即時人眼追蹤於汽車駕駛系統之應用

人臉辨識及即時偵測系統近二十幾年來逐漸受到重視，大量的研究者紛紛投入這方面的研究。事實上人臉辨識系統的應用包括民生、國防、醫療、安全等，範圍相當廣，但環境的變化是目前最大的限制因素。本論文提出一使用灰階CCD攝影機擷取即時影像的方式，首先系統認定影像中灰階值低於某特定值且其輪廓大約符合一圓形的影像為可能的眼睛影像，再以可變樣板進行即時比對以及人眼追蹤。而使用灰階影像的原因乃期望避免環境中因光源不足造成色彩資訊反射不完全，使系統能在昏暗或光源不穩定的環境下正常運作。系統在進行人眼追蹤的同時，系統將記錄下受測者眼睛張開或是闔上時在影像上所產生的差異，計算其構成影像的各點之間的變異數，用以分析受測者是否有眨眼的情形，若變異數過大即代表受測者眼睛為閉上的狀態，詳細分析說明將在文中一一詳述。

關鍵字

人臉辨識；即時影像；灰階影像；樣板比對；人眼追蹤；變異數

並列摘要

Human face recognition and real-time detect system has been more interesting in the last two decades. A large number of researchers have invested efforts in this field of study. In a fact, the applications of human face recognition system have included the people’s livelihood, national defense, medical treatment and security applications. But the variations of environment are the best constraint. The objective of this study is to develop a real-time video system base on gray-level CCD camera. The system will identify if the gray-level value in the image is lower than the threshold, and its outline is nearly a circular form, than it’s maybe the iris region. System will tracking human eyes by the variable templates in real-time. This study builds on gray-level system because of the color information will be muffled when the lower illumination, it may cause the system which is based on color image, can not work under the changeable illumination. When the system is tracking human’s eyes, the system will record how much the variance of the eyes region between the eyes are open or closed. The system will detect the blinking motion by compute the variance of the eyes region image, if it gets a larger variance means the eye is closed. The details will be interpreted in the article.

並列關鍵字

face recognition, Real-time ； Gray-level ； Template Matching ； Eye Tracking ； Variance

參考文獻

[18] 蔡全益，雙影像視覺技術於人臉辨識之研究，國立台北科技大學，工業工程與管理研究所，碩士論文，2005

[1] David Tack, Ian Craw, “Tracking and measuring drivers’ eyes,” Image and Vision Computing, vol. 14, 1996, pp.541-547.

[2] S. Sirohey, A. Rosenfeld, Z. Duric, “A method of detecting and tracking irises and eyelids in video,” Pattern Recognition, vol.35, 2002, pp.1389–1401.

[3] Huachun Tan, Yu-Jin Zhang, “Detecting eye blink states by tracking iris and eyelids,” Pattern Recognition Letters, vol.27, 2006, pp.667–675.

[5] Hyeon Bae, Sungshin Kim, “Real-time face detection and recognition using hybrid-information extracted from face space and facial features,” Image and Vision Computing, vol.23, 2005, pp.1181–1191.

國際替代計量

即時人眼追蹤於汽車駕駛系統之應用

未授權

主題瀏覽