TY - JOUR
T1 - Combining priors, appearance, and context for road detection
AU - Álvarez, Jose M.
AU - López, Antonio M.
AU - Gevers, Theo
AU - Lumbreras, Felipe
PY - 2014/6
Y1 - 2014/6
N2 - Detecting the free road surface ahead of a moving vehicle is an important research topic in different areas of computer vision, such as autonomous driving or car collision warning. Current vision-based road detection methods are usually based solely on low-level features. Furthermore, they generally assume structured roads, road homogeneity, and uniform lighting conditions, constraining their applicability in real-world scenarios. In this paper, road priors and contextual information are introduced for road detection. First, we propose an algorithm to estimate road priors online using geographical information, providing relevant initial information about the road location. Then, contextual cues, including horizon lines, vanishing points, lane markings, 3-D scene layout, and road geometry, are used in addition to low-level cues derived from the appearance of roads. Finally, a generative model is used to combine these cues and priors, leading to a road detection method that is, to a large degree, robust to varying imaging conditions, road types, and scenarios.
AB - Detecting the free road surface ahead of a moving vehicle is an important research topic in different areas of computer vision, such as autonomous driving or car collision warning. Current vision-based road detection methods are usually based solely on low-level features. Furthermore, they generally assume structured roads, road homogeneity, and uniform lighting conditions, constraining their applicability in real-world scenarios. In this paper, road priors and contextual information are introduced for road detection. First, we propose an algorithm to estimate road priors online using geographical information, providing relevant initial information about the road location. Then, contextual cues, including horizon lines, vanishing points, lane markings, 3-D scene layout, and road geometry, are used in addition to low-level cues derived from the appearance of roads. Finally, a generative model is used to combine these cues and priors, leading to a road detection method that is, to a large degree, robust to varying imaging conditions, road types, and scenarios.
KW - 3-D scene layout
KW - Illuminant invariance
KW - lane markings
KW - road detection
KW - road prior
KW - road scene understanding
KW - vanishing point
UR - http://www.scopus.com/inward/record.url?scp=84902085874&partnerID=8YFLogxK
U2 - 10.1109/TITS.2013.2295427
DO - 10.1109/TITS.2013.2295427
M3 - Article
SN - 1524-9050
VL - 15
SP - 1168
EP - 1178
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
IS - 3
M1 - 6719504
ER -