Title: Research on spatial pattern recognition of landscape architecture based on multi-source remote sensing images

Authors: Shujing Wang

Addresses: School of Art and Design, Jilin University of Architecture and Technology, Changchun, 130114, China

Abstract: In order to overcome the low recall rate, peak signal-to-noise ratio and correct recognition rate of spatial pattern in traditional spatial pattern recognition methods, a landscape spatial pattern recognition method based on multi-source remote sensing images was proposed. First, we obtain multi-source remote sensing images of landscape architecture, use ORB algorithm to extract multi-source remote sensing image feature points, and fuse multi-source remote sensing images. Then, MSRCR algorithm is used to enhance the fused image, LOG edge detection operator is used to obtain the image edge, and MCR model is used to determine the landscape patch characteristics. Finally, the spatial pattern recognition model of landscape architecture is built, and the spatial pattern recognition results are obtained. The experimental results show that the maximum recall rate of this method is 97%, the maximum peak signal to noise ratio of image is 59.3 dB, and the correct recognition rate varies from 97% to 99%.

Keywords: multi-source remote sensing image; landscape architecture; spatial pattern recognition; MSRCR algorithm; LOG edge detection calculation; MCR model.

DOI: 10.1504/IJETM.2024.138202

International Journal of Environmental Technology and Management, 2024 Vol.27 No.3, pp.216 - 231

Received: 17 Jan 2023
Accepted: 27 Mar 2023
Published online: 30 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article