Spatial ray features for real-time ego-lane extraction

Kühnl, Tobias; Kummert, Franz; Fritsch, Jannik

doi:10.1109/itsc.2012.6338740

Cited by 58 publications

(41 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be mainly contributed to the spatial prior we learn with the CN. How important position information is for this dataset can be seen by the performance of the baseline algorithm of (Kühnl et al, 2012) which uses only the pixel position during testing without any appearance features.…”

Section: Methods Maxfmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

Brust

Sickert

Simon

et al. 2015

Proceedings of the 10th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. In particular, we focus on road detection and urban scene understanding, two application areas where we are able to achieve state-of-the-art results on the KITTI as well as on the LabelMeFacade dataset. Furthermore, our paper offers a guideline for people working in the area and desperately wandering through all the painstaking details that render training CNs on image patches extremely difficult.

show abstract

Section: Methods Maxfmentioning

confidence: 99%

“…Road detection Following up on their work with slow feature analysis (Kühnl et al, 2011), the authors of (Kühnl et al, 2012) propose spatial ray features to find boundaries of the road. The former work serves as a source for base classifiers which model road, boundary, and lanes.…”

Section: Related Workmentioning

confidence: 99%

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

Brust

Sickert

Simon

et al. 2015

Proceedings of the 10th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

show abstract

“…In order to capture also traffic participants, Alvarez et al [18] propose to incorporate vehicle detections into the evaluation measure. More recently, also the evaluation of pixel-level correctness in the BEV space has been carried out [16].…”

Section: Related Workmentioning

confidence: 99%

“…While the boundary positions provide the width only implicitly and might be subject to some underlying lane model, the width is especially relevant for inner-city driving with sudden congestions. Evaluation measures that focus on the lane width have been presented in [8], [16].…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, most of the existing work does not distinguish road areas on a semantic level, e.g., ego-lane vs. opposing lane, which is crucial for ADAS and autonomous driving. Only recently, methods for detecting lane markings and curbstones have been combined explicitly [13], [14], [15] or implicitly [16] to achieve city lane detection. The final target of such approaches is the identification of the egolane, independent of the boundary type or lane shape.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new performance measure and evaluation benchmark for road detection algorithms

Fritsch

Kühnl

Geiger

2013

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)

Self Cite

560

317

View full text Add to dashboard Cite

Abstract-Detecting the road area and ego-lane ahead of a vehicle is central to modern driver assistance systems. While lane-detection on well-marked roads is already available in modern vehicles, finding the boundaries of unmarked or weakly marked roads and lanes as they appear in inner-city and rural environments remains an unsolved problem due to the high variability in scene layout and illumination conditions, amongst others. While recent years have witnessed great interest in this subject, to date no commonly agreed upon benchmark exists, rendering a fair comparison amongst methods difficult.In this paper, we introduce a novel open-access dataset and benchmark for road area and ego-lane detection. Our dataset comprises 600 annotated training and test images of high variability from the KITTI autonomous driving project, capturing a broad spectrum of urban road scenes. For evaluation, we propose to use the 2D Bird's Eye View (BEV) space as vehicle control usually happens in this 2D world, requiring detection results to be represented in this very same space. Furthermore, we propose a novel, behavior-based metric which judges the utility of the extracted ego-lane area for driver assistance applications by fitting a driving corridor to the road detection results in the BEV. We believe this to be important for a meaningful evaluation as pixel-level performance is of limited value for vehicle control. State-of-the-art road detection algorithms are used to demonstrate results using classical pixellevel metrics in perspective and BEV space as well as the novel behavior-based performance measure. All data and annotations are made publicly available on the KITTI online evaluation website in order to serve as a common benchmark for road terrain detection algorithms.

show abstract

RBNet: A Deep Neural Network for Unified Road and Road Boundary Detection

Chen

2017

Lecture Notes in Computer Science

129

View full text Add to dashboard Cite

Spatial ray features for real-time ego-lane extraction

Cited by 58 publications

References 16 publications

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding

A new performance measure and evaluation benchmark for road detection algorithms

RBNet: A Deep Neural Network for Unified Road and Road Boundary Detection

Contact Info

Product

Resources

About