跳到主要內容

臺灣博碩士論文加值系統

(34.204.198.73) 您好!臺灣時間:2024/07/21 16:54
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:邱哲楠
研究生(外文):Zhe-Nan Chiu
論文名稱:基於多層深度學習之預測駕駛煞車行為
論文名稱(外文):Predicting Driver Braking Action Using Multi-Layer DeepLearning Sensory Fusion
指導教授:賴國華
指導教授(外文):K. Robert Lai
口試委員:簡廷因黃柏鈞
口試委員(外文):Ting-Ying ChienPo-Chun Huang
口試日期:107-6-25
學位類別:碩士
校院名稱:元智大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:106
語文別:中文
論文頁數:33
中文關鍵詞:深度學習駕駛煞車預測先進駕駛輔助系統預警式分析
外文關鍵詞:Deep learningPrediction of driver brakingAdvanced driver assistance systemPredictive analysis
相關次數:
  • 被引用被引用:0
  • 點閱點閱:191
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在先進駕駛輔助系統中,未及時煞車行為是一個重要的議題,因為它會使駕駛暴露在危險的行車環境中,因此,提早且準確地預測駕駛煞車行為是必須的,可降低潛在的危險並為駕駛爭取更多的時間做出反應。在本篇論文中,我們收集車內外多元的豐富資料,並提出多層深度學習架構convolutional neural network (CNN)加上bidirectional long short-term memory units (BL)去預測即將發生的煞車行為,CNN精於提取行車資料的特徵而BL善於保有資料的時間序列性。實驗結果顯示不論是在預測煞車行為的前五秒內、車速高或車速低的情境下、或是在路口及轉彎的煞車行為,我們的架構在準確率和f-score方面,皆優於其他兩種深度學習架構:BL及uni-LSTM。此外,對於駕駛人方面,我們採取leave-one-out交叉驗證,呈現整體行車資料對於不同駕駛人的結果並探討之。
In advanced driver assistance system (ADAS), non-timely braking action is one of the important issues because it makes drivers exposed to a terrible and dangerous driving environment. For this reason, predicting driver braking action early and accurately must appear up, which can lower the potential of unsafe driving behavior and provide drivers more time to react. In this paper, we have sensory fusion data source from inside and outside of the car and our proposed multi-layer deep learning architecture (CBL) to predict braking action, which consists of convolutional neural network (CNN) and bidirectional long short-term memory units (BL) while CNN is good at extracting driving characteristic and BL is useful for keeping time-series data. The result points that the CBL performs much better than the other two architectures: bidirectional LSTM (BL) and uni-LSTM (UL) based on the high accuracy and f-score, and it also shows leave-one-out cross validation for drivers and many interesting differences in the speed, turning and intersection from time -5s to 0s.
摘要 iii
ABSTRACT iv
誌謝 v
目錄 v
表目錄 viii
圖目錄 ix
第一章、緒論 1
1.1 研究動機 1
1.2 研究目的 1
1.3 研究架構 3
第二章、文獻回顧 5
2.1駕駛行為分析之資料選擇 5
2.2 駕駛煞車行為分析之資料選擇 5
2.3 深度學習之駕駛煞車行為分析 6
第三章、研究架構 7
3.1 系統概論 7
3.2 多層深度學習架構 8
3.2.1 多維標度法 Multidimensional scaling (MDS) 8
3.2.2 卷積神經網絡 Convolutional Neural Network (CNN) 9
3.2.3 雙向長短期記憶模型 Bidirectional LSTM (BL) 10
第四章、評估與結果 12
4.1 實驗規劃 12
4.1.1 不平衡資料 16
4.1.2 YOLO 物件偵測 16
4.1.3 網絡訓練 17
4.2 研究結果 17
4.2.1 評估指標 18
4.2.2 整體 煞車行為 18
4.2.3 高速/低速 煞車行為 19
4.2.4 轉彎 煞車行為 21
4.2.5 路口 煞車行為 22
4.2.6 情境比較 23
4.2.7 駕駛人模型比較 25
第五章、結論 30
參考文獻 31
1. Lyu, N., et al., A field operational test in China: Exploring the effect of an advanced driver assistance system on driving performance and braking behavior. Transportation Research Part F: Traffic Psychology and Behaviour, 2018.
2. Wang, J., W. Xu, and Y. Gong, Real-time driving danger-level prediction. Engineering Applications of Artificial Intelligence, 2010. 23(8): p. 1247-1254.
3. Gao, J. and G.A. Davis, Using naturalistic driving study data to investigate the impact of driver distraction on driver's brake reaction time in freeway rear-end events in car-following situation. Journal of safety research, 2017. 63: p. 195-204.
4. Kim, J.-W., et al. Combined regression and classification approach for prediction of driver's braking intention. in Brain-Computer Interface (BCI), 2015 3rd International Winter Conference on. 2015. IEEE.
5. Bellet, T., et al., A computational model of the car driver interfaced with a simulation platform for future Virtual Human Centred Design applications: COSMO-SIVIC. Engineering Applications of Artificial Intelligence, 2012. 25(7): p. 1488-1504.
6. Kumtepe, O., G.B. Akar, and E. Yuncu. Driver aggressiveness detection using visual information from forward camera. in Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on. 2015. IEEE.
7. Liu, H., et al., Visualization of driving behavior based on hidden feature extraction by using deep learning. IEEE Transactions on Intelligent Transportation Systems, 2017. 18(9): p. 2477-2489.
8. Hori, C., et al. Driver confusion status detection using recurrent neural networks. in Multimedia and Expo (ICME), 2016 IEEE International Conference on. 2016. IEEE.
9. Jain, A., et al., Brain4cars: Car that knows before you do via sensory-fusion deep learning architecture. arXiv preprint arXiv:1601.00740, 2016.
10. Dong, W., et al., Characterizing driving styles with deep learning. arXiv preprint arXiv:1607.03611, 2016.
11. Christopoulos, S.-R.G., S. Kanarachos, and A. Chroneos, Learning Driver Braking Behavior Using Smartphones, Neural Networks and the Sliding Correlation Coefficient: Road Anomaly Case Study. IEEE Transactions on Intelligent Transportation Systems, 2018.
12. Lv, C., et al., Hybrid-Learning-Based Classification and Quantitative Inference of Driver Braking Intensity of an Electrified Vehicle. IEEE Transactions on Vehicular Technology, 2018.
13. Duan, J., et al., Driver braking behavior analysis to improve autonomous emergency braking systems in typical Chinese vehicle-bicycle conflicts. Accident Analysis & Prevention, 2017. 108: p. 74-82.
14. Jalali, M., et al., Model predictive control of vehicle stability using coordinated active steering and differential brakes. Mechatronics, 2017. 48: p. 30-41.
15. Shirazi, M.S. and B. Morris. Observing behaviors at intersections: A review of recent studies & developments. in Intelligent Vehicles Symposium (IV), 2015 IEEE. 2015. IEEE.
16. Jiang, L., X. Chen, and W. He. SafeCam: Analyzing intersection-related driver behaviors using multi-sensor smartphones. in Pervasive Computing and Communications (PerCom), 2016 IEEE International Conference on. 2016. IEEE.
17. Oliver, N. and A.P. Pentland. Driver behavior recognition and prediction in a SmartCar. in PROC SPIE INT SOC OPT ENG. 2000. Citeseer.
18. Li, Y., et al. Braking assistance algorithm considering driver characteristics at signalized intersection. in Transportation Information and Safety (ICTIS), 2017 4th International Conference on. 2017. IEEE.
19. Wang, W., J. Xi, and D. Zhao, Learning and Inferring a Driver's Braking Action in Car-Following Scenarios. arXiv preprint arXiv:1801.03905, 2018.
20. Jing, S. and Z. Zhihua. A study on prediction of vehicle critical follow distance based on driver's behavior by using BP neural network. in Measuring Technology and Mechatronics Automation (ICMTMA), 2013 Fifth International Conference on. 2013. IEEE.
21. Olabiyi, O., et al., Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network. arXiv preprint arXiv:1706.02257, 2017.
22. Wickelmaier, F., An introduction to MDS. Sound Quality Research Unit, Aalborg University, Denmark, 2003. 46(5).
23. Hauke, J. and T. Kossowski, Comparison of values of Pearson's and Spearman's correlation coefficients on the same sets of data. Quaestiones geographicae, 2011. 30(2): p. 87-93.
24. LeCun, Y., et al., Object recognition with gradient-based learning, in Shape, contour and grouping in computer vision. 1999, Springer. p. 319-345.
25. Hochreiter, S. and J. Schmidhuber, Long short-term memory. Neural computation, 1997. 9(8): p. 1735-1780.
26. Chawla, N.V., N. Japkowicz, and A. Kotcz, Special issue on learning from imbalanced data sets. ACM Sigkdd Explorations Newsletter, 2004. 6(1): p. 1-6.
27. He, H. and E.A. Garcia, Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 2009. 21(9): p. 1263-1284.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top