|
This article is cited in 11 scientific papers (total in 11 papers)
IMAGE PROCESSING, PATTERN RECOGNITION
The hybrid CPU/GPU implementation of the computational procedure for digital terrain models generation from satellite images
V. A. Fursovab, E. V. Goshinab, A. P. Kotovab a Samara National Research University, Samara, Russia
b Image Processing Systems Institute îf RAS – Branch of the FSRC “Crystallography and Photonics” RAS, Samara, Russia
Abstract:
In this paper a procedure of building a digital terrain model (DTM) from the satellite images is researched. The procedure is based on the authors' previously developed algorithms of fast image matching for building disparity maps implemented on GPUs (Graphics Processing Units). In this paper we propose a computational procedure for constructing a DTM from the satellite stereo images. Experimental studies have shown that while this procedure constructs a DTM that may be less accurate than the one achieved with the use of the ENVI software, it offers a significantly shorter time of processing.
Keywords:
digital image processing, stereo images, 3D-scene reconstruction, image matching, CUDA-technology, ENVI.
Received: 17.07.2016 Accepted: 31.10.2016
Citation:
V. A. Fursov, E. V. Goshin, A. P. Kotov, “The hybrid CPU/GPU implementation of the computational procedure for digital terrain models generation from satellite images”, Computer Optics, 40:5 (2016), 721–728
Linking options:
https://www.mathnet.ru/eng/co293 https://www.mathnet.ru/eng/co/v40/i5/p721
|
Statistics & downloads: |
Abstract page: | 145 | Full-text PDF : | 69 | References: | 40 |
|