Multiple Lane Detection Algorithm Based on Novel Dense Vanishing Point Estimation

Umar Özgünalp, Rui Fan, Xiao Ai, Naim Dahnoun

Abstract: The detection of multiple curved lane markings is still a challenge for advanced driver assistance systems today, due to interference such as road markings and shadows cast by roadside structures and vehicles. The vanishing point V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> contains the global information of the road image. Hence, V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> -based lane detection algorithms are quite insensitive to interference. When curved lanes are assumed, V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> shifts with respect to the rows of the image. In this paper, a V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> for each individual row of the image is estimated by first extracting a V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">py</sub> (vertical position of the V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> ) for each individual row of the image from the v-disparity. Then, based on the estimated V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">py</sub> 's, a 2-D V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">px</sub> (horizontal position of the V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> ) accumulator is efficiently formed. Thus, by globally optimizing this 2-D V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">px</sub> accumulator, globally optimum V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> s for the road image are extracted. Then, estimated V <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> s are utilized for multiple curved lane marking detection on nonflat road surfaces. The resultant system achieves a detection rate of 99% in 1862 frames of six stereo vision test sequences.