End-To-End Ego Lane Estimation Based on Sequential Transfer Learning for Self-Driving Cars

Kim, Jiman; Park, Chanjong

doi:10.1109/cvprw.2017.158

Cited by 136 publications

(58 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As explained above, these heuristic methods are computationally expensive and prone to robustness issues due to road scene variations. Another line of work [20] casts the lane detection problem as a multi-class segmentation problem, in which each lane forms its own class. By doing so, the output of the network contains disentangled binary maps for each lane and can be trained in an end-to-end manner.…”

Section: Introductionmentioning

confidence: 99%

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

Neven

Brabandere

Georgoulis

et al. 2018

2018 IEEE Intelligent Vehicles Symposium (IV)

646

371

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Neven

Brabandere

Georgoulis

et al. 2018

2018 IEEE Intelligent Vehicles Symposium (IV)

646

371

View full text Add to dashboard Cite

show abstract

“…VPGNet (Lee et al [18]), follows a similar concept and additionally detects other road markings and the vanishing point to improve lane detection. Kim and Park [16] re-formulate the local-feature extraction stage as a semantic-segmentation problem, with two classes corresponding to the left and right lane delimiters, extending the reach of the network to perform clustering. However, a world-coordinate lane model must still be fitted to each cluster, and multiple lanes are not handled.…”

Section: Related Workmentioning

confidence: 99%

3D-LaneNet: End-to-End 3D Multiple Lane Detection

Garnett¹,

Cohen²,

Pe'er³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

150

114

View full text Add to dashboard Cite

We introduce a network that directly predicts the 3D layout of lanes in a road scene from a single image. This work marks a first attempt to address this task with onboard sensing without assuming a known constant lane width or relying on pre-mapped environments. Our network architecture, 3D-LaneNet, applies two new concepts: intranetwork inverse-perspective mapping (IPM) and anchorbased lane representation. The intra-network IPM projection facilitates a dual-representation information flow in both regular image-view and top-view. An anchor-percolumn output representation enables our end-to-end approach which replaces common heuristics such as clustering and outlier rejection, casting lane estimation as an object detection problem. In addition, our approach explicitly handles complex situations such as lane merges and splits. Results are shown on two new 3D lane datasets, a synthetic and a real one. For comparison with existing methods, we test our approach on the image-only tuSimple lane detection benchmark, achieving performance competitive with stateof-the-art.

show abstract

“…However, pixel-wise semantic segmentation is a more chal- lenging problem, as each pixel should be classified. Kim et al [27] propose a sequential transfer learning method based on fully convolutional neural networks (FCNNs) by segmenting the road in the first step and then lane marking segmentation on the road-masked image. This method is similar to the methodology used in current lane-marking detection algorithms in remote sensing.…”

Section: B Related Workmentioning

confidence: 99%

Aerial LaneNet: Lane-Marking Semantic Segmentation in Aerial Imagery Using Wavelet-Enhanced Cost-Sensitive Symmetric Fully Convolutional Neural Networks

Azimi

Fischer

Körner

et al. 2019

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lane-wise traffic management, and urban planning. Lane markings are one of the important components of such maps. Lane markings convey the rules of roads to drivers. While these rules are learned by humans, an autonomous driving vehicle should be taught to learn them to localize itself. Therefore, accurate and reliable lane marking semantic segmentation in the imagery of roads and highways is needed to achieve such goals. We use airborne imagery which can capture a large area in a short period of time by introducing an aerial lane marking dataset. In this work, we propose a Symmetric Fully Convolutional Neural Network enhanced by Wavelet Transform in order to automatically carry out lane marking segmentation in aerial imagery. Due to a heavily unbalanced problem in terms of number of lane marking pixels compared with background pixels, we use a customized loss function as well as a new type of data augmentation step. We achieve a high accuracy in pixelwise localization of lane markings compared with the state-ofthe-art methods without using 3rd-party information. In this work, we introduce the first high-quality dataset used within our experiments which contains a broad range of situations and classes of lane markings representative of today's transportation systems. This dataset will be publicly available and hence, it can be used as the benchmark dataset for future algorithms within this domain.

show abstract

End-To-End Ego Lane Estimation Based on Sequential Transfer Learning for Self-Driving Cars

Cited by 136 publications

References 37 publications

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

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

3D-LaneNet: End-to-End 3D Multiple Lane Detection

Aerial LaneNet: Lane-Marking Semantic Segmentation in Aerial Imagery Using Wavelet-Enhanced Cost-Sensitive Symmetric Fully Convolutional Neural Networks

Contact Info

Product

Resources

About