Rural Remote Sensing Layout Planning Model Based on Cascaded Deep Residual Network

With the development of urbanization in villages and towns, rural layout planning is an important basis for infrastructure construction and plays a role in the field of rural planning and design space. Remote sensing monitoring can provide real-time and effective layout information for the planning system, which is convenient to reflect the rural grid division and layout style intuitively. In this paper, a lightweight deep residual network is used for distributed computing in 3D graphics. Its feature extraction and connection mode are improved by the SDN connection network structure. It is applied to the generation of super-resolution remote sensing images. Through machine learning’s image local feature processing, we construct the vector representation of super-resolution data. Then, we reduce the network layer output by folding the multi-layer convolution, forming the feature matrix space of lightweight processing. The structure introduces a non-parametric remote-sensing information processing mechanism, which can improve the quality of service and computing performance of devices in the Internet of Things. The design model generates more grids, and the logical reasoning time is faster. The physical characteristics enable it to be applied to more application scenarios. After the experimental analysis on the built simulation platform, the processing effect of the proposed model for remote sensing images is significantly better than that of the comparison scheme because the average performance is improved by 11.2%. Further, the best visualization effect is achieved. It keeps the best network communication state. Improving the model plays a decisive role in the quality of remote sensing image feature extraction and determines the performance and effectiveness of the designed algorithm. The method is more suitable for the embedded terminal in the Internet of Things state. It provides technical support for the future development of low-altitude remote sensing and can play a greater practical role.