An Efficient Network for Lane Segmentation

Haoran Li; Dongbin Zhao; Yaran Chen; Qichao Zhang

doi:10.1007/978-981-13-7983-3_16

An Efficient Network for Lane Segmentation

Haoran Li, Dongbin Zhao, Yaran Chen, Qichao Zhang^*

^*Corresponding author for this work

Department of Intelligent Science

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

5 Citations (Scopus)

Abstract

As the basis of scenes understanding for autonomous driving, lane segmentation is always a challenge due to the various illumination conditions, heavy traffics and richly-textured roads. Because of the heavily biased distribution of lane/non-lane pixels, it is hard to achieve satisfying results by using image segmentation networks such as fully convolution neural networks (FCN). In this paper, we propose a new loss function to tackle the unbalanced data distribution problem. It has shown that the loss function significantly improves the performance of available segmentation networks such as FCN on the lane segmentation task.

Original language	English
Title of host publication	Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers
Editors	Huaping Liu, Fuchun Sun, Dewen Hu
Publisher	Springer Verlag
Pages	177-185
Number of pages	9
ISBN (Print)	9789811379826
DOIs	https://doi.org/10.1007/978-981-13-7983-3_16
Publication status	Published - 2019
Event	4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018 - Beijing, China Duration: 29 Nov 2018 → 1 Dec 2018

Publication series

Name	Communications in Computer and Information Science
Volume	1005
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018
Country/Territory	China
City	Beijing
Period	29/11/18 → 1/12/18

Keywords

Autonomous driving
Lane segmentation
Loss function

Access to Document

10.1007/978-981-13-7983-3_16

Cite this

Li, H., Zhao, D., Chen, Y., & Zhang, Q. (2019). An Efficient Network for Lane Segmentation. In H. Liu, F. Sun, & D. Hu (Eds.), Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers (pp. 177-185). (Communications in Computer and Information Science; Vol. 1005). Springer Verlag. https://doi.org/10.1007/978-981-13-7983-3_16

@inproceedings{ff8c5d891faa4208a0c7e7d21b1f3923,

title = "An Efficient Network for Lane Segmentation",

abstract = "As the basis of scenes understanding for autonomous driving, lane segmentation is always a challenge due to the various illumination conditions, heavy traffics and richly-textured roads. Because of the heavily biased distribution of lane/non-lane pixels, it is hard to achieve satisfying results by using image segmentation networks such as fully convolution neural networks (FCN). In this paper, we propose a new loss function to tackle the unbalanced data distribution problem. It has shown that the loss function significantly improves the performance of available segmentation networks such as FCN on the lane segmentation task.",

keywords = "Autonomous driving, Lane segmentation, Loss function",

author = "Haoran Li and Dongbin Zhao and Yaran Chen and Qichao Zhang",

note = "Publisher Copyright: © 2019, Springer Nature Singapore Pte Ltd.; 4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018 ; Conference date: 29-11-2018 Through 01-12-2018",

year = "2019",

doi = "10.1007/978-981-13-7983-3_16",

language = "English",

isbn = "9789811379826",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "177--185",

editor = "Huaping Liu and Fuchun Sun and Dewen Hu",

booktitle = "Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers",

}

Li, H, Zhao, D, Chen, Y & Zhang, Q 2019, An Efficient Network for Lane Segmentation. in H Liu, F Sun & D Hu (eds), Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 1005, Springer Verlag, pp. 177-185, 4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018, Beijing, China, 29/11/18. https://doi.org/10.1007/978-981-13-7983-3_16

An Efficient Network for Lane Segmentation. / Li, Haoran; Zhao, Dongbin; Chen, Yaran et al.
Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers. ed. / Huaping Liu; Fuchun Sun; Dewen Hu. Springer Verlag, 2019. p. 177-185 (Communications in Computer and Information Science; Vol. 1005).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - An Efficient Network for Lane Segmentation

AU - Li, Haoran

AU - Zhao, Dongbin

AU - Chen, Yaran

AU - Zhang, Qichao

PY - 2019

Y1 - 2019

N2 - As the basis of scenes understanding for autonomous driving, lane segmentation is always a challenge due to the various illumination conditions, heavy traffics and richly-textured roads. Because of the heavily biased distribution of lane/non-lane pixels, it is hard to achieve satisfying results by using image segmentation networks such as fully convolution neural networks (FCN). In this paper, we propose a new loss function to tackle the unbalanced data distribution problem. It has shown that the loss function significantly improves the performance of available segmentation networks such as FCN on the lane segmentation task.

AB - As the basis of scenes understanding for autonomous driving, lane segmentation is always a challenge due to the various illumination conditions, heavy traffics and richly-textured roads. Because of the heavily biased distribution of lane/non-lane pixels, it is hard to achieve satisfying results by using image segmentation networks such as fully convolution neural networks (FCN). In this paper, we propose a new loss function to tackle the unbalanced data distribution problem. It has shown that the loss function significantly improves the performance of available segmentation networks such as FCN on the lane segmentation task.

KW - Autonomous driving

KW - Lane segmentation

KW - Loss function

UR - http://www.scopus.com/inward/record.url?scp=85065800036&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-7983-3_16

DO - 10.1007/978-981-13-7983-3_16

M3 - Conference Proceeding

AN - SCOPUS:85065800036

SN - 9789811379826

T3 - Communications in Computer and Information Science

SP - 177

EP - 185

BT - Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers

A2 - Liu, Huaping

A2 - Sun, Fuchun

A2 - Hu, Dewen

PB - Springer Verlag

T2 - 4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018

Y2 - 29 November 2018 through 1 December 2018

ER -

An Efficient Network for Lane Segmentation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this