DEVELOPMENT OF AN ALGORITHM FOR COMPRESSING AEROSPACE IMAGES FOR THE SUBSEQUENT RECOGNITION AND IDENTIFICATION OF VARIOUS OBJECTS

Sarinova A. Neftissov A. Rzayeva L. Yessenov A. Kirichenko L. Kazambayev I.
2024 Technology Center

Eastern-European Journal of Enterprise Technologies
2024 #3 Issue 2(129)83 - 94 pp.

The object of study is the recognition and identification of various objects in aerospace images. To solve the problems of compressing hyperspectral aerospace images with losses, the development of a compression algorithm is proposed. As a result, an algorithm has been developed for compressing aerospace images for subsequent recognition and identification of various objects using wavelet transform for processing high- and medium-resolution space images when monitoring from remote sensing satellites, based on the use of structural features of object images. In particular, orthogonal and wavelet transforms are presented, adapted for compression of hyperspectral aerospace images with losses, an adaptive discrete cosine transform algorithm is presented, followed by quantization with a loss level and compression. Thanks to a series of experiments on hyperspectral aerospace images, the effectiveness of the proposed algorithm in terms of the degree of compression, as well as the characteristics of the limits of its applicability, can be highlighted. The use of wavelets provides progressive compression of the bitstream, which makes it possible to achieve lossless compression with minimal loss of information due to the modified Huffman algorithm with a compression ratio of 9 more than 2.5 times in existing algorithms, as well as the quality metric of the restored images, the peak signal-to-noise ratio is sufficiently below 32.56. The developed compression algorithm demonstrates the effectiveness of its application in terms ofa setofcharacteristics andis superior to analogues. The scope and conditions for the practical use of the results obtained is a comparison of the proposed algorithm with the results of experiments obtained for universal compression algorithms for archivers and a compressor Copyright

compression , compression algorithm , Haar wavelet function , hyperspectral aerospace images , remote sensing , wavelet transform

Text of the article Перейти на текст статьи

Department of Intelligent Systems and Cybersecurity, Kazakhstan
Research and Innovation Center “Industry 4.0”, Kazakhstan
Astana IT University, Mangilik El ave., 55/11, Business center EXPO, block C1, Astana, 010000, Kazakhstan

Department of Intelligent Systems and Cybersecurity
Research and Innovation Center “Industry 4.0”
Astana IT University

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026