Skip to main content
SpringerLink
Log in

RGB-D indoor semantic segmentation network based on wavelet transform

  • Original Paper
  • Published:
Evolving Systems Aims and scope Submit manuscript

Abstract

In computer vision, convolution and pooling operations often lose high-frequency information, and contour details also disappear as the network becomes deeper, especially in image semantic segmentation. For RGB-D image semantic segmentation, all the effective information of RGB and depth images can not be effectively used, while the form of wavelet transform can well preserve the low frequency and high frequency information of the original image. In order to solve the problem of information loss in RGB-D indoor semantic segmentation network, we proposed a RGB-D indoor semantic segmentation network based on wavelet transform. The wavelet transform fusion module is designed to preserve contour details, where discrete wavelet transform blocks are used in place of pooling operations. And a wavelet transform connection module is used to connect contextual information between the encoder and decoder. They can make full use of the complementarity of high and low frequency information to improve the segmentation accuracy of object edge contours. The proposed efficient method is evaluated on the commonly used indoor datasets NYUv2 and SUNRGB-D, and the results show that the proposed method achieves state-of-the-art performance and real-time inference.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Availability of data and materials

Publicly available dataset was used in this study. The NYUv2 dataset can be found here: https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html. The SUNRGBD dataset can be found here: http://rgbd.cs.princeton.edu/.

References

  • Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495

    Article  Google Scholar 

  • Borse S, Cai H, Zhang Y, Porikli F (2021) Hs3: learning with proper task complexity in hierarchically supervised semantic segmentation. arXiv preprint arXiv:2111.02333

  • Borse S, Wang Y, Zhang Y, Porikli F (2021) Inverseform: a loss function for structured boundary-aware segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5901–5911

  • Chang M, Guo F, Ji R (2018) Depth-assisted refinenet for indoor semantic segmentation. In: 2018 24th international conference on pattern recognition (ICPR). IEEE, pp 1845–1850

  • Chen L-Z, Lin Z, Wang Z, Yang Y-L, Cheng M-M (2021) Spatial information guided convolution for real-time rgbd semantic segmentation. IEEE Trans Image Process 30:2313–2324

    Article  Google Scholar 

  • Couprie C, Farabet C, Najman L, LeCun Y (2013) Indoor semantic segmentation using depth information. arXiv preprint arXiv:1301.3572

  • Dong G, Yan Y, Shen C, Wang H (2020) Real-time high-performance semantic image segmentation of urban street scenes. IEEE Trans Intell Transp Syst 22(6):3258–3274

    Article  Google Scholar 

  • Eigen D, Fergus R (2015) Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE international conference on computer vision, pp 2650–2658

  • Gupta S, Girshick R, Arbeláez P, Malik J (2014) Learning rich features from rgb-d images for object detection and segmentation. In: European conference on computer vision. Springer, pp 345–360

  • Hazirbas C, Ma L, Domokos C, Cremers D (2016) Fusenet: incorporating depth into semantic segmentation via fusion-based cnn architecture. In: Asian conference on computer vision. Springer, pp 213–228

  • He Y, Chiu W-C, Keuper M, Fritz M (2017) Std2p: Rgbd semantic segmentation using spatio-temporal data-driven pooling. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4837–4846

  • He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  • Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861

  • Hu Y, Chen Z, Lin W (2018) Rgb-d semantic segmentation: a review. In: 2018 IEEE international conference on multimedia and expo workshops (ICMEW). IEEE, pp 1–6

  • Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141

  • Hu X, Yang K, Fei L, Wang K (2019) Acnet: attention based network to exploit complementary features for rgbd semantic segmentation. In: 2019 IEEE international conference on image processing (ICIP). IEEE, pp 1440–1444

  • Jiang J, Zheng L, Luo F, Zhang Z (2018) Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation. arXiv preprint arXiv:1806.01054

  • Kaut H, Singh R (2016) A review on image segmentation techniques for future research study. Int J Eng Trends Technol 35(11):504–505

    Article  Google Scholar 

  • Li Q, Shen L (2020) Wavesnet: Wavelet integrated deep networks for image segmentation. arXiv preprint arXiv:2005.14461

  • Li Q, Shen L, Guo S, Lai Z (2020) Wavelet integrated cnns for noise-robust image classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7245–7254

  • Liu P, Zhang H, Lian W, Zuo W (2019) Multi-level wavelet convolutional neural networks. IEEE Access 7:74973–74985

    Article  Google Scholar 

  • Li Y, Wang Y, Leng T, Zhijie W (2020) Wavelet u-net for medical image segmentation. In: International conference on artificial neural networks. Springer, pp 800–810

  • Li Y, Zhang J, Cheng Y, Huang K, Tan T (2017) Semantics-guided multi-level rgb-d feature fusion for indoor semantic segmentation. In: 2017 IEEE international conference on image processing (ICIP). IEEE, pp 1262–1266

  • Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440

  • Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693. https://doi.org/10.1109/34.192463

    Article  MATH  Google Scholar 

  • Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  • Park S-J, Hong K-S, Lee S (2017) Rdfnet: Rgb-d multi-level residual feature fusion for indoor semantic segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 4980–4989

  • Ramamonjisoa M, Firman M, Watson J, Lepetit V, Turmukhambetov D (2021) Single image depth estimation using wavelet decomposition. arXiv preprint arXiv:2106.02022

  • Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241

  • Seichter D, Köhler M, Lewandowski B, Wengefeld T, Gross H-M (2020) Efficient rgb-d semantic segmentation for indoor scene analysis. arXiv preprint arXiv:2011.06961

  • Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: European conference on computer vision. Springer, pp 746–760

  • Song S, Lichtenberg SP, Xiao J (2015) Sun rgb-d: a rgb-d scene understanding benchmark suite. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 567–576

  • Wu Y, Jiang J, Huang Z, Tian Y (2021) Fpanet: feature pyramid aggregation network for real-time semantic segmentation. Appl Intell 52:3319–3336. https://doi.org/10.1007/s10489-021-02603-z

    Article  Google Scholar 

  • Xia H, Ma M, Li H, Song S (2021) Mc-net: multi-scale context-attention network for medical ct image segmentation. Appl Intell 1:1–12

    Google Scholar 

  • Xing Y, Wang J, Chen X, Zeng G (2019) Coupling two-stream rgb-d semantic segmentation network by idempotent mappings. In: 2019 IEEE international conference on image processing (ICIP). IEEE, pp 1850–1854

  • Xu K, Qin M, Sun F, Wang Y, Chen Y-K, Ren F (2020) Learning in the frequency domain. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1740–1749

  • Yuan X, Shi J, Gu L (2021) A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Syst Appl 169:114417. https://doi.org/10.1016/j.eswa.2020.114417

    Article  Google Scholar 

  • Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881–2890

  • Zhou W, Yuan J, Lei J, Luo T (2021) Tsnet: three-stream self-attention network for rgb-d indoor semantic segmentation. IEEE Intell Syst 36(4):73–78. https://doi.org/10.1109/MIS.2020.2999462

    Article  Google Scholar 

Download references

Funding

This work was supported by Guizhou Provincial Science and Technology Foundation under Grant no. QKHJC-ZK[2021]Key001.

Author information

Author notes

  1. Yuhong Liu, Shiyi Jiang and Rongfen Zhang contributed equally to this work.

Authors and Affiliations

  1. College of Big Data and Information, Guizhou University, Guiyang, 550025, Guizhou, People’s Republic of China

    Runze Fan, Yuhong Liu, Shiyi Jiang & Rongfen Zhang

Authors
  1. Runze Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuhong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shiyi Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rongfen Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed equally to this work. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Rongfen Zhang.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fan, R., Liu, Y., Jiang, S. et al. RGB-D indoor semantic segmentation network based on wavelet transform. Evolving Systems 14, 981–991 (2023). https://doi.org/10.1007/s12530-022-09479-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12530-022-09479-5

Keywords

Search

Navigation