For today, autonomous UAVs are a combination of artificial intelligence, mechanical devices, and navigational instruments. To save computing resources and improve the quality of their navigation, motion control systems, recognition, etc., real-time UAV's video has to be preprocessed by segmentation or clustering algorithms. In this work, the analysis of parameters of effective graph-based (EGB) and pyramidal segmentation algorithms (PSA) was obtained for digital images of aerial photography. The authors used RGB, Lab, and HSV (BHS) color models. According to the results of testing EGB algorithm is faster, but its result of segmentation is ordinary. Whereas, PSA produces a result that is closer to human perception but its disadvantage is a long processing time. Authors recommended Lab and HBS formats of image, since their segmentation results are more effective than, for example, at RGB.
Segmentation of Digital Images of Aerial Photography
01.10.2019
849122 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
AERIAL PHOTOGRAPHY SYSTEM, AERIAL PHOTOGRAPHY METHOD, AND AERIAL PHOTOGRAPHY PROGRAM
Europäisches Patentamt | 2024
|Europäisches Patentamt | 2024
|3D AERIAL PHOTOGRAPHY SYSTEM EDITABLE 3D TARGET IMAGE OF DIGITAL AERIAL PHOTOGRAPHY INFORMATION
Europäisches Patentamt | 2021
|Aerial photography device and aerial photography method thereof
Europäisches Patentamt | 2015
|NTRS | 1985