English  |  正體中文  |  简体中文  |  Items with full text/Total items : 888/888 (100%)
Visitors : 12017038      Online Users : 507
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://ccur.lib.ccu.edu.tw/handle/A095B0000Q/340


    Title: 利用模糊語意影像特徵表示法及FPGA平台之車內人臉偵測與定位研究;A Face Detection and Localization System for Driver Using Semantic-based Vague Image Representation and a FPGA Platform
    Authors: 陳紀安;CHEN, CHIN-AN
    Contributors: 電機工程研究所
    Keywords: 現場可程式邏輯閘陣列;影像模糊語意影像特徵表達法;人臉偵測與定位;SVIR;Face localization;Face detection;FPGA
    Date: 2016
    Issue Date: 2019-07-17
    Publisher: 電機工程研究所
    Abstract: 近幾年來,台灣車輛肇事率逐年攀升,其事故發生原因多為駕駛未注意前方車輛行駛狀況所致。因此,近年來各大車廠陸續開發出可事先偵測並提醒駕駛者是否專心開車的預警系統,以期有效降低此類交通事故的發生。其中,以利用人臉來判斷駕駛之專注情況最值得研究。然而,由於車內空間有限,導致人臉偵測之運算能力也隨之受限。為此,本研究專注於開發一套低體積、低功耗之人臉追蹤系統,以便未來對人臉姿態及表情做進一步之分析。在本研究計畫中,系統首先利用數位相機取得人臉影像,接著採用模糊語意影像特徵表達法(Semantic-based Vague Image Representation, SVIR) 來完成人臉特徵辨識及追蹤。此演算法之特色在於以更少的運算資源,就能夠有效地達到人臉追蹤之目的。而精簡之演算過程,更能幫助本研究實現在系統單晶片之上,進而達到體積小、低功耗以及即時處理之效能。在晶片設計方面,則是採用現場可程式邏輯閘陣列(Field Programmable Gate Array, FPGA)晶片做為測試開發平台,以符合體積小與低開發成本之目的,以期能讓此系統未來能夠更加普及化。最後,在本論文的實驗結果中,本系統設計除了達成人臉偵測與定位之目的,系統資源使用量也僅占晶片運算資源的6.24%,消耗286.83 mW的功率。其功耗少於傳統偵測法使用的高耗能處理器,不但符合先前的研究目標,精簡化的運算過程也使得本系統能在低體積且低性能的晶片上達成高解析度和即時處理。因此,本研究的新式設計有助於未來基於嵌入式裝置的人臉偵測系統之發展。
    The traffic accident in Taiwan has been gradually increased in recent years by distraction to vehicle in front. To improve this issue, many car manufacturers have developed various assistant systems to warn driver before accident. However, the lower computing power constrained by narrow space in car is a critical problem for developing an intelligent driving assistant system. For this, this research focuses on the feasibility for designing a compact, low-power, and low-cost face tracking for driver, which is helpful to monitor driver’s condition in real-time.In this research, a digital camera is employed to collect driver’s face. Meanwhile, a novel and concise algorithm of semantics-based vague image representation (SVIR) is also adopted to abstract driver’s face features in order to implement entire system on a single chip. Here a field-programmable gate array (FPFA) developing platform is working as a test bed in which it demonstrates the feasibility for a low-power and low-cost face tracking system.According to the experimental results, the proposed system has a lower power consumption at 286.83mW with only 6.24% hardware resource usage of chip. With this design, driver’s face can be effectively tracked during the scanning of image pixels. Such real-time performance is workable and promising for drive’s assistant system in the future.
    Appears in Collections:[電機工程研究所] 學位論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML321View/Open


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


    版權聲明 © 國立中正大學圖書館網頁內容著作權屬國立中正大學圖書館

    隱私權及資訊安全政策

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback