Towards End-to-End Lane Detection: an Instance Segmentation Approach

By Davy Neven, Bert De Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool. 2018 IEEE Intelligent Vehicles Symposium (IV), 2018

804 citations recorded by the source corpus.

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane departure or trajectory planning decision in fully autonomous cars. Traditional lane detection methods rely on a combination of highly-specialized, hand-crafted features and heuristics, usually followed by post-processing techniques, that are computationally expensive and prone to scalability due to road scene variations. More recent approaches leverage deep learning models, trained for pixel-wise lane segmentation, even when no markings are present in the image due to their big receptive field. Despite their advantages, these methods are limited to detecting a pre-defined, fixed number of lanes, e.g. ego-lanes, and can not cope with lane changes. In this paper, we go beyond the aforementioned limitations and propose to cast the lane detection problem as an instance segmentation problem - in which each lane forms its own instance - that can be trained end-to-end. To parametrize the segmented lane instances before fitting the lane, we further propose to apply a learned perspective transformation, conditioned on the image, in contrast to a fixed ”bird’s-eye view” transformation. By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, predefined transformation. In summary, we propose a fast lane detection algorithm, running at 50 fps, which can handle a variable number of lanes and cope with lane changes. We verify our method on the tuSimple dataset and achieve competitive results.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8b2ea3ecac8abd2357fbf8ca59ec31bad3191388

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 Computer Vision and Pattern Recognition

Citations in the corpus

Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, neutral): “It is mainly utilized for vehicle [37], [104], pedestrian [105]– [107], lane marking [108]– [110] and trafﬁc sign [111] detection in AV.”
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution (2021, methodology): “Early deep-learning-based methods detect lane lines through segmentation [28, 27].”
YOLOP: You Only Look Once for Panoptic Driving Perception (2021, background): “[19] constructs a dual-branch network to perform semantic segmentation and pixel embedding on images.”
Learning Lightweight Lane Detection CNNs by Self Attention Distillation (2019, methodology): “Many algorithms [16, 15, 8] have been tested in TuSimple since it was the largest lane detection dataset before 2018.”
VectorMapNet: End-to-end Vectorized HD Map Learning (2022, methodology): “Most lane detection algorithms [32, 33] use a pixel-level segmentation technique combined with sophisticated post-processing.”
RESA: Recurrent Feature-Shift Aggregator for Lane Detection (2020, methodology): “This demonstrates RESA owns much stronger capability to capture structural prior of objects than traditional segmentation modules and SCNN.”
Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks (2019, background): “In [47], a network called LaneNet was proposed.”
Ultra Fast Structure-aware Deep Lane Detection (2020, methodology): “For the Tusimple lane detection benchmark, seven methods are used for comparison, including Res18-Seg [3], Res34-Seg [3], LaneNet [21], EL-GAN [5], SCNN [22] and SAD [9].”