PDF

Abstract:
We propose a novel effective algorithm for real-time semantic segmentation of images that has the best accuracy in its class. Based on a comparative analysis of preliminary segmentation methods, methods for calculating attributes from image segments, as well as various algorithms of machine learning, the most effective methods in terms of their accuracy and performance are identified. Based on the research results, a modular near real-time algorithm of semantic segmentation is constructed. Training and testing is performed on the ISPRS Vaihingen collection of aerial photos of the visible and IR ranges, to which a pixel map of the terrain heights is attached. An original method for obtaining a normalized nDSM for the original DSM is proposed.

Keywords:
image analysis, pattern recognition, detection, classification, aerial images, DSM, superpixels, feature vector, semantic segmentation, machine learning, conditional random fields.

Citation:
Blokhinov YB, Gorbachev VA, Rakutin YO, Nikitin AD. A real-time semantic segmentation algorithm for aerial imagery. Computer Optics 2018; 42(1): 141-148. DOI: 10.18287/2412-6179-2018-42-1-141-148.

References:

1. Gorbachev VA. Dense terrain stereoreconstruction using modified SGM. Journal of Computer and Systems Sciences International 2014; 53(2): 212-223. DOI: 10.1134/S1064230714020105.
2. Verkeenko MS, Gorbachev VA. Development of dense models of the Earth’s surface based on the semiglobal matching method for the case of multiple overlapping images. Journal of Computer and Systems Sciences International 2017; 56(6): 997-1007. DOI: 10.1134/S1064230717060132.
3. Long J., Shelhamer E, Darrell T. Fully Convolutional Networks for Semantic Segmentation. IEEE Conference on Computer Vision and Pattern Recognition 2015: 3431-3440. DOI: 10.1109/CVPR.2015.7298965.
4. 2D Semantic labeling contest. – Source: <http://www2.isprs.org/commissions/comm3/wg4/semantic-labeling.html>
5. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 2012; 34(11): 2274-2281. DOI: 10.1109/TPAMI.2012.120.
6. Malik J, Belongie S, Leung T, Shi J. Contour and texture analysis for image segmentation. International Journal of Computer Vision 2001; 43(1): 7-27. DOI: 10.1023/A:1011174803800.
7. Ojala T, Pietikäinen M, Harwood DA. Comparative study of texture measures with classification based on feature distributions. Pattern Recognition 1996; 29(1): 51-59. DOI: 10.1016/0031-3203(95)00067-4.
8. Papageorgiou CP, Oren M, Poggio T. A general framework for object detection. Proceedings of International Conference on Computer Vision 1998: 555-562. DOI: 10.1109/ICCV.1998.710772.
9. Machine learning (K.V. Voroncov's lecture course). – Source: <http://www.machinelearning.ru/wiki/index.php?title=Машинное_обучение_%28курс_лекций%2C_К.В.Воронцов%29>.
10. Finley T, Joachims T. Training structural SVMs when exact inference is intractable. Proceedings of the 25th international conference on Machine learning 2008: 304-311. DOI: 10.1145/1390156.1390195.
11. Kolmogorov V, Rother C. Minimizing non-submodular functions with graph cuts – A review. IEEE Transactions on Pattern Analysis and Machine Intelligence 2007; 29(7): 1274-1279. DOI: 10.1109/TPAMI.2007.1031.
12. Müller AC, Behnke S. PyStruct Structured prediction in Python. Journal of Machine Learning Research 2014; 15(1): 2055-2060.
13. Cramer M. The DGPF – Test on digital aerial camera evaluation overview and test design. Photogrammetrie – Fernerkundung – Geoinformation 2010; 2: 73-82. DOI: 10.1127/1432-8364/2010/0041.
14. Evaluierung digitaler photogrammetrischer luftbildkamerasysteme. Source: <http://www.ifp.uni-stuttgart.de/dgpf/DKEP-Allg.html>.

---

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20