Abstract
Semantic segmentation plays a very important role in computer vision. It can be used in many real-world applications, such as virtual reality and augmented reality, robotics and autopilot technology. The existing models have large amount of network parameters and high complexity, and can not fully extract the context information of the image. In order to solve the problem of high complexity and poor real-time performance of DenseNet, the backbone network of DenseAspp model, this paper proposes an image semantic segmentation method based on Shufflenetv2. The lightweight convolutional neural network Shufflenet-v2 is used to replace DenseNet as the backbone network of the segmentation model to extract features, which effectively reduces the amount of parameters and calculation of the model and improves the real-time performance of the segmentation algorithm. SkNet, a selective convolution kernel mechanism, enables each neuron to adaptively select the size of receptive field according to the multi-scale information of input features, thus improving the segmentation accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, Y., Wang, Q., Jia, W., Lu, Y., Li, Y., He, X.: See more than once: Kernel-sharing atrous convolution for semantic segmentation. Neurocomput. 443, 26–34 (2021)
Zhang, Y., Sun, X., Dong, J., Chen, C., Lv, Q.: GPNet: gated pyramid network for semantic segmentation. Pattern Recogn. 115, 107940 (2021)
Sediqi, K.M., Lee, H.J.: A novel upsampling and context convolution for image semantic segmentation. Sensors 21(6), 2170 (2021)
Yan, J., Zhong, Y., Fang, Y., Wang, Z., Ma, K.: Exposing semantic segmentation failures via maximum discrepancy competition. Int. J. Comput. Vis. 129(5), 1768–1786 (2021). https://doi.org/10.1007/s11263-021-01450-2
Xu, Z., Zhang, W., Zhang, T., Li, J.: HRCNet: high-resolution context extraction network for semantic segmentation of remote sensing images. Remote Sens. 13(1), 71 (2020)
Miyamoto, R., et al.: Visual navigation based on semantic segmentation using only a monocular camera as an external sensor: special issue on real world robot challenge in Tsukuba and Osaka. J. Robot. Mech. 32(6), 1137–1153 (2020)
Zhou, D., et al.: Robust building extraction for high spatial resolution remote sensing images with self-attention network. Sensors 20(24), 7241 (2020)
Wu, T., Tang, S., Zhang, R., Cao, J., Zhang, Y.: CGNet: a light-weight context guided network for semantic segmentation. IEEE Trans. Image Process. Publ. IEEE Sig. Process. Soc. 30, 1169–1179 (2020)
Pozzer, S., Rezazadeh Azar, E., Dalla Rosa, F., Chamberlain Pravia, Z.M.: Semantic segmentation of defects in infrared thermographic images of highly damaged concrete structures. J. Perform. Constr. Facil. 35(1), 04020131 (2021)
Pemasiri, A., Nguyen, K., Sridharan, S., Fookes, C.: Multi-modal semantic image segmentation. Comput. Vis. Image Understanding 202, 103085 (2021)
Feng, J., Liu, Y.-S., Gong, L.: Junction-aware shape descriptor for 3D articulated models using local shape-radius variation. Sig. Process. 112, 4–16 (2015)
Dewanto, V., Aprinaldi, A., Ian, Z., Wisnu, J.: A novel knowledge-compatibility benchmarker for semantic segmentation. Int. J. Smart Sens. Intell. Syst. 8(2), (2015)
Gritti, T., Damkat, C., Monaci, G.: Semantic video scene segmentation and transfer. Comput. Vis. Image Underst. 122, 172–181 (2014)
Pei, D., Li, Z., Ji, R., Sun, F: Efficient semantic image segmentation with multi-class ranking prior. Comput. Vis. Image Underst. 120, 81–90 (2014)
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
Zhong, G., Zhao, H., Liu, G. (2022). Lightweight Semantic Segmentation Convolutional Neural Network Based on SKNet. In: Liu, Q., Liu, X., Chen, B., Zhang, Y., Peng, J. (eds) Proceedings of the 11th International Conference on Computer Engineering and Networks. Lecture Notes in Electrical Engineering, vol 808. Springer, Singapore. https://doi.org/10.1007/978-981-16-6554-7_15
Download citation
DOI: https://doi.org/10.1007/978-981-16-6554-7_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6553-0
Online ISBN: 978-981-16-6554-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)