Algorithm to find the shape of objects from the analysis of data obtained in the infrared range

Authors: Zelenskiy A. A., Semenischev E. A., Frants V. A.

Annotation: In this paper, we consider algorithms for preprocessing images obtained in the infrared range and reconstructing the contours of objects. The application of these approaches provides an approximate idea of the form of objects, in the absence of information obtained in the optical range. As the approaches used for primary data processing, the following algorithms are used: filtering and blurring the image; threshold binarization; detection of the boundaries of temperature changes. The algorithm for filtering and blurring the image is based on a multicriteria method. The algorithm of threshold binarization is based on threshold processing. The algorithm to find the boundary of an object is based on the application of a mathematical approach for finding an equidistant curve. The article presents block diagrams of algorithms and their mathematical description. The set of test images shows the effectiveness of the proposed approach used to find the shape of objects from the analysis of data obtained in the infrared range.

Keywords: thermal imaging, filtering, equidistant curve, infrared, border detector