Segmentation of aerospace images using convolutional neural networks

Authors

  • V. Hnatushenko
  • I. Gnennyi
  • I. Udovyk
  • O. Shevtsova

DOI:

https://doi.org/10.34185/1562-9945-6-137-2021-03

Keywords:

segmentation, aerospace imaging, machine learning, convolutional neural network

Abstract

To solve practical problems, including for the management of territories, monitoring of emergencies, for the development of the ecology of our planet, for the study and ecological research of our planet, effective algorithms for the segmentation of multispectral images are needed. In recent years, image segmentation using convolutional neural networks has become very popular. A significant difference of this approach is the annotation of the assignment of each pixel to a particular class of objects, so that the learning process of such networks is completely controlled. The paper proposes a new method for segmentation of aerospace im-ages of high spatial resolution based on convolutional neural networks and mask generation. Our model is based on a combined U-Net network with MobileNetV2 as the backbone. It trains on ground data and provides a full prediction mask. A network has been implemented, consisting of separate networks of the same class, working on the expansion of segmentation. Semantic features are used to reduce errors at the semantic level of the outline. Since an in-dependent test revealed some shortcomings in certain classes of the earth's surface, further re-search will be devoted to the creation of a catalog of training samples to support successful differentiation of objects. In general, the obtained accuracy estimates demonstrate the modern characteristics of the developed model, as well as the effectiveness of this combination of network and datasets for test regions. The results show that the proposed algorithm can effec-tively improve the overall accuracy of the semantic segmentation of high spatial resolution remote sensing images and reduce the training time and segmentation time.

References

Hordiiuk, D. M., Hnatushenko, V. V. (2017). Neural network and local laplace filter methods applied to very high resolution remote sensing imagery in urban damage detection. 2017 IEEE International Young Scientists Forum on Applied Physics and Engineering (YSF).doi:10.1109/ysf.2017.8126648.

Mozgovoy Dmitriy, Hnatushenko Volodymyr, Vasyliev Volodymyr. Accuracy evaluation of automated object recognition using multispectral aerial images and neural network. Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108060H (9 August 2018);

https://doi.org/10.1117/12.2502905.

Brand A.K., Manandhar, A.: SEMANTIC SEGMENTATION OF BURNED AREAS IN SATELLITE IMAGES USING A U-NET-BASED CONVOLUTIONAL NEURAL NETWORK, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2021, 47–53, https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-47-2021, 2021.

Hnatushenko V., Zhernovyi V. (2020) Method of Improving Instance Segmentation for Very High Resolution Remote Sensing Imagery Using Deep Learning. In: Babichev S., Peleshko D., Vynokurova O. (eds) Data Stream Mining & Processing. DSMP 2020. Communications in Computer and Information Science, vol 1158. Springer, Cham. https://doi.org/10.1007/978-3-030-61656-4_21

Hnatushenko Volodymyr, Zhernovyi Vadym, Udovik Iryna, Shevtsova Olga. Intelligent System for Building Separation on a Semantically Segmented Map. 2 International Workshop on Intelligent Information Technologies & Systems of Information Security (IntelITSIS-2021) Khmelnytskyi, Ukraine. http://ceur-ws.org/Vol-2853/keynote1.pdf

Marushko E.E, Doudkin A.A, Zheng X. Identification of Earth’s surface objects using ensembles of convolutional neural networks. Journal of the Belarusian State University. Mathematics and Informatics. 2021;2:114–123.

Simonyan, K., Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR, abs/1409.1556.

Sandler M., Howard A., Zhu M., Zhmoginov A. and Chen L. MobileNetV2: Inverted Residuals and Linear Bottlenecks. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510-4520, doi: 10.1109/CVPR.2018.00474.

Knapheide J., Stabernack B., Kuhnke M. A High Throughput MobileNetV2 FPGA Implementation Based on a Flexible Architecture for Depthwise Separable Convolution. 30th International Conference on Field-Programmable Logic and Applications (FPL), 2020, pp. 277-283, doi: 10.1109/FPL50879.2020.00053.

Published

2021-12-10