Construction of Object Boundaries for the Autopilotof a Surface Robot from Satellite Imagesusing Computer Vision Methods

TL;DR

This paper presents a computer vision-based algorithm for detecting water body boundaries in satellite images, enabling surface robot autopilots to navigate more accurately by identifying water boundaries and converting them into GPS coordinates.

Contribution

It introduces a novel method combining color detection, image filtering, and contour operators to accurately identify water boundaries and generate GPS coordinates for robot navigation.

Findings

Sobel operator provides the most accurate boundary detection.

The algorithm successfully converts contours into GPS coordinates.

The method improves boundary detection accuracy for surface robots.

Abstract

An algorithm and a program for detecting the boundaries of water bodies for the autopilot module of asurface robot are proposed. 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 operators of Sobel,Roberts, Prewitt, and from them the one that detects the boundary more accurately is selected for thismodule. 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.