Environmental landscape art design based on visual neural network model in rural construction

• Autorzy: Wang Lu-Yao , He Yi-Ping

Identyfikatory

DOI

10.2478/eces-2023-0028

• Języki publikacji: EN

Abstrakty

EN

As the resources of social development continue to tilt to the countryside, the speed of rural construction continues to accelerate. In recent years, because of the higher quality of lifestyles, the demand of rural environment landscape art has gradually increased. In order to assist rural construction and improve the artistic quality of its environmental landscape, this paper proposes an environmental landscape art design method based on a visual neural network model. Firstly, the Swin Transformer text encoder is used to characterise the landscape art demand in rural construction. Then, the text feature vector of landscape art demand is input into the GAN model to generate the image content of rural construction. Finally, to better evaluate the landscape art level of the above methods in this paper, we propose an evaluating method for the landscape designing tasks. We conduct the experiments and achieve the FID value of 15.23, which can demonstrate that our method can effectively carry out an environmental landscape design for rural construction and simplify the process of rural construction. The landscape design evaluation method can evaluate the environmental landscape design accurately by the accuracy of over 80 %, and further improve and optimise the acceptance link of rural construction.

Słowa kluczowe

EN

rural construction; environmental landscape; design; neural network; evaluation method

PL

budownictwo wiejskie; krajobraz środowiska; projektowanie; sieć neuronowa; metoda oceny

• Wydawca: Towarzystwo Chemii i Inżynierii Ekologicznej
• Czasopismo: Ecological Chemistry and Engineering. S
• Rocznik: 2023
• Tom: Vol. 30, nr 2
• Strony: 267--274
• Opis fizyczny: Bibliogr. 15 poz., rys., tab.

Twórcy

autor

Wang Lu-Yao

• Department of Environmental Art Design, Shaanxi Fashion Engineering University, Xi’an 712000, Shaanxi, China

• https://orcid.org/0009-0005-2664-8969

autor

He Yi-Ping

• BasicTeach Office, Shaanxi Fashion Engineering University, Xi’an 712000, Shaanxi, China

• https://orcid.org/0009-0003-8649-4901

Bibliografia

• [1] Wu CH, Tsai SB, Liu W, Shao XF, Xia YK, Wacławek M. Green environment and sustainable development: methods and applications. Ecol Chem Eng S. 2021;28(4):467-70. DOI: 10.2478/eces-2021-0030.
• [2] Liu W, Tsai SB, Wu CH, Shao X, Wacławek M. Corporate environmental management and sustainable operation: theory and application. Ecol Chem Eng S. 2022;29(3):283-5. DOI: 10.2478/eces-2022-0020.
• [3] Domon G. Landscape as resource: Consequences, challenges and opportunities for rural development. Landscape Urban Planning. 2011;100(4):338-40. DOI: 10.1016/j.landurbplan.2011.02.014.
• [4] Lafortezza R, Brown RD. A framework for landscape ecological design of new patches in the rural landscape. Environ Manage. 2004; 34:461-73. DOI: 10.1007/s00267-002-2009-z.
• [5] Peng L. Intelligent landscape design and land planning based on neural network and wireless sensor network. J Intelligent Fuzzy Systems. 2021;40(2):2055-67. DOI: 10.3233/jifs-189207.
• [6] Creswell A, White T, Dumoulin V. Generative adversarial networks: an overview. IEEE Signal Processing Magazine. 2018;35(1):53-65. DOI: 10.1109/MSP.2017.2765202.
• [7] Goodfellow I, Pouget-Abadie J, Mirza M. Generative adversarial nets. Advances in Neural Information Processing Systems. 2014;2672-80. DOI: 10.1007/978-3-658-40442-0_9.
• [8] Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. IEEE/CVF Conf Computer Vision Pattern Recognition. 2019;4401-10. DOI: 10.1109/cvpr.2019.00453.
• [9] Park T, Liu MY, Wang TC. Semantic image synthesis with spatially-adaptive normalization. IEEE/CVF Conf Computer Vision Pattern Recognition. 2019;2337-46. DOI: 10.1109/cvpr.2019.00244.
• [10] Sauer A, Schwarz K, Geiger A. Stylegan-xl:scaling stylegan to large diverse datasets. ACM SIGGRAPH 2022. Conf Proc. 2022;1-10. DOI: 10.1145/3528233.3530738.
• [11] Huang GB, Saratchandran P, Sundararajan N. An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks. IEEE Trans Systems, Man, Cybernetics, Part B (Cybernetics). 2004;34(6):2284-92. DOI: 10.1109/TSMCB.2004.834428.
• [12] Zhang H, Xu T, Li HS, Zhang ST, Wang XG, Huang XL, et al. StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks. IEEE/CVF Int Conf Computer Vision. 2017;5908-16. DOI: 10.1109/ICCV.2017.629.
• [13] Xu T, Zhang PC, Huang QY, Zhang H, Gan Z, Huang XL, et al. AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks. IEEE/CVF Conf Computer Vision Pattern Recognition. 2018;1316-24. DOI: 10.1109/CVPR.2018.00143.
• [14] Zhu MF, Pan PB, Chen W, Yang Y. DM-GAN: Dynamic memory generative adversarial networks for text-to-image synthesis. IEEE/CVF Conf Computer Vision Pattern Recognition. 2019;5795-803. DOI: 10.1109/CVPR.2019.00595.
• [15] Xu Q, Guan X, Cao J, Ma Y, Wu H. MPR-GAN: A novel neural rendering framework for MLS point cloud with deep generative learning. IEEE Trans Geosci Remote Sensing. 2022;60(5704916):1-16. DOI: 10.1109/TGRS.2022.3212389.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).