Research on Style Transfer Network for Autonomous Driving Data Generation

被引：0
|
作者：
Wang D. [1 ]
Du J. [1 ]
Cao J. [1 ]
Zhang M. [2 ]
Zhao G. [1 ]
机构：
[1] School of Automative Engineering, Harbin Institute of Technology, Weihai
[2] 32184 Troops, Beijing
来源：
Qiche Gongcheng/Automotive Engineering | 2022年 / 44卷 / 05期
关键词：
Autonomous driving; Deep learning; GANs; Style transfer;
D O I：
10.19562/j.chinasae.qcgc.2022.05.005
中图分类号：
学科分类号：
摘要：
The data abundance of the autonomous driving dataset is the key to ensuring the robustness and reliability of autonomous driving algorithm based on deep learning, but the amount of data with night scenes and various climates and weather conditions in current autonomous driving datasets are still very limited. In order to meet the application needs in the field of unmanned driving, a style transfer network is built, which can convert the current autonomous driving data into various forms such as night and snow, etc. The network adopts a structure of single encoder-dual decoder, combined with various means such as semantic segmentation networks, skip connections, and multi-scale discriminators to improve the quality of generated images with good vision effects. Deeplabv3+ semantic segmentation network trained by real data is used to evaluate the images generated and the results show that the mean intersection over union of the images generated by the network adopted is 2.50 and 4.41 percentage points higher than that generated by AugGAN and UNIT networks with double encoder-double decoder structure respectively. © 2022, Editorial Board, Journal of Applied Optics. All right reserved.
引用
收藏
页码：684 / 690and721
相关论文
共 25 条
  • [1] GEIGER A, LENZ P, STILLER C, Et al., Vision meets robotics: the KITTI dataset, International Journal of Robotics Research, 32, 11, pp. 1231-1237, (2013)
  • [2] YU F, CHEN H, WANG X, Et al., Bdd100k: a diverse driving dataset for heterogeneous multitask learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636-2645, (2020)
  • [3] CORDTS M, OMRAN M, RAMOS S, Et al., The cityscapes dataset for semantic urban scene understanding, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213-3223, (2016)
  • [4] TIAN Y, PEI K, JANA S, Et al., Deeptest: automated testing of deep-neural-network-driven autonomous cars, Proceedings of the 40th International Conference on Software Engineering, pp. 303-314, (2018)
  • [5] GATYS L A, ECKER A S, BETHGE M., A neural algorithm of artistic style, Journal of Vision, (2015)
  • [6] JOHNSON J, ALAHI A, FEI-FEI L., Perceptual losses for real-time style transfer and super-resolution, European Conference on Computer Vision, pp. 694-711, (2016)
  • [7] IOFFE S, SZEGEDY C., Batch normalization: accelerating deep network training by reducing internal covariate shift, International Conference on Machine Learning, pp. 448-456, (2015)
  • [8] ULYANOV D, VEDALDI A, LEMPITSKY V., Instance normalization: the missing ingredient for fast stylization, (2016)
  • [9] LI Y, WANG N, LIU J, Et al., Demystifying neural style transfer, Twenty-sixth International Joint Conference on Artificial Intelligence, (2017)
  • [10] ULYANOV D, VEDALDI A, LEMPITSKY V., Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6924-6932, (2017)
123