English  |  正體中文  |  简体中文  |  Items with full text/Total items : 78345/78345 (100%)
Visitors : 32621832      Online Users : 1175
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/44682

    Title: 以動態視覺為基礎的前車停止啟動與俯瞰碰撞偵測;Stop-and-go and Top-view Obstacle Detection based on Dynamic Vision
    Authors: 藍易康;Lan-Yi Kang
    Contributors: 資訊工程研究所
    Keywords: 前車啟動;前車停止;俯瞰碰撞偵測;stop-and-go;Top-view
    Date: 2010-07-27
    Issue Date: 2010-12-09 13:52:38 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 在都市內行車有較多的不便與危險;在本研究中,我們針對以下兩種情況做安全偵測。第一種情況,在都市行駛車輛時會有不少的時間是在等待交通號誌的變換或是在走走停停的擁擠車陣中。在等待交通號誌或是塞車的這段時間,駕駛人可能會分心或做其他事情,若此時前方車輛已往前駛離或是停止,可能就會造成不便或碰撞。第二種情況則是車輛在都市中行駛有汽機車靠近,但車體的結構與後照鏡的角度會影響後視視野而導致有部份盲點且同時難以注意車輛週遭其餘區域的情況,使得駕駛無法全面顧及車輛週遭環境,如此就有可能發生擦撞。在本研究中,我們提出前車停止啟動偵測與俯瞰碰撞偵測的方法,可幫助駕駛者了解前車的動向及己車周遭移動物體之動向,在發生危險之前告知駕駛人,使駕駛更為方便及安全。在前車停止啟動偵測與俯瞰碰撞偵測的方法中,相同的部份都是先偵測角點,利用角點做光流向量的估計,得到動態資訊後,再各別做前車停止啟動偵測或俯瞰碰撞偵測。 在前車停止與啟動偵測方面,篩選光流向量並調整光流向量的大小,將同一物體之光流向量調整成為大小差不多的向量,接著利用此條件將向量分群得到移動區塊,再對移動區塊判斷前車是否啟動或停止,並能避免己車前方與側方各方向汽機車與行人之影響、夜間側後方來車大燈造成前方車亮度變化、夜間各種燈光造成的明暗變化、雨天之雨刷擺動、陰晴變化等因素所造成的誤判,給予駕駛人正確的警示。 在俯瞰碰撞偵測方面,我們先篩選適合的光流向量,再利用光流向量的方向、位置、及大小做分群,對分群得到的移動區塊分析其移動的軌跡及與己車碰撞的可能碰撞時間判斷是否要給予駕駛者警告。 前車停止啟動偵測與俯瞰碰撞偵測的方法在Intel? Pentium? Core2 Duo 1.86GHz及2GB RAM的個人電腦上執行,在前車停止啟動偵測可達每秒25至30張畫面,正確率可達99?;而在俯瞰碰撞偵測可達每秒25至30張畫面,正確率可達98?。It is inconvenience and danger while driving in urban areas. Drivers spend much time waiting for traffic signals and stuck in jams. Lack of concentration at such moments may lead to accidents. Due to the limitation of field of view, drivers are mostly unable to see all the area around the vehicle during driving. For the safety of drivers, the stop-and-go and top-view obstacle detection methods are proposed in this study. Corners are used as features to calculate optical flow. We perform stop-and-go and top-view obstacle detections based on the optical flow. In the stop-and-go detection method, we first filter optical flow and adjust the length of optical flow. The length of optical flows of an object is almost the same. The adjusted length is used as the condition for clustering. Then, we use these moving objects to recognize whether the front vehicle is stopping or going. This detection method can also avoid the effects of vehicles in different direction, variant weather, and the light at nighttime. In the top-view obstacle detection method, the direction, position, and length of optical flows are used as condition for clustering. By analyzing the trajectory of moving objects and computing the possible collision time, we can recognize whether the moving object is dangerous. The proposed methods are evaluated in several variant environments. The detection rate of stop-and-go method is 99? and the frame rate is 25 frames per second. The detection rate of the top-view detection method is 98? and the frame rate is 30 frames per second.
    Appears in Collections:[資訊工程研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明