A drowsiness detection method based on displacement and gradient vectors

Songklanakarin Journal of Science and Technology (SJST)

卷:40

Pished Bunnun¹  Astuo Yoshitaka²  Sorn Sooksatra³  Toshiaki Kondo³ 

[1] National Electronic and Computer Technology Center, National Science and Technology Development Agency, Khlong Luang, Pathum Thani, 12120 Thailand;

[2] School of Information Sciences, Japan Advanced Institute of Science and Technology, Ishikawa, 923-1292 Japan;

[3] School of Information and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Khlong Luang, Pathum Thani, 12120 Thailand;

关键词: drowsiness detection;    gradient vectors;    displacement vectors;    infrared LEDs;    face detection;   

DOI  :  10.14456/sjst-psu.2018.62

来源: DOAJ

【 摘 要 】

This paper presents a drowsiness detection method for drivers based on visual features in a video sequence. Imageintensities are traditionally visual features. However, it is known that they are directly influenced by lighting conditions. Wepropose a human eye detection method using the normalized cross-correlation between displacement vectors and gradientvectors. Gradient vectors are dependent on lighting conditions but the normalization step makes them independent ofilluminations. In this way, the proposed method can detect human eyes regardless of various lighting conditions. We have alsofound that normalized cross-correlation can be useful, not only for detecting eyes, but also for recognizing open and closed eyestates. To overcome poor lighting conditions, we used infrared auxiliary illumination in order to make the proposed method workevery moment. The computation speed of the proposed method is fast enough to perform at video rates.

【 授权许可】

Unknown