Abstract
Aiming at the problem of fuzzy edge segmentation and incomplete division in DeepLabV3+ segmentation results of parts, we propose an improved DeepLabV3+ semantic segmentation algorithm. Firstly, We replace Xception in the original network with lightweight MobileNet_V2 on the backbone network, improving the lightness of the network model. Then, channel attention is introduced into the backbone network to enhance the importance of effective feature information and enhance the learning ability of parts objective. After that, using feature fusion branches to adaptively learn spatial information of low-level features at different levels to obtain richer semantic information. Finally, the asymmetric convolution is used to replace the \(3\times 3\) convolution in the Decode-part to improve the processing ability of the convolution kernel and verify on the self-built mechanical parts dataset. The experimental results show that our method can achieve more precise semantic segmentation effect compared with the traditional deeplabv3+ and other segmentation methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, C., Li, Y.G., Luo, L.F.: Parts image feature extraction based on SIFT-SUSAN algorithm. Manufacturing automation 36(16), 81–85 (2014)
Han, Y.J.: Research on Geometric features-based Method for Workpiece recognition. Dalian University of Technology, Liaoning (2014)
Girshick, R., Donahue, J., Daeewll, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587. Columbus (2014)
Liu, W., Aanguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multi-Box detector. In: European Conference on Computer Vision, pp 21–37. Springer Verlag (2016)
Zhang, J., Liu, F.L., Wang, R.W.: Research on industrial parts recognition algorithm based on YOLOv3 in intelligent assembly. Photoelectron and laser 31(10), 1054–1061 (2020)
Yu, Y.W., Han, X., Du, L.Q.: Target part recognition based on Inception-SSD algorithm. Optical precision engineering 28(8), 1799–1809 (2020)
Yang, L., Chen, S.Y., Cui, G.H., Zhu, X.L.: Recognition and location method of workpiece based on improved YOLOv4. Modular machi. Tools and Autom. Machine. Technol. 10, 28–32 (2021)
Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis Machine Intelligence, 2481–2495 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention. Springer, pp. 234–241 (2015)
Huang, H.S., Wei, Z.Y., Yao, L.G.: Research on part instance segmentation and recognition based on deep learning. Modular machi. Tools and Automat. Machine. Technol. 5, 122–125 (2019)
Hong, Q., Song, Q., Yang, C.T., Zhang, P., Chang, L.: Image segmentation technology of mechanical parts based on intelligent vision. J Machin. Manuf. Automa. 49(5), 203–206 (2020)
Wang, Y.: Part segmentation in cluttered scene based on convolutional neural network. Qingdao Technology University, Shandong (2021)
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European Conference on Computer Vision, pp. 833–851. Berlin (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNet_V2: Inverted residuals and linear bottlenecks. In: Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520. IEEE Computer Society (2018)
Li, Q.H., Li, C.P., Zang, J., Chen, H., Wang, S.Q.: Survey of compressed deep neural network. Computer Science 46(9), 1–14 (2019)
Wang, Q., Wu, B., Zhu, P., Li, P., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11531–11539. IEEE Computer Society (2020)
Liu, S.T., Huang, D., Wang, Y.H.: Learning spatial fusion for single-shot Object Detection https://arxiv.org/abs/1911.09516 (2020)
Ding, X., Guo, Y., Ding, G., Han, J.: ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks, pp. 1911–1920. Institude of Electrical and Electronics Engineers Inc (2019)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6230–6239. IEEE Press, Washington (2017)
Sun, K., Xiao, B., Liu, D., Wang, J.D.: Deep high-resolution representation learning for human pose estimation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 5686–5696 (2019)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017). https://doi.org/10.48550/arXiv.1706.05587
Acknowledgment
This work is supported by the National Natural Science Foundation of China (52075532), the Nature Science Foundation of Liaoning Province (2020-MS-030), and the Youth Innovation Promotion Association of Chinese Academy of Sciences (2021199).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hou, W., Fu, S., Xia, X., Xia, R., Zhao, J. (2022). Research on Part Image Segmentation Algorithm Based on Improved DeepLabV3+ . In: Liu, H., et al. Intelligent Robotics and Applications. ICIRA 2022. Lecture Notes in Computer Science(), vol 13458. Springer, Cham. https://doi.org/10.1007/978-3-031-13841-6_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-13841-6_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13840-9
Online ISBN: 978-3-031-13841-6
eBook Packages: Computer ScienceComputer Science (R0)