Construction of object boundaries for the autopilot of a surface robot from satellite images using computer vision methods

by

A.N. Grekov1,2, Y.E. Shishkin1, S.S. Peliushenko1, A.S. Mavrin1,2

1Institute of Natural and Technical Systems, RF, Sevastopol, Lenin St., 28

2Sevastopol State University, RF, Sevastopol, Universitetskaya St., 33

E-mail: iurii.e.shishkin@gmail.com

DOI: 10.33075/2220-5861-2021-3-107-118

UDC 681.3    

Abstract:

   In recent years, technological development and a fast rate of population growth have led to an increase in anthropogenic pressure and the level of human resource use, resulting in climatic changes. This has caused significant negative trends in the state of the natural environment, hydrosphere and atmosphere. Surface water bodies like rivers, lakes, seas and oceans are some of the key backbone elements.

   In fact, there is currently no continuous monitoring of water bodies, which would reveal changes in their physico-chemical parameters and areas. To carry out such monitoring, it is proposed to use an unmanned surface robot.

   In our work, we investigate an algorithm for constructing maps for the autopilot of a surface robot based on satellite images of the terrain using computer vision methods.

   The solution to similar problems has been considered by many authors. They proposed several methods for detecting water bodies, such as multispectral index methods, morphological methods, and others. Also, for the implementation of the method for detecting the boundaries of water bodies in the image, there are many different algorithms that have different efficiency for different target tasks.

   In our article, we propose an algorithm and a program for detecting the boundaries of water bodies for the autopilot module of a surface robot. A method for detecting water objects on satellite maps by the method of finding a color in the HSV color space, using erosion, dilation – methods of digital image filtering is applied. The following operators for constructing contours on the image are investigated: the Sobel, Roberts, Prewitt operators, and from them, the one that detects the boundary more accurately is selected for this module. An algorithm for calculating the GPS coordinates of the contours is created. The proposed algorithm allows saving the result in a format suitable for the surface robot autopilot module.

Keywords: Water bodies, satellite maps, boundaries detection, environmental control, erosion, dilatation, Sobel, Roberts, Prewitt operators, GPS coordinates.

To quote:

Full text in PDF(RUS)

REFERENCES

  1. Kataev M.Y., and Bekerov A.A. Metodyka obnarugeni’a vodnuh ob’ektov po mnogostupenchatum sputnikovum ismereniyam (Method for detecting water bodies using multispectral satellite measurements). Doklady tomskogo gosudarstvennogo universiteta sistem upravlenija i radiojelektroniki, 2017, Vol. 20, No. 4, pp. 105–108. DOI: 10.21293/1818-0442-2017-20-4-105-108
  2. Shishkin Ju.E., and Grekov A.N. Koncepcija intellektual’noj sistemy avtomatizirovannogo jekologicheskogo monitoringana baze malogabaritnyh avtonomnyh robotov Sistemy kontrolja okruzhajushhej sredy. (The concept of an intelligent automated environmental monitoring system based on small-sized autonomous robots). Monitoring systems of environment, 2018, No. 14 (34), pp. 63–69. DOI: 10.33075/2220-5861-2018-4-63-69
  3. Shishkin I.E., Grekov A.N., and Nikishin V.V. Intellektual’naja sistema podderzhki prinjatija reshenij dlja obnaruzhenija anomalij i korrekcii inercial’noj navigacii bespilotnyh nazemnyh transportnyh sredstv (Intelligent Decision Support System for Detection of Anomalies and Unmanned Surface Vehicle Inertial Navigation Correction). Materialy Mezhdunarodnoj Rossijskoj konferencii po avtomatizacii 2019 goda, RusAutoCon 2019, Vol. 1, pp. 1–6. DOI:10.1109/rusautocon.2019.8867601
  4. Shishkin I.E., Grekov A.N., and Grekov N.A. A multi-model system of intelligent unmanned surface vehicles for environmental monitoring. Mezhdunarodnaja mnogoprofil’naja konferencija po promyshlennomu inzhiniringu i sovremennym tehnologijam, FarEastCon 2019, pp. 1–6. DOI:10.1109/FarEastCon.2019.8934037
  5. Shishkin Yu.E. Kompleksnyj podhod k postroeniju kart na osnove sputnikovyh izobrazhenij dlja provedenija monitoringovyh nabljudenij za morskoj akvatoriej (An ensemble approach to constructing maps based on satellite images for conducting monitoring observations of marine aquatics). Monitoring systems of environment – 2020, tezisy dokladov Mezhdunarodnoj nauchno-tehnicheskoj konferencii, 2020, p. 23.
  6. Balandin D.V., and Kogan M.M. Sintez zakonov upravlenija na osnove linejnyh matrichnyh neravenstv (Synthesis of control laws based on linear matrix inequalities). Moscow. 2007, 280 p.
  7. Algazinov E.K., and Sirota A.A. Analiz i komp’juternoe modelirovanie in-formacionnyh processov i sistem: Prikladnaja informatika (Analysis and computer modeling of information processes and systems: Applied informatics). Moscow: Dialog-MEPhI. 2009, 416 p.
  8. Tomakova R.A., and Filist S.A. Metod obrabotki i analiza slozhnostrukturiruemyh izobrazhenij na osnove vstroennyh funkcij sredy matlab (Method of processing and analysis of complex structured images based on the built-in functions of the matlab environment). Bulletin of the Trans-Baikal State University, 2012, No. 1 (80), pp. 3–9.
  9. Gonzalez R. Cifrovaja obrabotka izobrazhenij (Digital image processing). Moscow: Technosphere, 2009. 1104 p.
  10. Hao Jiang, Min Feng, and Yunqiang Zhu. An Automated Method for Extracting Rivers and Lakes from Landsat Imagery (An Automated Method for Extracting Rivers and Lakes from Landsat Imagery). Remote Sens., 2014, No. 6, pp. 5067–5089. DOI:10.3390/rs6065067
  11. Rishikeshan C.A., and Ramesh H. An automated mathematical morphology driven algorithm for water body extraction from remotely sensed images. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, Vol. 146, pp. 11–21.
  12. AlMaazmi Alya. Water bodies extraction from high resolution satellite images using water indices and optimal threshold. Proc. SPIE No. 10004, Image and Signal Processing for Remote Sensing, 18 October 2016, Vol. XXII, No. 100041J.
  13. Ranjay Shrestha, and Liping Di. Land/Water Detection and Delineation with Landsat Data using MatLab/ENVI. Agro-Geoinformatics, 2013 Second International Conference on DOI:10.1109/ Argo-Geoinformatics.2013.6621909
  14. Pantileikina T.P., and Moskaleva S.A. The use of SASPlanet and GoogleEarth software tools in the educational processDevelopment of regions in the XXI century (The use of SASPlanet and GoogleEarth software tools in the educational processDevelopment of regions in the XXI century): a collection of materials of the I International. scientific conf. North Ossetian State. K. L. Khetagurov University, 2013, pp. 374–379.
  15. Tomakova R.A., and Filist S.A. Metod obrabotki i analiza slozhnostrukturiruemyh izobrazhenij na osnove vstroennyh funkcij sredy matlab (Method of processing and analysis of complex structured images based on built-in functions of the matlab environment). Bulletin of the Trans-Baikal State University, 2012, Vol. 1 (80), pp. 3–9.
  16. Gonzalez R. Cifrovaja obrabotka izobrazhenij (Digital image processing). Moscow: Technosphere, 2012. 1101 p.
  17. Algorithms for selecting contours in an image / electronic resource // https://habr.com/ru/post/114452/ // (accessed: 18.06.2021).

 

Loading