請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/8708
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕 | |
dc.contributor.author | Pei-Kai Hsu | en |
dc.contributor.author | 許焙凱 | zh_TW |
dc.date.accessioned | 2021-05-20T20:00:01Z | - |
dc.date.available | 2010-02-24 | |
dc.date.available | 2021-05-20T20:00:01Z | - |
dc.date.copyright | 2010-02-24 | |
dc.date.issued | 2010 | |
dc.date.submitted | 2010-02-10 | |
dc.identifier.citation | [1] S. K. Kemue, “LANELOK: Detection of lane boundaries and vehicle tracking using image-processing techniques – Parts I and II” SPIE Mobile Robots IV, 1989.
[2] K.C. Kluge, YARF: An Open-Ended Framework for Robot Road Following, PH.D Thesis, Carnegie Mellon University, 1993. [3] K.C. Kluge, “Extracting road curvature and orientation from image edge points without perceptual grouping into features,” Proceedings of the Intelligent Vehicle ’94 Symposium, pp.109-114, 1994. [4] D. Pomerleau and T. Jochem, “Rapidly Adapting Machine Vision for Automated Vehicle Steering,” IEEE Expert, 11, (2), pp.302-7, April 1996. [5] K. C. Kluge, “Performance evaluation of vision-based lane sensing: some preliminary tools, metrics and result,” IEEE Conference on Intelligent Transportation System, 1997. [6] K. Y. Chiu and S. F. Lint, “Lane Detection using Color-Based segmentation”, Department of Electrical and Control Engineering, National Chiao-Tung University, Taiwan, ROC. [7] S. Terakubo, et. al., “Development of an AHS safe driving system,” SEI Technical Review, no. 45, pp.71-77, 1998. [8] M. Y. Chern, B. Y. Shyr, 'Locating nearby vehicles on highway at daytime based on the front vision of a moving car,' Proceedings of Robotics and Automation, vol. 2, 2003, pp. 2085 - 2090. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/8708 | - |
dc.description.abstract | 行車駕駛輔助系統是保護駕駛人及用路人安全很重要的設備之一,但是這種行車駕駛輔助系統通常由雷達或影像辨識技術達成,雷達系統因為配備昂貴通常是在高階的房車才會裝有這種系統,而影像辨識系統以目前的研究技術都要搭配相當高階的電腦系統如Intel Penten-4 3.0G CPU + 1G Ram才能達到與雷達系統相當的水平。 我們認為如果要在車上裝一台這麼高階的電腦系統才能成為行車駕駛輔助系統勢必是沒有使用者能接受,所以本論文的研究著重在尋求一套好的演算法能夠在準確度與裝置效能上達到一個平衡點。
現今,智慧型手機越來越普及化,RISC CPU運算能力已經能達到500MHz以上,加上它目前都具有Camera 及GPS功能,體積上也相當適合裝置在車上,而且Microsoft 也從 Windows Mobile 5.0以後訂出了透過Direct Show控制Camera及GPS的標準界面,所以我們選擇在智慧型手機上開發一套行車駕駛輔助系統讓擁有智慧型手機的駕駛人除了把智慧型手機拿來做導航外能多出行車駕駛輔助系統功能。 傳統的影像辨識技術除了需要運算能力很高階的電腦外,另一個問題就是架設上非常繁瑣,通常需要知道相機鏡頭的參數及架設位置,一般使用者很難自行去架設這樣的一個系統,所以我們的系統在設計時加入了這個考量,特別搭配GPS設計出不需要知道相機鏡頭參數及架設位置就能自動校正系統並且辨識出可能的車距。 我們的系統使用HTC Diamond 1 (P3700)這款智慧型手機做實驗,其具備QUALCOMM 7201A的RISC CPU,CPU 速度為528MHz及192MB RAM,是目前最普遍的智慧型手機架構,實驗證實我們的演算法能在這樣的系統上在100毫秒內處裡一個frame,也就是說我們能提前100毫秒就通知駕駛人可能發生的危險,保護其生命安全。 | zh_TW |
dc.description.abstract | A driver assistance system is an important device to keep the driver and passerby safe. This kind of device consists of radar system or computer vision in general. The radar system just sets in high-end cars and is very expensive. The computer vision system needs powerful computer with Penten-4 3.0G CPU and 1 gigabytes memory for qualifying with radar system. Most users need a useful driver system but might have difficulties to set this kind of computer devices. In this thesis, we have tried to develop an algorithm which has the competence in balancing the performance and the accuracy of this kind of system.
The smart phone becoming increasingly popular now, it has RSIC CPU which fast than 500 MHz and has camera and GPS system. The size of smart phone is also suite for setting on car. Microsoft had supported camera controlling by “Direct Show” and GPS APIs after Windows Mobile 5.0. Therefore, we chosen smart phone to be our target development device. We wish to make the smart phone not only has navigation function but also driver assistance system. The traditional computer vision system needs a powerful computer and complexity setup routine. Usually, users need to provide the focus length of camera and setting position. It is hard for users to set up this kind of system by themselves. By the way, we collocate with GPS to design an auto calibration system to avoid this complex set up routine. We chose HTC Diamond 1 (P3700) to be our experiment device. It has QUALCOMM 7201A RISC CPU which has 528MHz CPU speed and 192 mega bytes ram. This is the most popular smart phone architecture recently. We verified that we can make a decision in 100 milliseconds by our algorithm with this device. In other words, we can alert the driver an emerging danger 100 milliseconds n advance and keep them safe. | en |
dc.description.provenance | Made available in DSpace on 2021-05-20T20:00:01Z (GMT). No. of bitstreams: 1 ntu-99-P95922004-1.pdf: 1935072 bytes, checksum: 904ef93aa4fe8e1dda9147f2cdf0c752 (MD5) Previous issue date: 2010 | en |
dc.description.tableofcontents | 摘要......................................i
Abstract.................................ii Chapter 1 Introduction ...................1 1.1 Motivation............................1 1.2 Related Work..........................2 1.3 Objective.............................3 1.4 System Overview.......................3 1.5 Organization of this thesis...........5 Chapter 2 Road Cropping...................6 2.1 HSV Color Model.......................6 2.2 Lane Filter...........................9 2.3 Cache Enhance Lane Filter Coding......9 2.4 Lane Probed Algorithm................11 2.5 Road Area Conjecture.................14 Chapter 3 Accurate Lane Detection........17 3.1 Image Normalization..................17 3.2 Lane and Vehicle Detection...........18 3.3 Extract Lane.........................21 3.4 Lane Model...........................21 3.5 Slope Histogram......................23 3.6 Lane Voting..........................23 Chapter 4 Vehicle Detection..............27 4.1 Detect Vehicle by the Shadow.........27 4.2 C-means..............................27 Chapter 5 Auto Calibration...............29 5.1 GPS..................................29 5.2 Auto Calibration.....................29 Chapter 6 Distance Measurement...........32 Chapter 7 Experiment.....................33 7.1 Hardware Environment Description.....33 7.2 Software Environment Description.....34 7.3 Get Image by Direct Show.............34 7.4 Experiment Result....................35 Chapter 8 Conclusions and Future Works...37 Reference................................38 | |
dc.language.iso | zh-TW | |
dc.title | 具自動設定之駕駛輔助系統在智慧型手機上的應用 | zh_TW |
dc.title | A Calibration Free Driver Assistance System on Mobile Phone | en |
dc.type | Thesis | |
dc.date.schoolyear | 98-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 王傑智,陳彥仰 | |
dc.subject.keyword | 行車輔助系統,智慧型手機,電腦視覺,Windows Mobile,車道偵測,GPS,相機, | zh_TW |
dc.subject.keyword | Driver Assistance System,Smart Phone,Computer Vision,Windows Mobile,Lane Detection,GPS,Camera, | en |
dc.relation.page | 38 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2010-02-10 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-99-1.pdf | 1.89 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。