Self-Supervised Monocular Depth Estimation Based on Full Scale Feature Fusion

被引：0
|
作者：
Wang C. [1 ]
Chen Y. [1 ]
机构：
[1] Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2023年 / 35卷 / 05期
关键词：
chain residual pooling module; depth estimation; full scale feature fusion module; self-supervised;
D O I：
10.3724/SP.J.1089.2023.19418
中图分类号：
学科分类号：
摘要：
In order to solve the problems of fuzzy boundary and artifacts in the depth map generated by self-supervised monocular depth estimation, a depth network coding and decoding structure based on full scale feature fusion module (FSFFM) and chain residual pooling module (CRPM) is proposed. For decoding in FSFFM, the higher resolution features, the same resolution features obtained by the encoder and the lower resolution features obtained by the previous decoder are fused with the upper level inverse depth map, which enables the features learned by the network contain both global and local information. Then CRPM is designed and used to get the background context information from the fusion features. Finally, an accurate depth map is obtained. Experiments are carried out on KITTI dataset. Compared with baseline, the absolute error of depth value is reduced by 7.8%, and the accuracy with a threshold of 1.25 is improved by 1.1%. The results are better than most existing self supervised monocular depth estimation algorithms. © 2023 Institute of Computing Technology. All rights reserved.
引用
收藏
页码：667 / 675
页数：8
相关论文
共 24 条
  • [1] Snavely N, Seitz S M, Szeliski R., Skeletal graphs for efficient structure from motion, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, (2008)
  • [2] Di Hongwei, Chai Ying, Li Kui, A fast binocular vision stereo matching algorithm, Acta Optica Sinica, 29, 8, pp. 2180-2184, (2009)
  • [3] Chen Ying, Wang Yiliang, Unsupervised monocular depth estimation based on dense feature fusion, Journal of Electronics & Information Technology, 43, 10, pp. 2976-2984, (2021)
  • [4] Eigen D, Puhrsch C, Fergus R., Depth map prediction from a single image using a multi-scale deep network, Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 2366-2374, (2014)
  • [5] Liu F Y, Shen C H, Lin G S, Et al., Learning depth from single monocular images using deep convolutional neural fields, IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, 10, pp. 2024-2039, (2016)
  • [6] Laina I, Rupprecht C, Belagiannis V, Et al., Deeper depth prediction with fully convolutional residual networks, Proceedings of the 4th International Conference on 3D Vision, pp. 239-248, (2016)
  • [7] Zhao S S, Fu H, Gong M M, Et al., Geometry-aware symmetric domain adaptation for monocular depth estimation, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9780-9790, (2019)
  • [8] Garg R, Vijay Kumar B G, Carneiro G, Et al., Unsupervised CNN for single view depth estimation: geometry to the rescue, Proceedings of the 14th European Conference on Computer Vision, pp. 740-756, (2016)
  • [9] Godard C, Aodha O M, Brostow G J., Unsupervised monocular depth estimation with left-right consistency, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6602-6611, (2017)
  • [10] Zhou T H, Brown M, Snavely N, Et al., Unsupervised learning of depth and ego-motion from video, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6612-6619, (2017)
123