Map-supervised road detection

Laddha, Ankit; Kocamaz, Mehmet Kemal; Navarro-Serment, Luis E.; Hebert, Martial

doi:10.1109/ivs.2016.7535374

Cited by 77 publications

(41 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate the difficulties in ground truth annotation, Laddha et al [123] proposed map-supervised deep learning pipeline. In this approach, the ground truth annotation was done automatically based on the vehicle position, heading direction, camera parameters, GPS, and OpenStreetMap data.…”

Section: Road Surface Detectionmentioning

confidence: 99%

Perception, Planning, Control, and Coordination for Autonomous Vehicles

et al. 2017

View full text Add to dashboard Cite

Autonomous vehicles are expected to play a key role in the future of urban transportation systems, as they offer potential for additional safety, increased productivity, greater accessibility, better road efficiency, and positive impact on the environment. Research in autonomous systems has seen dramatic advances in recent years, due to the increases in available computing power and reduced cost in sensing and computing technologies, resulting in maturing technological readiness level of fully autonomous vehicles. The objective of this paper is to provide a general overview of the recent developments in the realm of autonomous vehicle software systems. Fundamental components of autonomous vehicle software are reviewed, and recent developments in each area are discussed.

show abstract

Section: Road Surface Detectionmentioning

confidence: 99%

Perception, Planning, Control, and Coordination for Autonomous Vehicles

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Our method achieves a competitive (the second place) result of Max F-measure 93.26%, which does not differ much from the best 93.43% of DDN [25]. In the listed methods, DDN [25], FTP [23], FCN LC [24], StixelNet [37] and MAP [23] are deep learning methods and only take advantage of RGB information; NNP [5], FusedCRF [6] and ProbBoost [7] exploit 3D information such as stereo vision and LIDAR data; HIM [38] and CB [18] make use of hand-crafted features to detect road region. In addition to the max F-measure, the results of other four criteria are in the top three.…”

Section: E Kitti Dataset: Performance On the Benchmarkmentioning

confidence: 96%

“…Like the proposed s-FCN-loc, FTP [23] and FCN LC [24] also belong to Fully Convolutional Networks. But they process small image patches.…”

Section: E Kitti Dataset: Performance On the Benchmarkmentioning

confidence: 99%

Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection

Wang

Yuan

2018

IEEE Trans. Intell. Transport. Syst.

210

View full text Add to dashboard Cite

Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving. Recently, many deep learning methods spring up for this task because they can extract high-level local features to find road regions from raw RGB data, such as Convolutional Neural Networks (CNN) and Fully Convolutional Networks (FCN). However, how to detect the boundary of road accurately is still an intractable problem. In this paper, we propose a siamesed fully convolutional networks (named as "s-FCN-loc"), which is able to consider RGB-channel images, semantic contours and location priors simultaneously to segment road region elaborately. To be specific, the s-FCNloc has two streams to process the original RGB images and contour maps respectively. At the same time, the location prior is directly appended to the siamesed FCN to promote the final detection performance. Our contributions are threefold: (1) An s-FCN-loc is proposed that learns more discriminative features of road boundaries than the original FCN to detect more accurate road regions; (2) Location prior is viewed as a type of feature map and directly appended to the final feature map in s-FCNloc to promote the detection performance effectively, which is easier than other traditional methods, namely different priors for different inputs (image patches); (3) The convergent speed of training s-FCN-loc model is 30% faster than the original FCN, because of the guidance of highly structured contours. The proposed approach is evaluated on KITTI Road Detection Benchmark and One-Class Road Detection Dataset, and achieves a competitive result with state of the arts.

show abstract

“…Lane detection is not isolated to dashcam imagery. Models that detect lanes in dashcams can in general be adapted to detect lanes in lidar point-clouds, open street maps, and satellite imagery [16,23,4]. The success of semantic segmentation based approaches to lane detection has benefited tremendously from rapid growth in architectures that empirically perform well on dense segmentation tasks [5,26,25].…”

Section: Related Workmentioning

confidence: 99%

FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network

Philion¹

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

151

View full text Add to dashboard Cite

The search for predictive models that generalize to the long tail of sensor inputs is the central difficulty when developing data-driven models for autonomous vehicles. In this paper, we use lane detection to study modeling and training techniques that yield better performance on real world test drives. On the modeling side, we introduce a novel fully convolutional model of lane detection that learns to decode lane structures instead of delegating structure inference to post-processing. In contrast to previous works, our convolutional decoder is able to represent an arbitrary number of lanes per image, preserves the polyline representation of lanes without reducing lanes to polynomials, and draws lanes iteratively without requiring the computational and temporal complexity of recurrent neural networks. Because our model includes an estimate of the joint distribution of neighboring pixels belonging to the same lane, our formulation includes a natural and computationally cheap definition of uncertainty. On the training side, we demonstrate a simple yet effective approach to adapt the model to new environments using unsupervised style transfer. By training FastDraw to make predictions of lane structure that are invariant to low-level stylistic differences between images, we achieve strong performance at test time in weather and lighting conditions that deviate substantially from those of the annotated datasets that are publicly available. We quantitatively evaluate our approach on the CVPR 2017 Tusimple lane marking challenge, difficult CULane datasets [29], and a small labeled dataset of our own and achieve competitive accuracy while running at 90 FPS.

show abstract

Map-supervised road detection

Cited by 77 publications

References 20 publications

Perception, Planning, Control, and Coordination for Autonomous Vehicles

Perception, Planning, Control, and Coordination for Autonomous Vehicles

Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection

FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network

Contact Info

Product

Resources

About