Plant Configuration Method of Landscape Architecture Based on Neural Network

Authors

  • Qian Wang School of International Exchange, Shandong Polytechnic, Jinan 250104, China

Abstract

Plant characteristics and color quantification are not considered in the configuration of plants in a landscape, resulting in poor rationality and less aesthetic appeal. Therefore, to address these two issues, in this paper, a landscape plant configuration method is proposed based on a neural network. This method involves: determining the principle of landscape plant configuration, extracting the green plant characteristics in landscape plant configuration using the scale-invariant feature transform (SIFT) algorithm, determining the floral characteristics bymeans of a cluster shape index, and combining the characteristics of the green plants and flowers in order to derive the plant characteristics of landscape plant configuration. The color of the plant landscape is divided using the SBE (Beauty analysis method) method, and the quantitative indexes of plant color are determined; these are: plant landscape hue index, color saturation, color lightness index and plant color uniformity. The quantitative index is calculated to determine the plant color in a landscaped garden. Through the pre-training of data on landscape garden plant configuration, the plant data in each layer of neurons are updated. Using MMD measurement, the overall mean value of two different fields is calculated to determine the loss function. Then, the landscape garden plant configuration model is constructed with the help of a neural network, and the source domain and target domain are further modified to achieve the final landscape garden plant configuration. The experimental results show that the proposed method can effectively improve the rationality of plant configuration and enhance the aesthetic appeal of the landscape.

Keywords: neural network, landscape architecture, plant configuration, SIFT algorithm, SBE method, color quantization.

Cite As

Q. Wang, "Plant Configuration Method of Landscape Architecture Based on Neural Network", Engineering Intelligent Systems,
vol. 31 no. 2, pp. 81-91, 2023.






Downloads

Published

2023-03-01

Issue

Vol. 31 No. 2 (2023): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.