Robust Lane Detection for Complicated Road Environment Based on Normal Map
Citations
48 citations
24 citations
Cites methods from "Robust Lane Detection for Complicat..."
...To establish the mathematical model of a structure, a Hough transform [77] was used in the pre‐ extraction before curve fitting....
[...]
20 citations
19 citations
Cites methods from "Robust Lane Detection for Complicat..."
...Monocular cameras were used in [2]–[4] as a road information acquisition sensor, and binocular cameras were used in [5]–[8] generally combine the detection of parallax maps and vanishing points to achieve drivable road detection....
[...]
16 citations
References
28,225 citations
"Robust Lane Detection for Complicat..." refers background or methods in this paper
...As a deep learning method, FCN requires a large amount of data to train 49686 VOLUME 6, 2018 a powerful model....
[...]
..., IPM + hyperbolic model [10], superparticle method [16], lane detection with two-stage feature extraction (LDTFE) method [26], and a state-of-the-art fully convolutional networks (FCN) method [32]....
[...]
...(a1)∼(a10) are the results of IPM + hyperbolic model [10], cyan lines refer to the detected lanes; (b1)∼(b10) are the results of superparticle [16], blue points refer to the detected lanes; (c1)∼(c10) are the results of LDTFE [26], magenta lines refer to the detected lanes; (d1)∼(d10) are the results of FCN [32], green area refers to the host lane; (e1)∼(e10) are the results of the proposed method, red lines refer to the detected lanes, and green area refers to the host lane....
[...]
...FCN method [32], a fully convolutional network is used for semantic segmentation of the host lane....
[...]
...In the FCN method [32], a fully convolutional network is used for semantic segmentation of the host lane....
[...]
1,064 citations
"Robust Lane Detection for Complicat..." refers methods in this paper
...One is Otsu’s method [30] which is a kind of global threshold method....
[...]
...(a1)∼(a4) are the original images; (b1)∼(b4) are the results of road segmentation; (c1)∼(c4) are the results of binarization with Otsu’s method [30]; (d1)∼(d4) are the results of proposed threshold segmentation method; (e1)∼(e4) are the results after removing noise....
[...]
735 citations
"Robust Lane Detection for Complicat..." refers background in this paper
...So advanced driver assistance systems (ADAS) [1], [2] which are designed to help drivers in driving process emerge as the times require....
[...]
...In the past two decades, researchers have made considerable progress in the vision-based approaches [2], [3], while facing several major challenges, especially in attaining robustness under complex lighting conditions and dense traffic....
[...]
716 citations
"Robust Lane Detection for Complicat..." refers background in this paper
...So advanced driver assistance systems (ADAS) [1], [2] which are designed to help drivers in driving process emerge as the times require....
[...]
...His research interests include computer vision, image processing, and ADAS....
[...]
...Lane-mark detection is one of the most important parts of ADAS and autonomous driving cars, and it’s also a precondition for lane departure warning (LDW) [3]–[5]....
[...]
672 citations