Recent progress in road and lane detection: a survey

By Aharon Bar-Hillel, Ronen Lerner, Dan Levi, Guy Raz. 2014

788 citations recorded by the source corpus.

Subfields: Automotive Engineering, Building and Construction, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Building and Construction

In Control and Systems Engineering

Citations in the corpus

A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, methodology): “rates, but fully automated driving will require a complete, semantic understanding of road structures and the ability to detect several lanes at long ranges [195].”
Overview of Environment Perception for Intelligent Vehicles (2017, methodology): “1) Lane Feature: In general, a lane feature can be detected by appearance of shape or color [12].”
Towards End-to-End Lane Detection: an Instance Segmentation Approach (2018, methodology): “ image. post-processing techniques are employed to ﬁlter out misdetections and group segments together to form the ﬁnal lanes. For a detailed overview of lane detection systems we refer the reader to [3]. In general, these traditional approaches are prone to robustness issues due to road scene varia”
Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy (2016, background): “While effective in well-maintained road environments, these approaches suffer in the presence of occlusions, shadows and changing lighting conditions, unstructured roads, and areas with few or no markings [2].”
Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime (2018, background): “Typical examples include the detection of roads [4], traffic lights [13], cars and pedestrians [6], [25], and tracking of such objects [27], [19].”
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding (2018, background): “e point the reader to [32,57]. Our work is complementary and focuses on semantic foggy scene understanding. 2.2 Foggy Scene Understanding Typical examples in this line include road and lane detection [3], trac light detection [28], car and pedestrian detection [19], and a dense, pixel-level segmenta”
Computing Systems for Autonomous Driving: State of the Art and Challenges (2020, methodology): “Then, postprocessing methods are leveraged to filter out misdetections and classify lane points to output the final lane detection results [95].”
Road marking detection using LIDAR reflective intensity data and its application to vehicle localization (2014, methodology): “Cameras have been widely used for road marking detection [1].”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, background): “For more information on conventional hand-crafted feature/cue based approaches, interested readers may refer to the following survey papers: [68,69] for lane line marking detection, [70] for road surface detection, [71,72] for vehicle detection and [73] for pedestrian detection.”
Vision-Based Driver Assistance Systems: Survey, Taxonomy and Advances (2015, background): “Cameras have become essential sensors in standard alert type functions such as traffic sign recognition (TSR) [5][6], cross traffic alert (CTA) [7], lane departure warning (LDW) [8] and object detection (OD) [7].”
Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene (2017, background): “Despite the appearing simple patterns of most lane marks, the task involves nontrivial tradeoff between several important aspects, including the speed, the accuracy and resolution of the detection, and modeling reliability [6], [40], [41].”
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners (2018, background): “Typical examples include the detection of roads [62], traffic lights [63], cars and pedestrians [64,65,1,2], and the tracking of such objects [66,67,68].”
Spatial As Deep: Spatial CNN for Traffic Scene Understanding (2017, background): “Despite the importance and dif-ﬁculty of trafﬁc lane detection, existing datasets are either too small or too simple, and a large public annotated benchmark is needed to compare different methods (Bar Hillel et al. 2014).”
RESA: Recurrent Feature-Shift Aggregator for Lane Detection (2020, background): “It could serve as signiﬁcant cues for autonomous driving and Advanced Driver Assistance System (ADAS) (bar hillel et al. 2014) to keep a car from staying beyond lane markings.”
Semantic Foggy Scene Understanding with Synthetic Data (2017, neutral): “Typical examples include road and lane detection [5], traffic light detection [35], car and pedestrian detection [24], and a dense, pixel-level segmentation of road scenes into most of the relevant semantic classes [8, 15].”
Fast LIDAR-based road detection using fully convolutional neural networks (2017, background): “The problem of road detection has been investigated for many years and a large variety of approaches can be found in the literature; see, for example, [1] for an in-depth survey of the field.”