辨識移動中障礙物做室外自動車導航之研究

A Study on Outdoor Guidance of Autonomous Land Vehicles by Detecting the Moving Obstacle

蘇英銓(Ying-Chuan Su)

指導教授 ： 駱榮欽 ； 洪永銘

國立臺北科技大學/機電學院/機電整合研究所/碩士(2008年)

摘要

本論文中，我們發展了一套人工智慧的行進間室外導航車系統可使車輛辨別移動中的障礙物以輔助於自動導航。本論文所提出的方法可找出移動中物體外並且偵測出障礙物移動的方向。更進一步的判斷是否會與自動導航車發生碰撞，提供自動導航車做出適合的避碰策略規劃。 室外自動導航車三個主要的部分的演算法，分別為影像擷取系統，靜態障礙物分析系統, 與動態物體分析系統。我們設定自動車是在一個戶外的環境做自動導航。 在分析上，我們使用的是以Lucas and Kanade的光流方程式。為了讓行進間的自動車偵測運動中的障礙物，首先我們必須有效的切割光流圖以便分割出圖片內的背景與物體。利用在光流場圖內檢測出每個像素所改變的向量，然後使用三維統計直方圖計直方圖統計異常的光流群組所代表的特徵，確認我們所判斷道路背景與運動中障物的位置，再經由型態學處理雜訊後可偵測出障礙物。在偵測出動態的障礙物以後，我們再利用一階線性方程式來預測出移動中物體與室外自動車到達預測的碰撞點時間關係後，使自動導航車產生策略去避免可能的碰撞。 實驗結果顯示了本論文提出的方法確實有效的閃躲移動中的物體並且進行自動車的導航。

關鍵字

光流光流場圖 ； 三維直方圖 ； 室外自動導航車

並列摘要

In this paper, we develop the system of autonomous land vehicles (ALV) by computer vision with artificial intelligent (AI) based on optical flow method. It makes ALV adapted to the complex environment. This system can verify the motion obstacle and estimate its movement, and then making path strategy to avoid collision.
Our algorithm of ALV has three parts, image capture system, static object analyzed system, and motion object detection system, respectively. We set ALV navigates at an outdoor environment automatically.
In computer vision analyzed, we present a method that use Lucas and Kanade's Optical flow equation, then we obtain the optical flow map, by using three-dimension histogram (3-D histogram) to gather statistics of our moving object, checking our optical vectors group, separating the optical vectors of obstacle and background, and use morphological process to segment the moving object. We segment them and use first-order linear equation to calculate the relationship between ALV and the motion obstacle. At last, calculate the collision time between the moving object and ALV and makes strategy to avoid collision with obstacle.
Finally, our experiment shows the method avoiding collision with moving object efficiently when ALV moving on its way.

並列關鍵字

Optical Flow ； Optical flow map ； Three Dimension Histogram ； Autonomous Land Vehicles

參考文獻

[1] M. Bertozzi, A. Broggi, A. Fascioli, “Vision-based intelligent vehicles: State of the art and perspective,” J. of Robotics and Autonomous Systems, June 2000 , pp. 1-16.

[4] 葉哲昌，利用鬆弛相關性改進3D對應點匹配與重建應用於室外自動導航車，碩士論文，國立臺北科技大學自動化科技研究所，台北，2006。

[6] Yinghua He, Hong Wang, and Bo Zhang, “Color-Based Road Detection in Urban Traffic Scenes,” IEEE Trans, Intelligent Transportation Systems, Vol. 5, No. 4, Dec 2004, pp. 309-318.

[7] Ma, J.; Ahuja, N., “Region Correspondence by Global Configuration Matching and Progressive Delaunay Triangulation,” IEEE Conference,” Vol2, June, 2000 pp.13-15.

[8] Il-Kyun Jung; Lacroix, S., “A robust interest points matching algorithm,” Eighth IEEE International Conference,” Vol2, July, 2001, pp.7-14.