Semantic segmentation algorithms of the Earth's surface pictures based on neural network methods | Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaja tehnika i informatika – Tomsk State University Journal of Control and Computer Science. 2020. № 51. DOI: 10.17223/19988605/51/8

Semantic segmentation algorithms of the Earth's surface pictures based on neural network methods

The aim of the work is to develop algorithms that solve the problem of semantic segmentation of images. A convolu- tional neural network with an original architecture was developed. Performing a software implementation of the algorithm, which allows to build a map of segmented objects of a different class. A comparison of the results of the proposed algorithm with existing analogues is presented.

Download file

Counter downloads: 163

Keywords

компьютерное зрение, искусственные нейронные сети, семантическая сегментация, обработка изображений, computer vision, artificial neural networks, semantic segmentation, image processing

Authors

Name	Organization	E-mail
Druki Alexey Alexeevich	National Research Tomsk Polytechnic University	druki@tpu.ru
Spitsyn Vladimir Grigorievich	National Research Tomsk Polytechnic University	spvg@tpu.ru
Arkalykov Erbolat Usenovich	National Research Tomsk Polytechnic University	arkalykov@tpu.ru

Всего: 3

References

Bundzel, M. & Hashimoto, S. (2010) Object identification in dynamic images based on the memory-prediction theory of brain function. Journal of Intelligent Learning Systems and Applications. 2(4). pp. 212-220. DOI: 10.4236/jilsa.2010.24024

Park, S. & Yoo, J.H. (2013) Realtime face recognition with SIFT based local feature points for mobile devices. The 1st Int. Conf. on Artificial Intelligence, Modelling and Simulation (AIMS 13). Malaysia. pp. 304-308. DOI: 10.1109/AIMS.2013.56

Tawfiq, A. & Ahmed, J. (2016) Object detection and recognition by using enhanced speeded up robust feature. International Journal of Computer Science and Network Security. 16(4). pp. 66-71.

Tore, V. & Chawan, P.M. (2016) FAST Clustering based feature subset selection algorithm for high dimensional data. Interna tional Journal of Computer Science and Mobile Computing. 5(7). pp. 234-238. DOI: 10.1109/TKDE.2011.181

Mammeri, A., Boukerche, A. & Khiari, E. (2016) MSER based text detection and communication algorithm for autonomous vehicles. IEEE Symposium of Computers and Communication. Messina, Italy. pp. 456-460. DOI: 10.1109/ISCC.2016.7543902

Dalal, N. & Triggs, B. (2005) Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). San Diego, USA. Vol. 1. pp. 886-893. DOI: 10.1109/CVPR.2005.177

Mohey el-Din, D. (2016) Enhancement bag-of-words model for solving the challenges of sentiment analysis. International Journal of Advanced Computer Science and Applications. 7(1). pp. 244-251. DOI: 10.14569/IJACSA.2016.070134

Kecman, V. & Melki, G. (2016) Fast online algorithms for support vector machines. IEEE South East Conference (SoutheastCon 2016). Virginia, USA. pp. 26-31. DOI: 10.1109/SECON.2016.7506733

Le Cun, Y. & Bengio, Y. (1998) Convolutional networks for images, speech and time series. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks. Vol. 7(1). Bradford Book. pp. 255-258.

Tensorflow.org. (n.d.) TensorFlow: The Python deep learning library. [Online] Available from: https://www.tensorflow.org (Accessed: 22nd October 2019).

Microway.com. (n.d.) Deep Learning Frameworks: A Survey of TensorFlow, Torch, Theano, Caffe, Neon, and the IBM Machine Learning Stack. [Online] Available from: https://www.microway.com/hpc-tech-tips/deep-learning-frameworks-survey-tensorflow-torch-theano-caffe-neon-ibm-machine-learning-stack (Accessed: 22nd October 2019).

Keras.io. (n.d.) Keras: The Python deep learning library. [Online] Available from: https://keras.io (Accessed: 22nd October 2019).

CS.toronto.edu. (n.d.) CIFAR-10 dataset of images. [Online] Available from: https://www.cs.toronto.edu/~kriz/cifar.html_ (Accessed: 22nd October 2019).

Abadi, M. (2016) TensorFlow: A System for Large-Scale Machine Learning. 12th USENIX Symposium on Operating Systems Design and Implementation. 33. pp. 25-33.

Duchi, J., Hazan, E., & Singer, Y. (2011) Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. Journal of Machine Learning Research. 12. pp. 2121-2159.

Kingma, D.P. (2015) Adam: a Method for Stochastic Optimization. In: Kingma, D.P. & Ba, J.L. (eds) Proc. Int. Conf. on Learning Representations. San Diego, USA. pp. 1-13.

ISPRS. (n.d.) 2D Semantic Labeling - Vaihingen dataset. [Online] Available from: http://www2.isprs.org/commissions/ comm3/wg4/2d-sem-label-vaihingen.html

Nguyen, V., Kim, H. & Jun, S. (2018) A Study on Real-Time Detection Method of Lane and Vehicle for Lane Change Assistant System Using Vision System on Highway. Engineering Science and Technology. pp. 822-833. DOI: 10.1016/j.jestch.2018.06.006

El-Khatib, S.A. (2015) Image segmentation using a mixed and exponential particle-based algorithm. Computer Science and Cybernetics. 1. pp. 126-133.

Koltsov, P.P. (2011) The use of metrics in a comparative study of the quality of work of image segmentation algorithms. Informatics and Its Applications. 5. pp. 53-634.