Semantic segmentation method on nighttime road scene based on Trans-nightSeg

被引：1

作者：

Li C. ^{[1
]}

Zhang W. ^{[1
]}

Shao Z. ^{[2
,3
]}

Ma L. ^{[3
]}

Wang X. ^{[1
]}

机构：

[1] School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou

[2] School of Computer Science and Technology, China University of Mining and Technology, Xuzhou

[3] Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai

来源：

Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2024年 / 58卷 / 02期

关键词：

generative adversarial network (GAN); image enhancement; road scene; semantic segmentation; style transformation;

D O I：

10.3785/j.issn.1008-973X.2024.02.008

中图分类号：

学科分类号：

摘要：

The semantic segmentation method Trans-nightSeg was proposed aiming at the issues of low brightness and lack of annotated semantic segmentation dataset in nighttime road scenes. The annotated daytime road scene semantic segmentation dataset Cityscapes was converted into low-light road scene images by TransCartoonGAN, which shared the same semantic segmentation annotation, thereby enriching the nighttime road scene dataset. The result together with the real road scene dataset was used as input of N-Refinenet. The N-Refinenet network introduced a low-light image adaptive enhancement network to improve the semantic segmentation performance of the nighttime road scene. Depth-separable convolution was used instead of normal convolution in order to reduce the computational complexity. The experimental results show that the mean intersection over union (mIoU) of the proposed algorithm on the Dark Zurich-test dataset and Nighttime Driving-test dataset reaches 56.0% and 56.6%, respectively, outperforming other semantic segmentation algorithms for nighttime road scene. © 2024 Zhejiang University. All rights reserved.

引用

页码：294 / 303

页数：9

共 29 条

[1] CORDTS M, OMRAN M, RAMOS S, Et al., The Cityscapes dataset for semantic urban scene understanding [C], IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213-3223, (2016)
[2] SAKARIDIS C, DAI D, GOOL L V., ACDC: the adverse conditions dataset with correspondences for semantic driving scene understanding [C], IEEE International Conference on Computer Vision, pp. 10765-10775, (2021)
[3] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, Et al., Generative adversarial networks [J], Communications of the ACM, 63, 11, pp. 139-144, (2020)
[4] REED S, AKATA Z, YAN X, Et al., Generative adversarial text to image synthesis [C], International Conference on Machine Learning, pp. 1060-1069, (2016)
[5] YEH R, CHEN C, LIM T Y, Et al., Semantic image inpainting with perceptual and contextual losses
[6] LEDIG C, THEIS L, HUSZAR F, Et al., Photo-realistic single image super-resolution using a generative adversarial network [C], IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681-4690, (2017)
[7] ISOLA P, ZHU J Y, ZHOU T, Et al., Image-to-image translation with conditional adversarial networks [C], IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125-1134, (2017)
[8] KARACAN L, AKATA Z, ERDEM A, Et al., Learning to generate images of outdoor scenes from attributes and semantic layouts
[9] ZHU J Y, PARK T, ISOLA P, Et al., Unpaired image-to-image translation using cycle-consistent adversarial networks [C], IEEE International Conference on Computer Vision, pp. 2223-2232, (2017)
[10] WANG H, CHEN Y, CAI Y, Et al., SFNet-N: an improved SFNet algorithm for semantic segmentation of low-light autonomous driving road scenes [J], IEEE Transactions on Intelligent Transportation Systems, 23, 11, pp. 21405-21417, (2022)

← 1 2 3 →