Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

A Segmentation Method Based on SE Attention and U-Net for Apple Image

  • Conference paper
  • First Online:

Part of the book series:Lecture Notes in Computer Science ((LNCS,volume 14356))

Included in the following conference series:

  • 562Accesses

Abstract

Apple image segmentation is the basis for apple target recognition and positioning in apple intelligent picking. Traditional apple image segmentation methods have problems such as low accuracy and poor recall rate. Based on the U-Net model, a SE attention mechanism fusion improved U-Net apple image segmentation method is proposed to utilize contextual information of features. First, 344 apple images were collected in the orchard and manually labeled using LabelMe software. The samples were expanded to 1700 using data augmentation. Then the U-type network structure is used to connect the feature maps of the low-level network and the high-level network. The skip connection is used to reduce the network complexity, and the number of feature map channels is superimposed. The SE attention mechanism is added to the decoder part to enhance the channel features of the effective feature maps for apple image segmentation tasks and suppress unimportant channel features to obtain rich contextual information for more refined feature maps. Finally, apple target segmentation is predicted based on the obtained feature maps. The results show that the U-Net model with SE attention fusion can accurately segment the apple region, especially for small-scale apples, and can further optimize the segmentation effect of the edge. The segmentation precision of the model can reach 98.86%, and F1 score is 98.96%, verifying that the proposed model can accurately segment apple targets of different scales in complex environments.

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

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 9151
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 11439
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Similar content being viewed by others

References

  1. Zhang, Y.J., Li, M.Z., Qiao, J., Liu, G.: Segmentation algorithm for apple recognition using image features and artificial neural network. Acta 0ptica Sinica28(11), 2104–2108 (2008)

    Google Scholar 

  2. Liu, X.Y., Zhao, D.A., Jia, W.K., Ruan, C.Z., Ji, W.: Fruits segmentation method based on superpixel features for apple harvesting robot. Trans. Chin. Soc. Agric. Mach.50(11), 15–23 (2019)

    Google Scholar 

  3. Liu, X.N., Wang, Y.T., Zhao, C., Zhu, C.W., Li, L.K.: Research on image segmentation method of Lingwu Long Jujubes based on watershed. Comput. Eng. Appl.54(15), 169–175+184 (2018)

    Google Scholar 

  4. Zhao, C., Wang, Y.T., Zhu, C.W.: Lingwu long jujubes image segmentation algorithm based on geometric features. Comput. Eng. Appl.55(15), 204–212 (2019)

    Google Scholar 

  5. Zhang, C.L., Zou, K.L., Pan, Y.: A method of apple image segmentation based on color-texture fusion feature and machine learning. Agronomy10(7) (2020)

    Google Scholar 

  6. Fan, P., et al.: A method of segmenting apples based on gray-centered RGB color space. Remote Sens.13(6), 1211 (2021)

    Article MathSciNet  Google Scholar 

  7. Peng, H., Wu, P.F., Zhai, R.F., Liu, S.M., Wu, L.L., Jing, X.: Image segmentation algorithm for overlapping fruits based on disparity map. Trans. Chin. Soc. Agric. Mach.43(06), 167–173 (2012)

    Google Scholar 

  8. Minaee, S., Boykov, Y.Y., Porikli, F., et al.: Image segmentation using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell.44(7), 3523–3542 (2022)

    Google Scholar 

  9. Liu, H., Jiang, J.B., S.Y., Jia, W.D., Zeng, X., Zhuang, Z.Z.: Multi-category segmentation of orchard scene based on improved DeepLab V3+. Trans. Chin. Soc. Agric. Mach.53(11), 255–261 (2022)

    Google Scholar 

  10. Chen, J., Han, M.N., Lian, Y., Zhang, S.: Segmentation of impurity rice grain images based on U-Net model. Trans. Chin. Soc. Agric. Eng.36(10), 174–180 (2020)

    Google Scholar 

  11. Zhang, S.W., Wang, Z., Wang, Z.L.: Method for image segmentation of cucumber disease leaves based on multi-scale fusion convolutional neural networks. Trans. Chin. Soc. Agric. Eng.36(16), 149–157 (2020)

    Google Scholar 

  12. Zhang, B.Y., Ni, H.M., Hu, X.Y., Qi, D.W.: Research on tree image segmentation based on U-net network. For. Eng.37(02), 67–73 (2021)

    Google Scholar 

  13. Duan, L.F., Xiong, X., Liu, Q., Yang, W.N., Huang, C.L.: Field rice panicles segmentation based on deep full convolutional neural network. Trans. Chin. Soc. Agric. Eng. (Transactions of the CSAE)34(12), 202–209 (2018)

    Google Scholar 

  14. Liu, L.B., Cheng, X.L., Lai, J.C.: Segmentation method for cotton canopy image based on improved fully convolutional network model. Trans. Chin. Soc. Agric. Eng. (Transactions of the CSAE)34(12), 193–201 (2018)

    Google Scholar 

  15. Xiong, J.T., Liu, B.L., Zhong, Z., Chen, S.M., Zheng, Z.H.: Litchi flower and leaf segmentation and recognition based on deep semantic segmentation. Trans. Chin. Soc. Agric. Mach.52(06), 252–258 (2021)

    Google Scholar 

  16. Jia, W.K., Zhang, Z.H., Shao, W.J., Ji, Z., Hou, S.J.: RS-Net: robust segmentation of green overlapped apples. Precis. Agric.23(2), 492–513 (2022)

    Article  Google Scholar 

  17. Xue, J.R., et al.: Image Segmentation method for Lingwu long jujubes based on improved FCN-8s. Trans. Chin. Soc. Agric. Eng. (Transactions of the CSAE)37(05), 191–197 (2021)

    Google Scholar 

  18. Ni, X., Li, C., Jiang, H., Takeda, F.: Deep learning image segmentation and extraction of blueberry fruit traits associated with harvestability and yield. Horticult. Res. (1) (2020)

    Google Scholar 

  19. Wang, J.J., Zhao, D.A., Ji, W., Cai, J.H., Li, F.Z.: Segmentation of apple image by BP neural network using in apple harvesting robot. J. Agric. Mech. Res. (11), 19–21 (2008)

    Google Scholar 

  20. Wjpd, A., Yt, A., Rong, L.B., et al.: Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot. Comput. Electron. Agric.172 (2020)

    Google Scholar 

  21. Li, Q.W., Jia, W.K., Sun, M.L., Hou, S.J., Zheng, Y.J.: A novel green apple segmentation algorithm based on ensemble U-Net under complex orchard environment. Comput. Electron. Agric.180, 105900 (2021)

    Article  Google Scholar 

  22. Nicolai, H., Pravakar, R., Volkan. I., MinneApple: a benchmark dataset for apple detection and segmentation. IEEE Robot. Autom. Lett.5(2) (2020)

    Google Scholar 

  23. Ronneberger, O., Philipp, F., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. CoRR, abs/1505.04597 (2015)

    Google Scholar 

  24. Jie, H., Li, S., Albanie, S., Gang, S., Wu, E.H.: Squeeze-and-excitation networks. IEEE Trans. Patt. Anal. Mach. Intell.PP(99) (2017)

    Google Scholar 

  25. Zhong, Z., Lin, Z.Q., Bidart, R., et al.: Squeeze-and-attention networks for semantic segmentation. CoRR, abs/1909.03402 (2019)

    Google Scholar 

  26. Qiu, Y.F., Wen, J.Y.: Image semantic segmentation based on combination of DeepLabV3+ and attention mechanism. Laser Optoelec. Prog.59(04), 130–139 (2022)

    Google Scholar 

Download references

Acknowledgement

This work is supported in part by National Natural Science Foundation of China under grant No. 61902339, by the Natural Science Basic Research Plan in Shaanxi Province of China under grants No. 2021JM-418, by the Epidemic Emergency Research Projects of Yan'an University under grant No. YDFK073, by Doctoral Starting up Foundation of Yan'an University under grant No. YDBK2019–06, by Yan'an Special Foundation for Science and Technology (2019–01, 2019–13).

Author information

Authors and Affiliations

  1. College of Mathematics and Computer Science, Yan’an University, Yan’an, 716000, China

    Liang Gao, Jinrong He, Longlong Zhai & Yiting He

Authors
  1. Liang Gao

    You can also search for this author inPubMed Google Scholar

  2. Jinrong He

    You can also search for this author inPubMed Google Scholar

  3. Longlong Zhai

    You can also search for this author inPubMed Google Scholar

  4. Yiting He

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toJinrong He.

Editor information

Editors and Affiliations

  1. Dalian University of Technology, Dalian, China

    Huchuan Lu

  2. University of Sydney, Sydney, NSW, Australia

    Wanli Ouyang

  3. Shenzhen University, Shenzhen, China

    Hui Huang

  4. Tsinghua University, Beijing, China

    Jiwen Lu

  5. Dalian University of Technology, Dalian, China

    Risheng Liu

  6. Institute of Automation, CAS, Beijing, China

    Jing Dong

  7. University of Technology Sydney, Sydney, NSW, Australia

    Min Xu

Rights and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gao, L., He, J., Zhai, L., He, Y. (2023). A Segmentation Method Based on SE Attention and U-Net for Apple Image. In: Lu, H.,et al. Image and Graphics. ICIG 2023. Lecture Notes in Computer Science, vol 14356. Springer, Cham. https://doi.org/10.1007/978-3-031-46308-2_22

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 9151
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 11439
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

[8]ページ先頭
©2009-2025 Movatter.jp