Computer Vision Algorithm and Architecture Design for Visually-Impaired Aid System

近年來，在盲人輔助系統上，電腦視覺分析逐漸變為主流研究方向，在現階段中，最普遍使用的盲人輔助系統為導盲犬與盲人手杖，然而，此種方式包含許多缺點如不方便性及價格昂貴等，在社交的場合或是擁擠的環境中，此種輔助方式極為不適用。此外，當盲人在行走於戶外環境時，它們無法提供環境的分析與障礙物的偵測，相較之下，電子輔助系統是較為理想的解決方式，它們提供了更多環境資訊與導航能力。然而最新的電子輔助系統較為笨重且功能受到限制，在本篇論文中，我們設計了攜帶式視覺分析盲人輔助系統與視覺分析導航系統，此系統幫助盲人行走並提供重要之環境資訊。 首先，我們發展出智慧型以深度圖(Depth Map)為基準之障礙物偵測系統，此系統的高準確度使得盲人可以快速且輕易閃避障礙物，根據深度圖的切割(Segmentation)與空間分布關係，我們提出的演算法可以高達95%以上的準確， 當障礙物被抓取之後，系統會提供障礙物的資訊例如深度、方向等，更進一步使用物體追蹤演算法(Object Tracking)來記錄障礙物之方向與路徑的軌跡，藉此可以預測障礙物未來動線以提早閃避，接著第二部份，為了使盲人了解環境資訊，我們提出深度特性模型(Depth Characteristic Mode)來抽取環境資訊，例如：道路、樓梯與牆壁，此功能可以使得盲人能更了解周遭環境，抽取出這些特定的資訊來使得盲人安全的行走道路、攀爬樓梯、沿著牆壁行走等，在第三部份更透過結合圖形辨識功能(Pattern Recognition)，設計出以全球衛星定位系統GPS(Globe Positioning System)為基準之視覺導航系統(Vision-based Navigation System)，這使得盲人可以在陌生的環境中，更精確定位所在的位置，借此我們 可以達到更精確的導航功能，在論文最後，我們挑出了兩項在系統架構中最為耗 時的區塊來做硬體加速，使得此系統可以達到即時偵測的功能，此兩區塊分別為 圖形切割與型態學操作(Morphology)，我們所用的製程為台積電(TSMC)提供之 65 奈米(nm)製程，此晶片可以操作在200MHz 之頻率，所耗的功率為56 毫瓦(mW)， 透過我們的硬體架構設計，在解析度640*480 之下可以達到2000 張每秒的處理速度，在最為複雜的情況下，也可以有28 張每秒的處理速度。 總合來說，我們提出了一套的盲人輔助系統之演算法與硬體架構設計，其中包含三大部分軟體演算法，分別為障礙物偵測、深度特性模型偵測與視覺導航系統，並且對於其中運算量最高之部份做硬體加速，在65 奈米製程下可使得整體系統可以達到即時偵測之功能。Recently, vision technologies are gradually introduced to electronic aids to assist elder people or the visually-impaired. The most commonly used mobility tools - guide dogs and white canes, are inconvenient and expensive, and have limited usability in recognizing surrounding objects. Electronic vision-based visually impaired aids are smarter as navigation tools that can perceive rich visual information of the environment for the user. However, state-of-the-arts are too bulky and still reveal many limitations such as detecting distant objects in outdoor environments In the thesis, we design a wearable vision-based visually impaired traffic analysis and navigation system for the visually impaired. The system aims to assist blind persons from basic needs to advanced requirements in their lives. First, we develop an intelligent depth-based obstacle detection system that allows blind avoid from from the obstacles easily. Then, to understand the environment, we propose a depth characteristic analysis system to help the blind get some information such as stair, road and wall. We also design a GPS-based visual navigation guide that combines recognition technology and the GPS function to provide higher accurate positioning result for the blind so that they can navigate independently even in an unfamiliar environment. Finally, we pick out the critical path in our system and design a new architecture to speed up the computational time. The chip is operated under 200MHz with 56mW in power consumption. Through our methodologies, 2000 frame with 640?80 resolution per second in general case and 28 frames per second in worst case. Totally speaking, we design a convenient portable vision-based visually impaired aid system for the visually impaired