Computer Simulation of Rural Landscape Design Based on Remote Sensing Image Technology

Introduction: The field of rural landscape design deals with the design and recovery of rural areas and landscape in a way that it can support natural biodiversity in addition to human needs in sustainable ways as well as maintaining its cultural character. It employs the use of plants, landforms and some water without interference with the environment in order to come up with useful and beautiful spaces. Recognizing the importance of preserving the environment while at the same time investing in developmental projects, it is centralized and focuses on the entire eco-system with the aim of enhancing the lives of the people. Aim: This study aims to develop theoretical aspect of an innovative computer simulation model for designing rural landscapes by applying the technology of remote sensing image. Research methodology: We suggest a new Starling Murmuration search-driven Adaptive YOLOv7 algorithm to identify and categorize several rural buildings and setting types. For the image data, we collected abundant data from several environments using UAV devices to train our proposed model. It is not surprising that our proposed model combined the use of three dimensional (3D) geographic information system (GIS) virtual imaging design model in the simulation of the rural landscape designs. Our recommended model is then extended using SM optimization to improve object detection with YOLOv7. By repeated adjustments of the network parameters in a somewhat similar fashion like flocking, we managed to enhance both accuracy and efficiency. This framework exploits crowdsourcing for delimiting rural buildings and landscapes with high-fidelity. Findings and Conclusion: We implemented our recommended model in Python software. During the phase of evaluation, we evaluate the efficacy of our recommended SM-AYOLOv7 model across a variety of parameters such as precision (91.72%), recall (92.34%), Intersection over Union (IoU) (90.23%), and f1 score (93.64%). Our experimental results precisely indicate that our approach outperforms traditional approaches. We demonstrate significant increases in accuracy and adaptability, especially when adjusting to dynamic configurations.