End-to-end Lane Detection through Differentiable Least-Squares Fitting

@article{Brabandere2019EndtoendLD,
  title={End-to-end Lane Detection through Differentiable Least-Squares Fitting},
  author={Bert De Brabandere and Wouter Van Gansbeke and Davy Neven and Marc Proesmans and Luc Van Gool},
  journal={2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)},
  year={2019},
  pages={905-913}
}
Lane detection is typically tackled with a two-step pipeline in which a segmentation mask of the lane markings is predicted first, and a lane line model (like a parabola or spline) is fitted to the post-processed mask next. [...] Key Method The architecture consists of two components: a deep network that predicts a segmentation-like weight map for each lane line, and a differentiable least-squares fitting module that returns for each map the parameters of the best-fitting curve in the weighted least-squares…Expand
End-to-End Lane Marker Detection via Row-wise Classification
TLDR
This paper proposes a method performing direct lane marker vertex prediction in an end-to-end manner, i.e., without any post-processing step that is required in the pixel-level dense prediction task, and translates the lane marker detection problem into a row-wise classification task, which takes advantage of the innate shape of lane markers. Expand
DSSF-net: Dual-Task Segmentation and Self-supervised Fitting Network for End-to-End Lane Mark Detection
TLDR
An end-to-end lane mark detection network named DSSF-net, which is capable of directly outputting the accurate fitted lane curves, is proposed, and achieves 74.9% in F1-score and outperforms the state-of-the-art models. Expand
A Novel Structure Prior-based Loss Function for Lane Detection
TLDR
A novel loss function based on the structure prior of lanes is proposed that makes the lane detection network more robust to segmentation outliers during fitting lane curves, and reduces fitting errors. Expand
Polynomial Regression Network for Variable-Number Lane Detection
TLDR
The proposed PRNet can detect variable-number of lanes and is highly effective and efficient, and significantly outperforms the previous state-of-the-art methods in terms of both accuracy and speed. Expand
Structure Guided Lane Detection
TLDR
A novel structure guided framework is proposed to solve problems including characterizing lanes, modeling the structural relationship between scenes and lanes, and supporting more attributes of lanes simultaneously to solve these problems simultaneously. Expand
Moment-based multi-lane detection and tracking
TLDR
A novel algorithm based on moments and Kalman filtering to achieve lane tracking, detecting all visible lane boundaries in front of the ego-car and outperforms other multi-lane detection algorithms regarding detection rate as well as accuracy. Expand
Semi-Local 3D Lane Detection and Uncertainty Estimation
TLDR
This work proposes a novel camera-based DNN method based on a semi-local, BEV, tile representation that breaks down lanes into simple lane segments that combines learning a parametric model for the segments along with a deep feature embedding that is then used to cluster segment together into full lanes. Expand
Lane Detection and Classification using Cascaded CNNs
TLDR
This work presents an end-to-end system for lane boundary identification, clustering and classification, based on two cascaded neural networks, that runs in real-time. Expand
RONELD: Robust Neural Network Output Enhancement for Active Lane Detection
TLDR
This paper presents a real-time robust neural network output enhancement for active lane detection (RONELD) method to identify, track, and optimize active lanes from deep learning probability map outputs and hypothesizes true active lanes through tracking preceding frames. Expand
Real-Time Lane Instance Segmentation Using SegNet and Image Processing
TLDR
This approach generates binary segmentation of lanes, then thebinary segmentation map is further processed to separate lanes, and a sliding window extracts each lane to produce the lane instance segmentation image. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 38 REFERENCES
Towards End-to-End Lane Detection: an Instance Segmentation Approach
TLDR
A fast lane detection algorithm, running at 50 fps, is proposed, which can handle a variable number of lanes and cope with lane changes, and is robust against road plane changes, unlike existing approaches that rely on a fixed, predefined transformation. Expand
DeepLanes: End-To-End Lane Position Estimation Using Deep Neural Networks
TLDR
An approach to estimate lane positions directly using a deep neural network that operates on images from laterally-mounted down-facing cameras, able to estimate the position of a lane marker with sub-centimeter accuracy on an embedded automotive platform, requiring no pre- or post-processing. Expand
A Lane Detection, Tracking and Recognition System for Smart Vehicles
TLDR
This thesis proposed a real-time lane assisting framework for intelligent vehicles, which consists of a comprehensive module and simplified module, which is the first parallel architecture that considers not only lane detection and tracking, but also lane marking recognition and departure warning. Expand
Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation
  • J. McCall, M. Trivedi
  • Engineering, Computer Science
  • IEEE Transactions on Intelligent Transportation Systems
  • 2006
TLDR
A comparison of a wide variety of methods, pointing out the similarities and differences between methods as well as when and where various methods are most useful, is presented. Expand
LANE DETECTION USING CATMULL-ROM SPLINE
In this paper, a Catmull-Rom spline based lane model which described the perspective effect of parallel lines was proposed for generic lane boundary. As Catmull-Rom spline can form arbitrary shapesExpand
A fast and stable lane detection method based on B-spline curve
A new structure road detection algorithm based on open uniform B-spline curve model is proposed. Firstly, canny edge detection algorithm is used to extract the road edge. Then road markings areExpand
A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography
TLDR
New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing. Expand
Efficient ConvNet for real-time semantic segmentation
TLDR
This paper proposes a deep architecture that is able to run in real-time while providing accurate semantic segmentation and achieves a classification performance that is among the state of the art, while being orders of magnitude faster to compute than other architectures that achieve top precision. Expand
End-to-End Learning of Geometry and Context for Deep Stereo Regression
We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem’s geometry to form a cost volume using deep featureExpand
Spatial As Deep: Spatial CNN for Traffic Scene Understanding
TLDR
This paper proposes Spatial CNN (SCNN), which generalizes traditional deep layer-by-layer convolutions to slice-byslice convolutions within feature maps, thus enabling message passings between pixels across rows and columns in a layer. Expand
...
1
2
3
4
...