Construction of rural landscape design system based on support vector machine and mean drift algorithm

Abstract

With the theory of beautiful China, the construction and planning of rural landscapes are getting more and more attention. However, China’s rural landscape design lacks innovation and practicality. Therefore, in order to avoid the homogeneity of rural landscape design, it is necessary to ensure that rural landscape designs are consistent with the sustainable development of the rural area system. The study is based on the vector machine and the mean shift algorithm in remote sensing control for the segmentation and feature extraction of architectural images, using the function weight addition and the introduction of background suppression factor, to develop a model and algorithms that are more suitable for the diversified features of the buildings. The results indicate that the research method has a maximum accuracy of 99% in extracting architectural images, and the image quality evaluation can reach 100%. In the application analysis, it was found that the economic benefit of unused land in the countryside was low, and the green conservation information of ancient villages in the landscape was 57.3%. Therefore, the model designed by the study has good integrity for architectural image feature extraction, good accuracy, high image quality, and good application value for countryside landscape design.

Keywords

rural landscapes landscape design background suppression image feature extraction vector machine mean shift algorithm function weight

Get full access to this article

View all access options for this article.

References

Nengem

. Symmetric kernel-based approach for elliptic partial differential equation. J Data Sci Inte System 2023; 1(2): 99–104.

Chinthamu

Karukuri

. Data science and applications. J Data Sci Inte System 2023; 1(1): 83–91.

Kumar

VTRP

Arulselvi

Sastry

KBS

. Comparative assessment of colon cancer classification using diverse deep learning approaches. J Data Sci Inte System 2023; 1(2): 128–135.

. A writer-dependent approach to offline signature verification based on one-class support vector machine. Pattern Recognit Image Anal 2024; 34(2): 340–351.

Yalcinkaya

Coruk

Kara

, et al. Hierarchical classification of analog and digital modulation schemes using higher-order statistics and support vector machines. Wirel Pers Commun 2024; 136(2): 827–847.

Ildikó

Klaus

Endre

. The role of a landscape rehabilitation student project in current landscape education - healing urbanization’s footprint. Acta Biologica Marisiensis 2023; 6(2): 100–112.

S Bhattacharyya

Majumder

Debnath

, et al. Arrhythmic heartbeat classification using ensemble of random forest and support vector machine algorithm. IEEE Trans Artif Intell 2021; 2(3): 260–268.

Tayana

Zsombor

. Pilot landscape and design-based programme to foster student environmental literacy. Acta Universitatis Sapientiae. Agric Environ 2023; 15(1): 1–12.

Eldeeb

Shehab

Alves

. A learning-based fast uplink grant for massive IoT via support vector machines and long short-term memory. IEEE Internet Things J 2021; 9(5): 3889–3898.

10.

DuchŻebrowska

Kurkowska

Wróblewska

. Nature and heritage - Sustainable Development Goals (SDG) as factors of social integration in the space of housing estates. Study of Zaspa. Środowisko Mieszkaniowe/Housing Environment 2023; 43(2): 31–43.

11.

Chakraborty

Paul

Das

. Automated clustering of high-dimensional data with a feature weighted mean shift algorithm. Proc AAAI Conf Artif Intell 2021; 35(8): 6930–6938.

12.

Bhat

Subudhi

Veerakumar

, et al. Target tracking using a mean-shift occlusion aware particle filter. IEEE Sens J 2021; 21(8): 10112–10121.

13.

Ganji

Minet

Weichenthal

, et al. Predicting traffic-related air pollution using feature extraction from built environment images. Environ Sci Technol 2020; 54(17): 10688–10699.

14.

Maarten

Floor

Maria

. Heritage contestation in matterscape, mindscape, and powerscape. Landsc Res 2023; 48(8): 1041–1053.

15.

Ding

Bruzzone

. DiResNet: Direction-aware residual network for road extraction in VHR remote sensing images. IEEE Trans Geosci Remote Sens 2020; 59(12): 10243–10254.

16.

Vincent

Raphael

Alexandre

. Water use efficiency across scales: from genes to landscapes. J Exp Bot 2023; 74(16): 4770–4788.

17.

Heo

Rajan

Khawaja

, et al. Machine learning approach to predict venous thromboembolism among patients undergoing multi-level spinal posterior instrumented fusion. J Spine Surg 2024; 10(2): 214–223.

18.

Barrios

MLC

Lima

EVR

. Influence of forest proportion and configuration at the watershed and riparian zone scales on sediment yield: a simulation experiment. Landsc Ecol 2023; 38(11): 2839–2860.

19.

Amir

Alireza

. Classifying random variables based on support vector machine and a neural network scheme. J Exp Theor Artif Intell 2024; 36(5): 679–702.

20.

Bukkarapu

Krishnasamy

. Biodiesel composition based machine learning approaches to predict engine fuel properties. Proc Inst Mech Eng - Part D J Automob Eng 2024; 238(7): 1844–1860.