Hyperspectral Image-Based Night-Time Vehicle Light Detection Using Spectral Normalization and Distance Mapper for Intelligent Headlight Control

Heekang Kim; Soon Kwon; Sungho Kim

doi:10.3390/s16071058

Hyperspectral Image-Based Night-Time Vehicle Light Detection Using Spectral Normalization and Distance Mapper for Intelligent Headlight Control

Sensors (Basel). 2016 Jul 8;16(7):1058. doi: 10.3390/s16071058.

Authors

Heekang Kim¹, Soon Kwon², Sungho Kim³

Affiliations

¹ Department of Electronic Engineering, Yeungnam University, 280, Daehak-ro, Gyeongsan-si, Gyeongsangbuk-do KS011, Korea. kimhk@ynu.ac.kr.
² Daegu Gyeongbuk Institute of Science and Technology, 333, Techno jungang-daero, Hyeonpung-myeon, Dalseong-gun, Daegu KS002, Korea. soonyk@dgist.ac.kr.
³ Department of Electronic Engineering, Yeungnam University, 280, Daehak-ro, Gyeongsan-si, Gyeongsangbuk-do KS011, Korea. sunghokim@ynu.ac.kr.

Abstract

This paper proposes a vehicle light detection method using a hyperspectral camera instead of a Charge-Coupled Device (CCD) or Complementary metal-Oxide-Semiconductor (CMOS) camera for adaptive car headlamp control. To apply Intelligent Headlight Control (IHC), the vehicle headlights need to be detected. Headlights are comprised from a variety of lighting sources, such as Light Emitting Diodes (LEDs), High-intensity discharge (HID), and halogen lamps. In addition, rear lamps are made of LED and halogen lamp. This paper refers to the recent research in IHC. Some problems exist in the detection of headlights, such as erroneous detection of street lights or sign lights and the reflection plate of ego-car from CCD or CMOS images. To solve these problems, this study uses hyperspectral images because they have hundreds of bands and provide more information than a CCD or CMOS camera. Recent methods to detect headlights used the Spectral Angle Mapper (SAM), Spectral Correlation Mapper (SCM), and Euclidean Distance Mapper (EDM). The experimental results highlight the feasibility of the proposed method in three types of lights (LED, HID, and halogen).

Keywords: Intelligent Headlight Control; headlight detection; hyperspectral image; intelligent transportation system; rear lamp detection; spectral distance.