Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection

Modern lane detection methods have achieved remarkable performances in complex real-world scenarios, but many have issues maintaining real-time efficiency, which is important for autonomous vehicles. In this work, we propose LaneATT: an anchor-based deep lane detection model, which, akin to other generic deep object detectors, uses the anchors for the feature pooling step. Since lanes follow a regular pattern and are highly correlated, we hypothesize that in some cases global information may be crucial to infer their positions, especially in conditions such as occlusion, missing lane markers, and others. Thus, this work proposes a novel anchor-based attention mechanism that aggregates global information. The model was evaluated extensively on three of the most widely used datasets in the literature. The results show that our method outperforms the current state-of-the-art methods showing both higher efficacy and efficiency. Moreover, an ablation study is performed along with a discussion on efficiency trade-off options that are useful in practice.

[1]  Mohsen Ghafoorian,et al.  EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection , 2018, ECCV Workshops.

[2]  Qibin Hou,et al.  SpinNet: Spinning convolutional network for lane boundary detection , 2019, Computational Visual Media.

[3]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Fabio Pizzati,et al.  Lane Detection and Classification using Cascaded CNNs , 2019, EUROCAST.

[5]  Alberto Ferreira de Souza,et al.  Self-Driving Cars: A Survey , 2019, Expert Syst. Appl..

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Zhenpeng Chen,et al.  PointLaneNet: Efficient end-to-end CNNs for Accurate Real-Time Lane Detection , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[8]  Bingbing Ni,et al.  Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection , 2018, ECCV.

[9]  Luc Van Gool,et al.  End-to-end Lane Detection through Differentiable Least-Squares Fitting , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[10]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[11]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Edilson de Aguiar,et al.  Ego-Lane Analysis System (ELAS): Dataset and algorithms , 2017, Image Vis. Comput..

[13]  Long Chen,et al.  Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks , 2019, IEEE Transactions on Vehicular Technology.

[14]  Huanyu Wang,et al.  Ultra Fast Structure-aware Deep Lane Detection , 2020, ECCV.

[15]  Chen Change Loy,et al.  Learning Lightweight Lane Detection CNNs by Self Attention Distillation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Xiaogang Wang,et al.  Spatial As Deep: Spatial CNN for Traffic Scene Understanding , 2017, AAAI.

[18]  Eduardo Romera,et al.  ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation , 2018, IEEE Transactions on Intelligent Transportation Systems.

[19]  Ali Hassan,et al.  Lane detection using lane boundary marker network with road geometry constraints , 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[20]  Wei Zhang,et al.  CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending , 2020, ECCV.

[21]  Jian Yang,et al.  Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit , 2020, IEEE Transactions on Intelligent Transportation Systems.

[22]  Alberto Ferreira de Souza,et al.  PolyLaneNet: Lane Estimation via Deep Polynomial Regression , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[23]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[24]  Yi Yang,et al.  Lane Detection in Low-light Conditions Using an Efficient Data Enhancement: Light Conditions Style Transfer , 2020, 2020 IEEE Intelligent Vehicles Symposium (IV).

[25]  Seungwoo Yoo,et al.  End-to-End Lane Marker Detection via Row-wise Classification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  S. Khan,et al.  Real time lane detection for autonomous vehicles , 2008, 2008 International Conference on Computer and Communication Engineering.

[27]  Jonah Philion,et al.  FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Chunxiao Liu,et al.  Inter-Region Affinity Distillation for Road Marking Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).