Algorithm for Creating 3d Scenes of Recognized Objects from Depth Maps-Reference-Cited by-同舟云学术

Algorithm for Creating 3d Scenes of Recognized Objects from Depth Maps

Published:2023-12-19 Issue:2 Volume:27 Page:90-104
ISSN:2686-6757
Container-title:Proceedings of the Southwest State University
language:
Short-container-title:Proceedings of the SWSU

Author:

Bobyr M. V.¹^ORCID,Emelyanov S. G.¹^ORCID,Milostnaya N. A.¹^ORCID

Affiliation:

1. Southwest State University

Abstract

Purpose of research. Development of an algorithm for constructing 3d scenes of recognized objects from synthesized depth maps in order to improve the speed of real-time image processing.Methods. The 3d scene construction algorithm is based on the method of stereo image construction using a threelevel fuzzy depth map construction model. At the first level of this model the boundaries of objects are determined using a modified Canny algorithm, at the second level the values of disparity are calculated on the basis of the sum of absolute differences algorithm modified by fuzzy logic methods, and at the final level the gradients of distances from the boundaries of images to the edges of recognized objects are calculated first and then according to the obtained values of disparity at the second and third levels of the fuzzy hierarchical model, the refined values of disparity are calculated, which are used to carry out the analysis of the depth map.Results. An algorithm for constructing 3d scenes of recognized objects using synthesized depth maps has been developed. It was determined that the proposed algorithm has better performance compared to existing depth map algorithms such as conjugate point algorithm and pyramidal algorithm.Conclusion. The experimental results showed that the proposed algorithm has a lower complexity compared to the analyzed algorithms (conjugate points and pyramidal). The minimum average execution time of the 3d scene construction operation was about 1-2 minutes, which is almost 120 times better compared to the conjugate point algorithms.

Publisher

Southwest State University

Subject

General Earth and Planetary Sciences,General Engineering,General Environmental Science

Reference24 articles.

1. Elhashash M., Qin R. Cross-view SLAM solver: Global pose estimation of monocular ground-level video frames for 3D reconstruction using a reference 3D model from satellite images. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 188, 62–74. https://doi.org/10.1016/j.isprsjprs.2022.03.018

2. Bobyr M., Arkhipov A., Emelyanov S., Milostnaya N. A method for creating a depth map based on a three-level fuzzy model. Engineering Applications of Artificial Intelligence, 2023, 117. https://doi.org/10.1016/j.engappai.2022.105629

3. Avrashkov P. P., Kos'kin N. A., Konstantinov I. S. Otsenka effektivnosti raz-lichnykh modelei konvertatsii izobrazhenii v stereoformat s pomoshch'yu kart glubiny. Nauchno-tekhnicheskii vestnik Povolzh'ya = Scientific and Technical Volga Region Bulletin, 2020, no. 12, pp. 165-168.

4. Potapov A. A., Gulyaev Yu. V., Nikitov S. A. Noveishie metody obrabotki izobrazhenii [Latest Image Processing Techniques]. Moscow, Fiziko-matematicheskaya literatura Publ., 2008, 496 p.

5. Gusev V. V. [Assessment of the accuracy of correlation matching algorithms and algorithms for obtaining pyramidal representation of images]. Sfera znanii: strukturnye preobrazovaniya i perspektivnye napravleniya razvitiya nauchnoi mysli [Field of knowledge: structural transformations and promising directions for the development of scientific thought]. Kazan', OOO "SitIvent" Publ., 2018, pp. 308-311 (In Russ.).