VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition
Seokju Lee,Junsik Kim,Jae Shin Yoon,Seunghak Shin,Oleksandr Bailo,Namil Kim,Tae-Hee Lee,Hyun Seok Hong,Seung-hoon Han,In So Kweon +9 more
- pp 1965-1973
TLDR
In this paper, a unified end-to-end trainable multi-task network that jointly handles lane and road marking detection and recognition that is guided by a vanishing point under adverse weather conditions is proposed.Abstract:
In this paper, we propose a unified end-to-end trainable multi-task network that jointly handles lane and road marking detection and recognition that is guided by a vanishing point under adverse weather conditions. We tackle rainy and low illumination conditions, which have not been extensively studied until now due to clear challenges. For example, images taken under rainy days are subject to low illumination, while wet roads cause light reflection and distort the appearance of lane and road markings. At night, color distortion occurs under limited illumination. As a result, no benchmark dataset exists and only a few developed algorithms work under poor weather conditions. To address this shortcoming, we build up a lane and road marking benchmark which consists of about 20,000 images with 17 lane and road marking classes under four different scenarios: no rain, rain, heavy rain, and night. We train and evaluate several versions of the proposed multi-task network and validate the importance of each task. The resulting approach, VPGNet, can detect and classify lanes and road markings, and predict a vanishing point with a single forward pass. Experimental results show that our approach achieves high accuracy and robustness under various conditions in realtime (20 fps). The benchmark and the VPGNet model will be publicly availableread more
Citations
More filters
Proceedings ArticleDOI
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Fisher Yu,Haofeng Chen,Xin Wang,Wenqi Xian,Yingying Chen,Fangchen Liu,Vashisht Madhavan,Trevor Darrell +7 more
TL;DR: This work constructs BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving and shows that special training strategies are needed for existing models to perform such heterogeneous tasks.
Posted Content
BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling.
TL;DR: The design and implementation of a scalable annotation system that can provide a comprehensive set of image labels for large-scale driving datasets, and a new driving dataset, which is an order of magnitude larger than previous efforts.
Proceedings ArticleDOI
Towards End-to-End Lane Detection: an Instance Segmentation Approach
TL;DR: In this article, the authors cast the lane detection problem as an instance segmentation problem, in which each lane forms its own instance and parametrize the segmented lane instances before fitting the lane, in contrast to a fixed "bird's-eye view" transformation.
Proceedings ArticleDOI
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
TL;DR: Self Attention Distillation (SAD) as discussed by the authors is a knowledge distillation approach, which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels.
Journal ArticleDOI
Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks
TL;DR: This work investigates lane detection by using multiple frames of a continuous driving scene, and proposes a hybrid deep architecture by combining the convolutional neural network and the recurrent neural network, which outperforms the competing methods in lane detection.
References
More filters
Journal ArticleDOI
A Novel Lane Detection System With Efficient Ground Truth Generation
TL;DR: A new night-time lane detection system and its accompanying framework are presented in this paper, which is an improvement over the ALD 1.0 with integration of pixel remapping, outlier removal, and prediction with tracking.
Book ChapterDOI
Robust Lane Detection Based On Convolutional Neural Network and Random Sample Consensus
Jihun Kim,Minho Lee +1 more
TL;DR: A robust lane detection method based on the combined convolutional neural network (CNN) with random sample consensus (RANSAC) algorithm is introduced and the performance is found to be better than other formal line detection algorithms such as RANSAC and hough transform.
Proceedings ArticleDOI
Real-time lane and obstacle detection on the GOLD system
Massimo Bertozzi,Alberto Broggi +1 more
TL;DR: The GOLD system allows detection of both generic obstacles and lane position in a structured environment (with painted lane markings) and it has been implemented on the PAPRICA system and works at a rate of 10 Hz.
Proceedings ArticleDOI
A practical system for road marking detection and recognition
Tao Wu,Ananth Ranganathan +1 more
TL;DR: A system for detecting and recognizing road markings from video input obtained from an in-car camera that uses MSER features and performs the template matching in an efficient manner so that this system can detect multiple road markings in a single image.
Proceedings ArticleDOI
Multi-lane detection in urban driving environments using conditional random fields
TL;DR: This paper proposes a new multi-lane detection algorithm that works well in urban situations and shows that CRFs are very effective tools for multi- lane detection because they find an optimal association of multiple lane marks in complex and challenging urban road situations.