片收集方式為多部不同視角之攝影機架攝於高樓斜角拍攝，存在視差及陰影等問題，且過去影像辨識技術之不足，導致車流軌跡有跳動的情形，近年更有研究進一步探討NGSIM資料的精確度問題，進而發展出軌跡重建技術，使重建後的軌跡資料能更合理並能應用於精細的微觀行為分析研究。

NGSIM 每一地點只包含45分鐘之車流軌跡資料，所涵蓋的車流情境非常有限，加上受影像解析度所限，軌跡資料品質也難以再提升。因近年新興科技如無人機(Unmanned Aerial Vehicle, UAV)、電腦視覺(Computer Vision, CV)技術的急速發展，已有應用於交通調查精進的案例，可用於類似NGSIM車流軌跡的蒐集，但其精確度尚有待評估。

因此，本研究對於無人機在高速公路路段所蒐集之影像，搭配深度學習影像辨識技術萃取之車流軌跡，設計軌跡資料之品質評估方法，並提出考慮影像偵測誤差分布之軌跡重建方法，對於不合理的軌跡予以修正，提高軌跡資料的品質。最後結合軌跡與空拍影片，將重建後的車輛四角坐標套回空拍影片，以便於人工確認重建後軌跡的品質以及車輛框格(bounding box)的正確性與密合程度。本研究進一步計算巨觀與微觀車流特性，比較軌跡重建前與重建後之差異。研究結果顯示，不論車流密度高低的情況下，軌跡重建後都有顯著的品質改善。

According to the observation perspective, traffic flow theory can be divided into the macroscopic and microscopic levels. Macroscopic traffic flow theory describes the overall behavior of vehicles, whereas microscopic traffic flow theory describes the behavior between two vehicles. In traffic data, vehicle trajectory data, which contains the spatial positions of vehicles at each time instance, is the most detailed form of traffic data. The most recognized vehicle trajectory dataset is the Next Generation SIMulation (NGSIM), a program initialized by the Federal Highway Administration (FHWA) of the US Department of Transportation in 2005. Up to now, the database has been widely used in numerous traffic studies to explore for the traffic characteristic and used to derive traffic flow models. However, there is no commonly recognized methodology to evaluate the quality and accuracy of NGSIM. The accuracy of the database was constrained by the video collection method and the image recognition technology at the time of the NGSIM program. Several synchronized cameras collected the videos with different monitoring angle mounting on top of high buildings adjacent to the roadway, resulting in parallax and shadows issues in the images. The accuracy of the NGSIM dataset has been criticized in several recent studies, advocating that trajectory reconstruction is needed before the trajectory database is used for microscopic studies. The purpose of trajectory reconstruction is to clean out the inconsistencies in the vehicle trajectory pairs and make sure the trajectory data can be more reasonable before it is used for further analysis at the microscopic level.


Each location of the NGSIM dataset covers a time period of only 45 minutes, and traffic scenarios contained in the data are limited. Coupled with the limitation of image resolution, the quality of trajectory data is difficult to improve further. Due to the rapid advancement of emerging technologies such as Unmanned Aerial Vehicle (UAV) and Computer Vision (CV) in recent years, there have been many successful traffic survey cases in collecting vehicle trajectories similar to the NGSIM program. Still, the accuracy of trajectories remains to be assessed.

Therefore, this study develops a quality assessment method and trajectory reconstruction algorithm for a vehicle trajectory dataset, which is obtained with aerial videos collected by UAV on highway sections and extracted by a deep-learning-based computer vision technique. The quality of reconstructed trajectory is further verified by embedding the reconstructed four-corner bounding boxes of vehicles onto the aerial videos, so as one can efficiently reconfirm the accuracy of the reconstructed trajectory by visualization. This research further calculates the macroscopic and microscopic traffic flow characteristics and compares the differences in traffic characteristics with the datasets before and after trajectory reconstruction. The results show that, regardless of high or low traffic density scenarios in the traffic stream, the proposed trajectory reconstruction methodology can significantly improve the quality of trajectory data.

摘要 i
ABSTRACT ii
誌謝 iv
目錄 v
圖目錄 vii
表目錄 ix
第一章　緒論 1
1.1 研究背景與動機 1
1.2 研究目的 4
1.3 研究範圍 5
1.4 研究流程 6
第二章　文獻回顧 8
2.1 影像資料處理方式 8
2.1.1 手動/半自動方式 8
2.1.2 電腦視覺方式 9
2.2 車流軌跡之應用 10
2.2.1 微觀車流模式 10
2.2.2 巨觀車流模式 11
2.2.3 相關估計與預測 11
2.3 車流軌跡之重建 12
2.4 小結 15
第三章　研究方法 17
3.1 空拍影片與軌跡資料庫 18
3.2 車流軌跡資料品質評估方法 23
3.2.1 初步檢測 25
3.2.2 詳細檢測 29
3.3 車流軌跡資料重建方法 31
3.4 巨觀車流特性 36
3.4.1 斷面流率 36
3.4.2 速率時空圖計算方式 37
3.4.3 車道變換判斷方式 38
3.5 微觀車流特性 40
3.5.1 瞬時速率、瞬時加速度 40
3.5.2 車間程、距離間隙 40
第四章　研究結果 41
4.1 重建前之軌跡品質檢測結果 41
4.1.1 初步檢測 41
4.1.2 詳細檢測 41
4.1.3 車流軌跡時空圖 42
4.2 重建後之軌跡品質檢測結果 44
4.2.1 初步檢測 44
4.2.2 詳細檢測 44
4.2.3 車流軌跡時空圖 45
4.3 不同情境下軌跡重建結果比較 47
4.3.1 情境一：車輛偵測受道路輔助標線、標字影響 47
4.3.2 情境二：中高密度壅塞狀況 50
4.4 巨觀車流特性 51
4.4.1 斷面流率 51
4.4.2 速率時空圖 52
4.4.3 車道變換位置與頻次 53
4.5 微觀車流特性 54
4.5.1 瞬時速率、瞬時加速度 54
4.5.2 車間程、距離間隙 56
第五章　結論與建議 58
5.1 結論 58
5.2 建議 59
參考文獻 60

王如玉(2018)，空拍影像之車流辨識與計算，國立交通大學，碩士論文。
林銘泓(2019)，PairingNet：基於連續影像之端到端車輛辨識與配對網絡，國立交通大學，碩士論文。
柳景瑜(2018)，結合深度學習車流分析的UAV交通監測平台，國立交通大學，碩士論文。
陳鴻君(2018)，基於空拍影像之車流資料收集，國立交通大學，碩士論文。
黃家耀、李子璋、謝旭昇、羅峻庭、黃郁傑、李威(2014)，機車行為模式在都市混合車流中之實証分析及模式建立，交通部科技顧問室研究報告書。
黃家耀、林貴璽、溫雲晨、廖晉毅、張舜淵、歐陽恬恬(2020)，無人機交通調查系統及其交通調查方法，中華民國專利(提出申請中)。
黃家耀、林貴璽、廖晉毅、溫雲晨、陳威瑜(2019)，高快速公路匝道分匯流區容量及服務水準分析之研究(1/3)-獨立進出口分匯流區，交通部運輸研究所委託計畫。
羅聖學(2017)，混合車流及高密度下之車輛影像辨識及軌跡追蹤，國立交通大學，碩士論文。
Abdeljaber, O., Younis, A., & Alhajyaseen, W. (2020). Extraction of Vehicle Turning Trajectories at Signalized Intersections Using Convolutional Neural Networks. Arabian Journal for Science and Engineering, 1–15. https://doi.org/10.1007/s13369-020-04546-y
Balal, E., Cheu, R. L., & Sarkodie-Gyan, T. (2016). A binary decision model for discretionary lane changing move based on fuzzy inference system. Transportation Research Part C: Emerging Technologies, 67, 47–61. https://doi.org/10.1016/j.trc.2016.02.009
Bock, J., Krajewski, R., Moers, T., Runde, S., Vater, L., & Eckstein, L. (2019). The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections. arXiv:1911.07602
Bucknell, C., & Herrera, J. C. (2014). A trade-off analysis between penetration rate and sampling frequency of mobile sensors in traffic state estimation. Transportation Research Part C: Emerging Technologies, 46, 132–150. https://doi.org/10.1016/j.trc.2014.05.007
Chen, D., Laval, J., Zheng, Z., & Ahn, S. (2012). A behavioral car-following model that captures traffic oscillations. Transportation Research Part B: Methodological, 46(6), 744–761. https://doi.org/10.1016/j.trb.2012.01.009
Chen, P., Zeng, W., Yu, G., & Wang, Y. (2017). Surrogate Safety Analysis of Pedestrian-Vehicle Conflict at Intersections Using Unmanned Aerial Vehicle Videos. Journal of Advanced Transportation, 2017. https://doi.org/10.1155/2017/5202150
Cleveland, W. S. (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, 74(369), 829–836. https://doi.org/10.1080/01621459.1979.10481038
Coifman, B. (2015). Empirical flow-density and speed-spacing relationships: Evidence of vehicle length dependency. Transportation Research Part B: Methodological, 78, 54–65. https://doi.org/10.1016/j.trb.2015.04.006
Coifman, B., & Li, L. (2017). A critical evaluation of the Next Generation Simulation (NGSIM) vehicle trajectory dataset. Transportation Research Part B: Methodological, 105, 362–377. https://doi.org/10.1016/j.trb.2017.09.018
 
Deng, W., Lei, H., & Zhou, X. (2013). Traffic state estimation and uncertainty quantification based on heterogeneous data sources: A three detector approach. Transportation Research Part B: Methodological, 57, 132–157. https://doi.org/10.1016/j.trb.2013.08.015
Edie, L. C. (1963). Discussion of Traffic Stream Measurements and Definitions. Proceedings of the 2nd International Symposium on the Theory of Traffic Flow, 139–154.
Fard, M. R., Mohaymany, A. S., & Shahri, M. (2017). A new methodology for vehicle trajectory reconstruction based on wavelet analysis. Transportation Research Part C: Emerging Technologies, 74, 150–167. https://doi.org/10.1016/j.trc.2016.11.010
Hamdar, S. H., Mahmassani, H. S., & Treiber, M. (2015). From behavioral psychology to acceleration modeling: Calibration, validation, and exploration of drivers’ cognitive and safety parameters in a risk-taking environment. Transportation Research Part B: Methodological, 78, 32–53. https://doi.org/10.1016/j.trb.2015.03.011
Hao, H., Ma, W., & Xu, H. (2016). A fuzzy logic-based multi-agent car-following model. Transportation Research Part C: Emerging Technologies, 69, 477–496. https://doi.org/10.1016/j.trc.2015.09.014
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, 2980–2988. https://doi.org/10.1109/ICCV.2017.322
He, Z. (2017). Research based on high-fidelity NGSIM vehicle trajectory datasets: A review. Research Gate, 1–33. https://doi.org/10.13140/RG.2.2.11429.60643
He, Z., Zheng, L., & Guan, W. (2015). A simple nonparametric car-following model driven by field data. Transportation Research Part B: Methodological, 80, 185–201. https://doi.org/10.1016/j.trb.2015.07.010
Herrera, J. C., & Bayen, A. M. (2010). Incorporation of Lagrangian measurements in freeway traffic state estimation. Transportation Research Part B: Methodological, 44(4), 460–481. https://doi.org/10.1016/j.trb.2009.10.005
Jabari, S. E., Zheng, J., & Liu, H. X. (2014). A probabilistic stationary speed-density relation based on Newell’s simplified car-following model. Transportation Research Part B: Methodological, 68, 205–223. https://doi.org/10.1016/j.trb.2014.06.006
 
Jiang, C., Qiu, R., Fu, T., Fu, L., Xiong, B., & Lu, Z. (2020). Impact of right-turn channelization on pedestrian safety at signalized intersections. Accident Analysis and Prevention, 136, 105399. https://doi.org/10.1016/j.aap.2019.105399
Jin, W. L. (2010). A kinematic wave theory of lane-changing traffic flow. Transportation Research Part B: Methodological, 44(8–9), 1001–1021. https://doi.org/10.1016/j.trb.2009.12.014
Jin, W. L. (2013). A multi-commodity Lighthill-Whitham-Richards model of lane-changing traffic flow. Transportation Research Part B: Methodological, 57, 361–377. https://doi.org/10.1016/j.trb.2013.06.002
Kanagaraj, V., Asaithambi, G., Toledo, T., & Lee, T. C. (2015). Trajectory data and flow characteristics of mixed traffic. Transportation Research Record, 2491(1), 1–11. https://doi.org/10.3141/2491-01
Koutsopoulos, H. N., & Farah, H. (2012). Latent class model for car following behavior. Transportation Research Part B: Methodological, 46(5), 563–578. https://doi.org/10.1016/j.trb.2012.01.001
Krajewski, R., Bock, J., Kloeker, L., & Eckstein, L. (2018). The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems. Proceedings of the 21st International Conference on Intelligent Transportation Systems, 2118–2125. https://doi.org/10.1109/ITSC.2018.8569552
Laval, J. A., & Leclercq, L. (2008). Microscopic modeling of the relaxation phenomenon using a macroscopic lane-changing model. Transportation Research Part B: Methodological, 42(6), 511–522. https://doi.org/10.1016/j.trb.2007.10.004
Laval, J. A., Toth, C. S., & Zhou, Y. (2014). A parsimonious model for the formation of oscillations in car-following models. Transportation Research Part B: Methodological, 70, 228–238. https://doi.org/10.1016/j.trb.2014.09.004
Lee, T. C. (2007). An Agent-Based Model to Simulate Motorcycle Behaviour in Mixed Traffic Flow, Ph.D Dissertation, mperial College London, UK. Available at <http://www.cts.cv.ic.ac.uk/documents/theses/LeePhD.pdf>.
Lee, T. C., Polak, J. W., & Bell, M. G. H. (2008). Trajectory Extractor user manual version 1.0, Technical Report, Centre for Transport Studies, ImperialCollege London, UK. Available at .
 
Li, S., Xiang, Q., Ma, Y., Gu, X., & Li, H. (2016). Crash risk prediction modeling based on the traffic conflict technique and a microscopic simulation for freeway interchange merging areas. International Journal of Environmental Research and Public Health, 13(11), 1157. https://doi.org/10.3390/ijerph13111157
Lu, X., & Skabardonis, A. (2007). Freeway Traffic Shockwave Analysis: Exploring NGSIM Trajectory Data. Proceedings of the 86th Annual Meeting of the Transportation Research Board.
Mikhail, E. M., Bethel, J. S., & McGlone, J. C. (2001). Introduction to Modern Photogrammetry. John Wiley & Sons. Inc., New York
Montanino, M., & Punzo, V. (2013). Making NGSIM Data Usable for Studies on Traffic Flow Theory: Multistep Method for Vehicle Trajectory Reconstruction. Transportation Research Record, 2390(1), 99–111. https://doi.org/10.3141/2390-11
Montanino, M., & Punzo, V. (2015). Trajectory data reconstruction and simulation-based validation against macroscopic traffic patterns. Transportation Research Part B: Methodological, 80, 82–106. https://doi.org/10.1016/j.trb.2015.06.010
Munigety, C. R., Vicraman, V., & Mathew, T.V. (2014). Semiautomated tool for extraction of microlevel traffic data from videographic survey. Transportation Research Record, 2443(1), 88–95. https://doi.org/10.3141/2443-10
Nguyen, L., Hanaoka, S., & Kawasaki, T. (2012). Describing non-lane-based motorcycle movements in motorcycle-only traffic flow. Transportation Research Record, 2281(1), 76–82. https://doi.org/10.3141/2281-10
Piccoli, B., Han, K., Friesz, T. L., Yao, T., & Tang, J. (2015). Second-order models and traffic data from mobile sensors. Transportation Research Part C: Emerging Technologies, 52, 32–56. https://doi.org/10.1016/j.trc.2014.12.013
Przybyla, J., Taylor, J., Jupe, J., & Zhou, X. (2015). Estimating risk effects of driving distraction: A dynamic errorable car-following model. Transportation Research Part C: Emerging Technologies, 50, 117–129. https://doi.org/10.1016/j.trc.2014.07.013
Punzo, V., Borzacchiello, M. T., & Ciuffo, B. (2011). On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation (NGSIM) program data. Transportation Research Part C: Emerging Technologies, 19(6), 1243–1262. https://doi.org/10.1016/j.trc.2010.12.007
 
Qian, Z. S., Li, J., Li, X., Zhang, M., & Wang, H. (2017). Modeling heterogeneous traffic flow: A pragmatic approach. Transportation Research Part B: Methodological, 99, 183–204. https://doi.org/10.1016/j.trb.2017.01.011
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference Computer Society Conference on Computer Vision and Pattern Recognition, 779–788. https://doi.org/10.1109/CVPR.2016.91
Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition, 6517–6525. https://doi.org/10.1109/CVPR.2017.690
Redmon, J., & Farhadi, A. (2018). YOLOV3: An Incremental Improvement. arXiv:1804.02767.
Sala, M., Soriguera, F., Huillca, K., & Vilaplana, V. (2019). Measuring traffic lane-changing by converting video into space–time still images. Computer-Aided Civil and Infrastructure Engineering, 34(6), 488–505. https://doi.org/10.1111/mice.12430
Siqueira, A. F., Peixoto, C. J. T., Wu, C., & Qian, W. L. (2016). Effect of stochastic transition in the fundamental diagram of traffic flow. Transportation Research Part B: Methodological, 87, 1–13. https://doi.org/10.1016/j.trb.2016.02.003
Tak, S., Woo, S., & Yeo, H. (2016). Study on the framework of hybrid collision warning system using loop detectors and vehicle information. Transportation Research Part C: Emerging Technologies, 73, 202–218. https://doi.org/10.1016/j.trc.2016.10.014
Talebpour, A., Mahmassani, H. S., & Hamdar, S. H. (2015). Modeling lane-changing behavior in a connected environment: A game theory approach. Transportation Research Part C: Emerging Technologies, 59, 216–232. https://doi.org/10.1016/j.trc.2015.07.007
Thiemann, C., Treiber, M., & Kesting, A. (2008). Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data. Transportation Research Record, 2088(1), 90–101. https://doi.org/10.3141/2088-10
Tian, J., Treiber, M., Ma, S., Jia, B., & Zhang, W. (2015). Microscopic driving theory with oscillatory congested states: Model and empirical verification. Transportation Research Part B: Methodological, 71, 138–157. https://doi.org/10.1016/j.trb.2014.11.003
Toledo, T., Koutsopoulos, H. N., & Ahmed, K. I. (2007). Estimation of vehicle trajectories with locally weighted regression. Transportation Research Record, 1999(1), 161–169. https://doi.org/10.3141/1999-17
Tordeux, A., Lassarre, S., & Roussignol, M. (2010). An adaptive time gap car-following model. Transportation Research Part B: Methodological, 44(8–9), 1115–1131. https://doi.org/10.1016/j.trb.2009.12.018
Treiterer, J., & Myers, J. (1974). The hysteresis phenomenon in traffic flow. Transportation and Traffic Theory, 6, 13–38.
Wang, C., Xu, C., & Dai, Y. (2019). A crash prediction method based on bivariate extreme value theory and video-based vehicle trajectory data. Accident Analysis and Prevention, 123, 365–373. https://doi.org/10.1016/j.aap.2018.12.013
Wang, W., Zhang, W., Guo, H., Bubb, H., & Ikeuchi, K. (2011). A safety-based approaching behavioural model with various driving characteristics. Transportation Research Part C: Emerging Technologies, 19(6), 1202–1214. https://doi.org/10.1016/j.trc.2011.02.002
Wojke, N., Bewley, A., & Paulus, D. (2017). Simple Online and Realtime Tracking with a Deep Association Metric. 2017 IEEE International Conference on Image Processing. https://doi.org/10.1109/ICIP.2017.8296962
Wu, L., & Coifman, B. (2014). Improved vehicle classification from dual-loop detectors in congested traffic. Transportation Research Part C: Emerging Technologies, 46, 222–234. https://doi.org/10.1016/j.trc.2014.04.015
Xu, Y., Yu, G., Wang, Y., Wu, X., & Ma, Y. (2016). A hybrid vehicle detection method based on viola-jones and HOG + SVM from UAV images. Sensors, 16(8), 1325. https://doi.org/10.3390/s16081325
Xu, Y., Yu, G., Wu, X., Wang, Y., & Ma, Y. (2017). An Enhanced Viola-Jones Vehicle Detection Method from Unmanned Aerial Vehicles Imagery. IEEE Transactions on Intelligent Transportation Systems, 18(7), 1845–1856. https://doi.org/10.1109/TITS.2016.2617202
Zhang, T., & Jin, P. J. (2019). A longitudinal scanline based vehicle trajectory reconstruction method for high-angle traffic video. Transportation Research Part C: Emerging Technologies, 103, 104–128. https://doi.org/10.1016/j.trc.2019.03.015
 
Zhao, X., Dawson, D., Sarasua, W. A., & Birchfield, S. T. (2017). Automated Traffic Surveillance System with Aerial Camera Arrays Imagery: Macroscopic Data Collection with Vehicle Tracking. Journal of Computing in Civil Engineering, 31(3), 04016072. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000646
Zheng, J., Suzuki, K., & Fujita, M. (2013). Car-following behavior with instantaneous driver-vehicle reaction delay: A neural-network-based methodology. Transportation Research Part C: Emerging Technologies, 36, 339–351. https://doi.org/10.1016/j.trc.2013.09.010
Zheng, Z., Ahn, S., Chen, D., & Laval, J. (2013). The effects of lane-changing on the immediate follower: Anticipation, relaxation, and change in driver characteristics. Transportation Research Part C: Emerging Technologies, 26, 367–379. https://doi.org/10.1016/j.trc.2012.10.007