Image restoration and fault tolerance of stereo SLAM based on generative adversarial net

被引：1

作者：

Wang K. ^{[1
]}

Yue B.-X. ^{[1
]}

Fu J.-W. ^{[1
]}

Liang J. ^{[1
]}

机构：

[1] College of Control Science and Engineering, Zhejiang University, Hangzhou

来源：

Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2019年 / 53卷 / 01期

关键词：

Fault tolerance; Image generation network; Image restoration; Pix2Pix; Simultaneous localization and mapping (SLAM);

D O I：

10.3785/j.issn.1008-973X.2019.01.013

中图分类号：

学科分类号：

摘要：

The classical Pix2Pix network was modified in order to promote the capacity of fault tolerance of simultaneous localization and mapping (SLAM) system. The network was gradually added to depth estimation network and its depth information, image reconstruction loss based on STN network and image inpainting loss based on image inpainting network. Information was mined based on the coupling of stereo images and merged to utilize information usage and promote model performance. Then generative adversarial net (GAN) and SLAM were combined, and the fault tolerance in the sensing level was directly realized. Experiments were performed on KITTI and Cityscapes dataset in order to prove the effectiveness of the improvement. The generated images and original images were both fed as inputs of stereo SLAM system. Results showed that the fault tolerance idea was approachable. © 2019, Zhejiang University Press. All right reserved.

引用

页码：115 / 125

页数：10

共 25 条

[1]

Shum H., Kang S.B., Review of image-based rendering techniques, Visual Communications and Image Processing, 4067, pp. 2-14, (2000)

[2]

Tatarchenko M., Dosovitskiy A., Brox T., Multi-view 3D models from single images with a convolutional network, Knowledge and Information Systems, 38, 1, pp. 231-257, (2015)

[3]

Davison A.J., Real-time simultaneous localisation and mapping with a single camera, Proceedings Ninth IEEE International Conference on Computer Vision, pp. 1403-1410, (2003)

[4]

Mur-Artal R., Montiel J.M.M., Tardos J.D., ORB-SLAM: a versatile and accurate monocular SLAM system, IEEE Transactions on Robotics, 31, 5, pp. 1147-1163, (2015)

[5]

Durrantwhyte H.F., Bailey T., Simultaneous localization and mapping, IEEE Robotics Automat Mag, 13, 3, pp. 108-117, (2006)

[6]

Lemaire T., Berger C., Jung I.K., Et al., Vision-based SLAM: stereo and monocular approaches, International Journal of Computer Vision, 74, 3, pp. 343-364, (2007)

[7]

Jaderberg M., Simonyan K., Zisserman A., Spatial transformer networks, Advances in Neural Information Processing Systems, pp. 2017-2025, (2015)

[8]

Tatarchenko M., Dosovitskiy A., Brox T., Single-view to multi-view: reconstructing unseen views with a convolutional network, Knowledge and Information Systems, 38, 1, pp. 231-257, (2015)

[9]

Zhao B., Wu X., Cheng Z.Q., Et al., Multi-view image generation from a single-view, Proceedings of the 26th ACM International Conference on Multimedia, pp. 383-391, (2018)

[10]

Zhou T., Tulsiani S., Sun W., Et al., View synthesis by appearance flow, European Conference on Computer Vision, pp. 286-301, (2016)

← 1 2 3 →