An Algorithm for Accurate Taillight Detection at Night

Abstract

Vehicle detection is an important process of many advance driver assistance system (ADAS) such as forward collision avoidance, Time to collision (TTC) and Intelligence headlight control (IHC). This paper presents a new algorithm to detect a vehicle ahead by using taillight pair. First, the proposed method extracts taillight candidate regions by filtering taillight colour regions and applying morphological operations. Second, pairing each candidates and pair symmetry analysis steps are implemented in order to have taillight positions. The aim of this work is to improve the accuracy of taillight detection at night with many bright spot candidates from streetlamps and other factors from complex scenes. Experiments on still images dataset show that the proposed algorithm can improve the taillight detection accuracy rate and robust under limited light images. General TermsThe general term of this study is image processing and computer vision.

Infrastructure-free NLoS Obstacle Detection for Autonomous Cars

“…Taillight Detection at Nights. Even though it is statistically more dangerous to drive at night, a survey of the literature suggests that vision based ADAS for night-time driving is less focused on [22], [3]. Instead vision based vehicle detection at day time is covered more broadly [24], [23], [21].…”

“…Despite this positive trend still around 1.3M fatalities occur due to road accidents every year according to the World Health Organization (WHO) 2 . Specifically dangerous are night time driving scenarios 3 and almost half of the intersection related crashes are caused due to the driver's inadequate surveillance 4 . Better perception systems and increased situational awareness could help to make driving safer.…”

HSV Color Space Based Lighting Detection for Brake Lamps of Daytime Vehicle Images

“…RGB color space is primary color space in which input images are represented [5]. The RGB information of images is usually translated to another color space for processing such as YCbCr color space [6], L*a*b* [7] and HSV color space [8], [9]. HSV (hue, saturation, value) is one alternative representation of the RGB color model, designed to more closely align with the way human vision perceives color-making attributes.…”

Car make and model recognition under limited lighting conditions at night

“…TL localization methods are presented in many studies, such as DAS and vehicle classification [25]. In this paper, the authors' algorithm [33], with accuracy of 95.35 %, is used to localize TL positions. The algorithm is based on the method proposed in [34], which consists of two processes: TL candidate extraction and TL verification.…”

“…Then, symmetry of each pair is measured by calculating symmetry score of alignment of pairs, aspect ratio of shapes, and size of candidate pairs. The taillight positions are subsequently verified by considering the most symmetry score [33]. Figure 3 shows an example of the images of taillight detection process where C symbols represent TL candidates.…”