This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 1 A Novel Strategy for Road Lane Detection and Tracking Based on a Vehicle’s Forward Monocular Camera David C. Andrade, Felipe Bueno , Felipe R. Franco, Rodrigo Adamshuk Silva , Student Member, IEEE, João Henrique Z. Neme, Erick Margraf, Student Member, IEEE, William T. Omoto, Felipe A. Farinelli , Angelo M. Tusset, Sergio Okida, Max M. D. Santos , Senior Member, IEEE, Artur Ventura, Saulo Carvalho, and Rodrigo dos Santos Amaral Abstract— Modern road vehicles are employing features of driver assistance systems (DAS) to improve drivability per- formance, comfort, and safety. In the future perspective, the advances in this field will lead these systems to the level of autonomous and cooperative driving, based on sensors networks and sensor fusion. This paper aims to present the readers a novel strategy for lane detection and tracking, which fits as a functional requirement to deploy DAS features like Lane Departure Warning and Lane Keeping Assist. To achieve the presented results, the digital image processing was divided into three levels. At the low-level, the input image dimensionality is reduced from three to one layer, the sharpness is improved, and region of interest is defined based on the minimum safe distance from the vehicle ahead. The feature extractor for lane edges detection design is part of the mid-level processing. The lane tracking strategy development is discussed in the high-level stage; Hough Transform and a shape-preserving spline interpolation are used to achieve a smooth lane fitting. The experimental outcomes were qualitatively and quantitatively evaluated using a ground truth comparison. The strategy shows good accuracy levels, including scenarios with shadows, curves, and road slope. Index Terms— Driver assistance systems, image processing, lane detection, lane tracking, monocular camera. Manuscript received May 14, 2017; revised October 27, 2017, February 6, 2018, and May 7, 2018; accepted June 28, 2018. This work was supported in part by FCA Latam (Betim-MG, Brazil) under INOVAR- AUTO and BNDES funding programs, which consist of a P&D project named Forward Looking Camera (FLC) and in part by the R&D Project Câmera de Visão Frontal–FLC, established under Agreement 01/2015 between Universidade Tecnológica Federal do Paraná–Ponta Grossa and Fiat Chrysler Automobiles under FLC Project DOU 201. The Associate Editor for this paper was N. Zheng. (Corresponding author: Max M. D. Santos.) D. C. Andrade, F. Bueno, F. R. Franco, R. A. Silva, J. H. Z. Neme, E. Margraf, W. T. Omoto, F. A. Farinelli, A. M. Tusset, S. Okida, and M. M. D. Santos are with the Automotive Systems Group, Universidade Tecnológica Federal do Paraná, Ponta Grossa PR 84016-210, Brazil (e-mail: davidandrade@alunos.utfpr.edu.br; felipebueno@alunos.utfpr.edu.br; felipefranco@alunos.utfpr.edu.br; rodrigo.2010@alunos.utfpr.edu.br; neme@ alunos.utfpr.edu.br; margraf@alunos.utfpr.edu.br; williamomoto@alunos. utfpr.edu.br; tusset@utfpr.edu.br; sergiookida@utfpr.edu.br; maxsantos@ utfpr.edu.br). A. Ventura, S. Carvalho, and R. S. Amaral are with FCA Latam, Betim MG 32.669-900, Brazil (e-mail: artur.ventura@fcagroup.com; saulo.carvalho@external.fcagroup.com; rodrgo.amaral@fcagroup.com). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TITS.2018.2856361 I. I NTRODUCTION M OBILITY is an important social and economic factor for humanity as it provides quality of life for individu- als and it is the backbone of commercial trading and services. For the outcomes, the inhabitants of industrialized countries have achieved a high degree of mobility due to the mass production of vehicles and road infrastructure investments. However, the popularization of automobiles has caused some logistical problems, such as traffic congestion and the increase of the risk of accidents [1], [2]. According to data from the National Highway Traffic Safety Administra- tion (NHTSA), 94% of the critical flaws in the chain of events preceding an accident are assigned to the driver, which justifies the investment in support systems [3]. Driver Assistance Systems (DAS) offer solutions to reduce the effects caused by the above-listed problems. Bengler et al. [4] have been analyzing over the past three decades the future perspective of DAS development, and structuring it according to the technological point of view: • From the late 1970s to the mid-1990s: The early systems were based on proprioceptive sensors to stabilize vehicle dynamics, such as ABS (Anti-lock Brake System), TCS (Traction Control System) and ESC (Electronic Stability Control); • From the early 1990s to the late 2000s: Exteroceptive sensors based systems with information, alarm and com- fort functions such as LDW (Lane Departure Warning), ACC (Adaptive Cruise Control) and Park Assist; • From the middle of the years 2000 to 2030: The goal is to reach autonomous and cooperative direction level through networks of sensors. Volvo Trucks [5] conducted a study about European road accidents which associates 22% of the accidents involving trucks with lane departure or rear-end collision. According to the Federal Highway Administration (FHWA), 54% of traffic accidents fatalities in the year of 2014 were caused by the vehi- cle departure from its driving path [6]. Therefore, regulations and programs to evaluate automotive safety performance have reinforced DAS development. For example, NHTSA’s require- ments for the deployment of rearview technology on all new 1524-9050 © 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.