- 學位論文
智慧型人車越道安全監視系統
Pedestrian and Vehicle Classification Surveillance System for Street-Crossing Safety
摘要
本論文提出了一個智慧型人車分類及越道安全監視系統。我們利用一個兩階段的演算法，且能有效地對物件進行分類。首先，對於移動物件進行偵測、追蹤，並且估測物件的移動速度，而將物件分成快速物件種類與慢速物件種類物。這樣的方式使我們能夠利用物件的寬度來分辨出汽車與機車。對於慢速物件而言，我們提出一個grey-scale based Recurrent Motion Image(GRMI)，來改進原始RMI行人辨識的缺點。再來我們採用Haar-like特徵與Adaboost學習演算法來區分行人與機車。最後關於汽車與機車，我們是使用物件的aspect ratio (AR)與面積特徵來進行分類。根據實驗，我們對524個物件進行辨識，且辨識率達95.99%。本系統能夠有效地運用於交通監控系統。
並列摘要
This thesis presents a framework for automatic pedestrian and motor vehicle classification in a street-crossing safety surveillance system. The proposed method is a coarse to fine classification approach divided into two stages. In the first stage, the moving objects are detected, tracked and clustered into fast moving and slow moving categories according to a motion speed estimation method. This approach is applicable to identify motor vehicles and further differentiate cars from scooters using width and shape features. The second stage identifies slow moving objects. We proposed the grey-scale based Recurrent Motion Image (GRMI) to overcome the drawbacks of the original RMI. Haar-like features and the Adaboost algorithm are then employed to distinguish between pedestrians and scooters. Cars and scooters are classified using the object aspect ratio (AR) and area feature. The experimental results show that the recognition rate for 524 objects achieved 95.99%. The proposed system is promising for application to the traffic monitoring surveillance system.
參考文獻
延伸閱讀
- 陳永安（2009）。智慧型路口行人安全警示系統〔碩士論文，國立臺北科技大學〕。華藝線上圖書館。https://doi.org/10.6841/NTUT.2009.00341
- 黃莫凱（2006）。全方位智慧型車輛--前車追撞及車道偏離警示系統〔碩士論文，國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU.2006.00932
- Chen, S. Y. (2012). 智慧型道路監控系統 [doctoral dissertation, Yuan Ze University]. Airiti Library. https://doi.org/10.6838/YZU.2012.00040
- 麥毅廷、陳振庸、陳怡伸、楊大威、高資淵、紀佳瑋（2011）。智慧型行車防撞安全系統。修平學報，(22)，135-152。https://doi.org/10.29548/BGYY.201103.0009
- 白家榮（2001）。Pedestrian detection and tracking at crossing〔碩士論文，國立臺灣師範大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0021-2603200719120017