Nighttime Driving Safety Improvement via Image Enhancement for Driver Face Detection

Abstract

Insufficient illumination makes driver face detection at night challenging. This paper proposes an adaptive attenuation quantification retinex (AAQR) method to enhance the details of nighttime images. There are three phases in this method: attenuation restriction, attenuation prediction, and adaptive quantification. The performance of the proposed method was evaluated by employing a robust face detection method via sparse representation. The collected driver face images at night were categorized into three groups (up-down, left-right, and mixed) according to the illumination distribution in each image. Results have shown that the detection rates of the images enhanced by the proposed AAQR method were 82%, 84%, and 91% for the up-down, left-right, and mixed illumination groups, respectively. In comparison to other image enhancement methods, the detection rate of the AAQR method was 2%-36% greater. Furthermore, the mean computing time for a single 640 × 480 nighttime image using AAQR was less than most of the compared advanced methods. Thus, the AAQR method is recommended for applications in driver face detection tasks at night.

Keywords

• Advanced driver assistance systems
• driver face detection
• nighttime driving safety
• image enhancement