A lane detection network based on IBN and attention
- 22 Downloads
In intelligent transportation system and advanced driving assistant system, lane detection is an indispensable security link. At present, deep learning has been applied to the task of lane detection, and some methods used semantic segmentation to separate lanes from background. This paper presents a modified encoder-decoder network with instance-batch normalization net (IBN-NET) and attention mechanism based on LaneNet structure. In view of the shortcomings of batch normalization (BN) in capturing texture in end-to-end segmentation, we consider further optimizing this part from the idea of image style transfer, which we solve the problem by replacing pixel-wise classification for scene labeling with capturing content images structure. To take advantage of visual and appearance invariance of instance normalization in encoder stage, IBN layers are applied to replace normal BN layers. Secondly, attention mechanism is added to the network, forcing it to focus on lane regions. This structure is very suitable for two-class semantics segmentation task with only lane and background. The experimental results show that the method can improve detection effect.
KeywordsLane detection Deep learning CNN IBN-net Attention
The work described in this paper was funded by Science and Technology Development Plan of Jilin Province (20170204020GX) and National Natural Science Foundation of China under grant U1564211 and 51805203.
Compliance with ethical standards
Conflict of interest
We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
This article does not contain any studies with human participants performed by any of the authors.
- 1.Aly M (2008) Real time detection of lane markers in urban streets. In: IEEE Intelligent Vehicles Symposium, Proceedings pp 7–12Google Scholar
- 2.Azimi SM, Fischer P, Körner M, Reinartz P (2018) Aerial LaneNet: lane marking semantic segmentation in aerial imagery using wavelet-enhanced cost-sensitive symmetric fully convolutional neural networksGoogle Scholar
- 3.Chen L-C, Yang Y, Wang J et al (2016) Attention to scale: scale-aware semantic image segmentation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE pp 3640–3649Google Scholar
- 4.De Brabandere B, Neven D, Van Gool L (2017) Semantic instance segmentation with a discriminative loss functionGoogle Scholar
- 5.Ghafoorian M, Nugteren C, Baka N et al (2018) EL-GAN: embedding loss driven generative adversarial networks for lane detectionGoogle Scholar
- 7.He B, Ai R, Yan Y, Lang X (2016) Accurate and robust lane detection based on dual-view convolutional neutral network. In: IEEE Intelligent Vehicles Symposium, ProceedingsGoogle Scholar
- 8.Huang X, Liu M-Y, Belongie S, Kautz J (2018) Multimodal unsupervised image-to-image translationGoogle Scholar
- 9.Isola P, Zhu JY, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017Google Scholar
- 10.Kim J, Park C (2017) End-to-end ego lane estimation based on sequential transfer learning for self-driving cars. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, pp 1194–1202Google Scholar
- 11.Lee S, Kim J, Yoon JS et al (2017) VPGNet: vanishing point guided network for lane and road marking detection and recognition. In: Proceedings of the IEEE International Conference on Computer VisionGoogle Scholar
- 13.Liu X, Deng Z, Yang G (2017a) Drivable road detection based on dilated FPN with feature aggregation. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, pp 1128–1134Google Scholar
- 16.Meyer A, Salscheider NO, Orzechowski PF, Stiller C (2018) Deep semantic lane segmentation for mapless driving. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’2018). Madrid, Spain, pp 871–875Google Scholar
- 17.Neven D, De Brabandere B, Georgoulis S et al (2018) Towards end-to-end lane detection: an instance segmentation approachGoogle Scholar
- 19.Oliveira GL, Burgard W, Brox T (2016) Efficient deep models for monocular road segmentation. In: IEEE International Conference on Intelligent Robots and SystemsGoogle Scholar
- 21.Pan X, Shi J, Luo P et al (2017) Spatial As Deep: Spatial CNN for Traffic Scene UnderstandingGoogle Scholar
- 23.Paszke A, Chaurasia A, Kim S, Culurciello E (2016) ENet: a deep neural network architecture for real-time semantic segmentationGoogle Scholar
- 26.Song W, Yang Y, Fu M et al (2018) Lane detection and classification for forward collision warning system based on stereo vision. IEEE Sens J PP:1Google Scholar
- 27.Ulyanov D, Vedaldi A, Lempitsky V (2016) Instance normalization: the missing ingredient for fast stylizationGoogle Scholar
- 28.Woo S, Park J, Lee J-Y, So Kweon I (2018) CBAM: convolutional block attention module. In: The European Conference on Computer Vision (ECCV)Google Scholar
- 30.Xu K, Ba J, Kiros R et al (2015) Show, attend and tell: neural image caption generation with visual attention. In: the 32nd International Conference on Machine Learning. Lille, France, pp 2048–2057Google Scholar
- 33.Yu G, Wang Z, Wu X et al (2017) Efficient lane detection using deep lane feature extraction method. SAE Int J Passeng Cars Electron Electr Syst 11. doi: https://doi.org/10.4271/2017-01-1970
- 34.Zhang H, Goodfellow I, Metaxas D, Odena A (2018) Self-attention generative adversarial networksGoogle Scholar