Night Vehicle Detection Using Variable Haar-Like
Feature
Jae-do KIM1, Sang-hee KIM2, Young-joon HAN1, Hern-soo HAHN1
【摘 要】Abstract-This paper proposes a night-time vehicle detection method using variable Haar-like feature. The specific features of front vehicle cannot be obtained in road image at night-time because of light reflection and ambient light, and it is also difficult to define optimal brightness and color of rear lamp according to road conditions. In comparison, the difference of vehicle region and road surface is more robust for road illumination environment. Thus, we select the candidates of vehicles by analysing the difference, and verify the candidates using those brightness and complexity to detect vehicle correctly. The feature of brightness difference is detected using variable horizontal Haar-like mask according to vehicle size in the location of image. And the region occurring rapid change is selected as the candidate. The proposed method is evaluated by testing on the various real road conditions.【期刊名称】测试科学与仪器【年(卷),期】2011(002)004【总页数】4
【关键词】Key words-vehicle detection; variable Haar-like feature; brightness distribution analysis
1 Introduction
In the past, the strength and reliability of vehicle structure are tested repeatedly on real conditions to secure vehicle safety. Intelligent safety is pursued by discerning and detecting main causes of vehicle accidents recently. Mostly, the major cause of vehicle accidents is careless driving of a driver.
In particular, the visibility at night is poorer than daytime and drowsy driving is occurring more often at that time
Numerous studies for detecting vehicle at night-time are being researched. The night-time image, basically, does not include detailed information because the quantity of light is very little. In order to solve this problem, many techniques are being researched to enhance contrast and color of night image[1-2].
Night Vehicle Detection Using Variable Haar-Like Feature
