Abstract
While semantic segmentation is useful for object detection and scene perception, traditional methods have limitations in terms of the level of accuracy details that can be recovered from a given image or scene. A label category can be assigned to each pixel by a deep learning-based semantic segmentation algorithm, which can be developed using the pyramid scene parsing method, which was proposed in this paper. Training and testing experimental results on public datasets were carried out, resulting in high mean accuracy and good intersection over union (IOU).
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
Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., Wang, J. OCNet: object context network for scene parsing (2018). Retrieved from http://arxiv.org/abs/1809.00916
Li, B., Shi, Y., Qi, Z., Chen, Z.: A survey on semantic segmentation. In: IEEE International Conference on Data Mining Workshops, ICDMW, 2018-November, pp. 1233–1240 (2019). https://doi.org/10.1109/ICDMW.2018.00176
Wu, G., Li, Y.: CyclicNet: an alternately updated network for semantic segmentation. Multimedia Tools and Applications 80(2), 3213–3227 (2021). https://doi.org/10.1007/s11042-020-09791-9
Alam, M., Wang, J.F., Guangpei, C., Yunrong, L., Chen, Y.: Convolutional neural network for the semantic segmentation of remote sensing images. Mobile Netw. Appl. 26(1), 200–215 (2021). https://doi.org/10.1007/s11036-020-01703-3
Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking Atrous Convolution for Semantic Image Segmentation (2017). Retrieved from http://arxiv.org/abs/1706.05587
Lateef, F., Ruichek, Y.: Survey on semantic segmentation using deep learning techniques. Neurocomputing 338(5), 321–348 (2019). https://doi.org/10.1016/j.neucom.2019.02.003
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings—30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-January, 6230–6239. (2017). https://doi.org/10.1109/CVPR.2017.660
Ko, T. Y., Lee, S.H.: Novel method of semantic segmentation applicable to augmented reality. Sensors (Switzerland) 20(6) (2020). https://doi.org/10.3390/s20061737
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018). https://doi.org/10.1109/TPAMI.2017.2699184
Fang, H., Lafarge, F.: Pyramid scene parsing network in 3D: improving semantic segmentation of point clouds with multi-scale contextual information. ISPRS J. Photogramm. Remote. Sens. 154(July), 246–258 (2019). https://doi.org/10.1016/j.isprsjprs.2019.06.010
Iccv, A., & Id, P.: Towards Bridging Semantic Gap to Improve Semantic Segmentation Anonymous ICCV submission. Iccv2019, 1(c), 1–5 (2019)
Thoma, M.: A survey of semantic segmentation, pp. 1–16 (2016). Retrieved from http://arxiv.org/abs/1602.06541
Yan, J., Zhong, Y., Fang, Y., Wang, Z., Ma, K.: Exposing semantic segmentation failures via maximum discrepancy competition. Int. J. Comput. Vision 129(5), 1768–1786 (2021). https://doi.org/10.1007/s11263-021-01450-2
Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., Wang, J.: OCNet: object context for semantic segmentation. Int. J. Comput. Vision 129(8), 2375–2398 (2021). https://doi.org/10.1007/s11263-021-01465-9
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 Singapore Pte Ltd.
About this paper
Cite this paper
Ravikiran, P., Chakkaravarthy, M. (2022). Improved Efficiency of Semantic Segmentation using Pyramid Scene Parsing Deep Learning Network Method. In: Reddy, V.S., Prasad, V.K., Mallikarjuna Rao, D.N., Satapathy, S.C. (eds) Intelligent Systems and Sustainable Computing. Smart Innovation, Systems and Technologies, vol 289. Springer, Singapore. https://doi.org/10.1007/978-981-19-0011-2_16
Download citation
DOI: https://doi.org/10.1007/978-981-19-0011-2_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0010-5
Online ISBN: 978-981-19-0011-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)