IMAGE SEGMENTATION AND OBJECT SELECTION BASED ON MULTI-THRESHOLD PROCESSING
https://doi.org/10.32603/1993-8985-2019-22-3-24-35
Abstract
Introduction. In order to automate data processing in remote observation systems using television and infrared cameras, synthetic aperture panoramic radars, as well as laser and acoustic systems, it is essential to be able to reliably detect, isolate, select and localise objects of various shapes in images.
Objective. The development of a methodology based on multi-threshold analysis.
Materials and methods. The developed image segmentation and object selection approach having optimal selection threshold assessment is based on the results of multi-threshold image analysis.
Results. Based on the analysis of a series of standard objects with known shapes hindered by synthetic noise, as well as representative examples of remotely sensed images of the Earth’s surface, improvements in the characteristics of both entire image segmentation and selection of particular objects according to several objective criteria were achieved.
Conclusion. The main advantage of the proposed approach consists in the minimisation of the post-processing shape modification of the selected objects. Although this is achieved at the cost of the resource-consuming multi-threshold analysis procedure for each processed image, this can be also partially compensated by the simplicity of the algorithm and its possible parallel implementation.
Keywords
multi-threshold processing,
image segmentation,
object selection,
binary integration method,
statistical modelling
Supporting agencies: This work was supported by the Russian Science Foundation (research project № 16-19-00172- П).
About the Authors
Vladimir Yu. Volkov
Saint Petersburg State University of Aerospace Instrumentation
Russian Federation
Russian Federation
Vladimir Yu. Volkov – Dr. of Sci. (Engineering) (1993), Professor (1995) of the Department of Radio Engineering Systems of Saint Petersburg Electrotechnical University "LETI. The author of 200 scientific publications. Area of expertise: image processing in computer vision systems; reception under a priori uncertainty conditions.
67, Bolshaya Morskaya Str., 190000, St. Petersburg
Oleg A. Markelov
Saint Petersburg Electrotechnical University "LETI"
Russian Federation
Russian Federation
Oleg A. Markelov – Cand. of Sci. (Engineering) (2014), Associate Professor of the Department of Radio Engineering Systems of Saint Petersburg Electrotechnical University "LETI". The author of more than 50 scientific publications. Area of expertise: statistical analysis of time series.
5, Professor Popov Str., 197376, St. Petersburg
Mikhail I. Bogachev
Saint Petersburg Electrotechnical University "LETI"
Russian Federation
Russian Federation
Mikhail I. Bogachev – Cand. of Sci. (Engineering) (2006), Associate Professor (2011), Leading Scientist of the Department of Radio Equipment Systems of Saint Petersburg Electrotechnical University "LETI". The author of 150 scientific publications Area of expertise: complex systems theory; statistical data analysis.
5, Professor Popov Str., 197376, St. Petersburg
References
1. Gonsales R., Vuds R. Tsifrovaya obrabotka izobrazhenii [Digital image processing]. Moscow, Tekhnosfera, 2005, 1104 p. (In Russ.)
2. Blaschke T. Object Based Image Analyses for Remote Sensing. ISPRS J. of Photogrammetry and Remote Sensing. 2010, vol. 65, iss. 1, pp. 2–16. doi: 10.1016/j.isprsjprs.2009.06.004
3. Lang S., Baraldi A., Tiede D., Hay G., Blaschke T. Towards a (GE)OBIA 2.0 Manifesto-Achievements and Open Challenges in Information & Knowledge Extraction from Big Earth Data. GEOBIA'2018, Montpellier, 18–22 June, 2018. Basel: MDPI AG. P.
4. Gao G. Statistical Modeling of SAR Images: A Survey. Sensors. 2010, vol. 10, no 1, pp. 775–795. doi: 10.3390/s100100775
5. Zhou W., Troy A. An Object-Oriented Approach for Analyzing and Characterizing Urban Landscape at the Parcel Level. Int. J. of Remote Sensing, 2008, vol. 29, no. 11, pp. 3119–3135. doi: 10.1080/01431160701469065
6. Gu H., Han Y., Yang Y., Li H., Liu Z., Soergel U., Blaschke T., Cui S. An Efficient Parallel Multi-Scale Segmentation Method for Remote Sensing Imagery. Remote Sensing. 2018, vol. 10, no. 4, pp. 590(1–18). doi: 10.3390/rs10040590
7. Cheng J., Tsai Y., Hung W., Wang S., Yang M. Fast and Accurate Online Video Object Segmentation via Tracking Parts / // Proc. of the 2018 IEEE Conf. on Computer Vision and Pattern Recognition. 18–23 June 2018, Salt Lake City. Piscataway, IEEE, 2018, pp. 7415–7424. doi: 10.1109/CVPR.2018.00774
8. Wang M. A. Multiresolution Remotely Sensed Image Segmentation Method Combining Rainfalling Watershed Algorithm and Fast Region Merging. Int. Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2008, vol. XXXVII, Pt. B4, pp. 1213–1217.
9. Arora S., Acharya J., Verma A., Panigrahi P.K. Multilevel thresholding for image segmentation through a fast statistical recursive algorithm. Pattern Recognition Letters. 2008, vol. 29, iss. 2, pp. 119–125. doi: 10.1016/j.patrec. 2007.09.005
10. Yang J., Yang Y., Yu W., Feng J., Yang J. MultiThreshold Image Segmentation based on K-means and Firefly Algorithm. Proc. of 3rd Int. Conf. on Multimedia Technology (ICMT-13). Paris: Atlantis Press, 2013, pp. 134–142. doi: 10.2991/icmt-13.2013.17
11. Priyanka P., Vasudevarao K., Sunitha Y., Sridhar B. A. Multi Level Fuzzy Threshold Image Segmentation Method for Industrial Applications. IOSR J. of Electronics and Communication Engineering (IOSR-JECE), 2017, vol. 12, iss. 2, ver. III, pp. 06–17. doi: 10.9790/2834-1202030617
12. Banimelhem O., Yahya A. Y. Multi-Thresholding Image Segmentation using Genetic Algorithm. Proc. IPCV, 16–19 July 2012, Las-Vegas, Las-Vegas: CSREA, 2012. URL: http://worldcomp-proceedings.com/proc/p2011/IPC8346.pdf (accessed 11.06.2019)
13. Cuevas E., González A., Fausto F., Zaldívar D., Pé- rez-Cisneros M. Multithreshold Segmentation by Using an Algorithm Based on the Behavior of Locust Swarms. Hindawi Publishing Corporation. Mathematical Problems in Engineering, vol. 2015, art. ID 805357 (1–25). doi: 10.1155/2015/805357
14. Volkov V. Extraction of Extended Small-Scale Objects in Digital Images. The ISPRS Archives. 2015, vol. XL-5/W6, pp. 87–93. doi: 10.5194/isprsarchives-XL-5-W6-87-2015
15. Bogachev M., Volkov V., Kolaev G., Chernova L., Vishnyakov I., Kayumov A. Selection and Quantification of Objects in Microscopic Images: from Multi-Criteria to Multi-Threshold Analysis. Bionanoscience. 2019, vol. 9, iss. 1, pp. 59–65. doi: 10.1007/s12668-018-0588-2
16. Klyuev N. F. Obnaruzhenie impul'snykh signalov s pomoshch'yu nakopitelei diskretnogo deistviya [Detection of Pulse Signals Using Discrete Action Drives.]. Moscow, Sov. Radio, 1963, 111 p. (In Russ.)
17. Volkov V. Yu. Adaptive Extraction of Small Objects in Digital Images. Journal of the Russian Universities. Radioelectronics. 2017, no. 1, pp. 17–28. (In Russ.)
Review
For citations:
Volkov V.Yu., Markelov O.A., Bogachev M.I. IMAGE SEGMENTATION AND OBJECT SELECTION BASED ON MULTI-THRESHOLD PROCESSING. Journal of the Russian Universities. Radioelectronics. 2019;22(3):24-35. https://doi.org/10.32603/1993-8985-2019-22-3-24-35
Views:
1261
Email this article 