To address the common challenges of insufficient local detail representation and low global modeling efficiency in high-resolution remote sensing image semantic segmentation, this paper proposes a segmentation network that integrates convolutional neural networks and state-space models, named RMUNet. The proposed model employs a lightweight ResNet18 as the encoder and introduces a visual state space block (VSSBlock) in the decoder to achieve efficient global context modeling. Meanwhile, a local feature compensation module (LFCM) is designed to enhance the perception of fine-grained semantic information. To mitigate the semantic bias that may arise during the fusion of shallow and deep features, a cross-level fusion attention module (CFAM) is further proposed to enable effective collaboration between spatial and semantic representations. Experimental results demonstrate that RMUNet achieves mean intersection-over-union (mIoU) scores of 83.78%, 87.09%, and 52.85% on the Vaihingen, Potsdam, and LoveDA datasets, respectively, outperforming existing mainstream methods. While maintaining low computational complexity, RMUNet significantly enhances feature representation and segmentation accuracy, providing an efficient and effective solution for high-resolution remote sensing image interpretation.

In the report, based on the remote sensing ecological index, the landscape ecological characteristics of Fuzhou during the past 20 years were investigated, and the ecological sources with different levels were identified using an ecological sensitivity evaluation index system. Five resistance factors which are derived from natural and social dimensions were selected to construct a comprehensive resistance surface. The critical ecological components which include circuit theory model identifying ecological corridors were used to construct the Fuzhou's ecological security framework. The results indicated that the identified ecological source areas in Fuzhou covered approximately 2992.38 km², accounting for 25.97% of the total area, and which display a spatial distribution characterized by higher density in the west and lower density in the east. A total of 78 ecological corridors were identified, with a spatial pattern of dense distribution in the central and western regions and sparse distribution in the southeast. The ecological pinch points covered an area of 12.83 km², which are concentrated in the northern and northwestern regions with higher ecological quality, while the ecological obstacle points covered 31.68 km², and which are primarily located in the main urban area of Fuzhou.

Aimed at the limitation of the discriminative capability of the extracted features and unsatisfactory classification performance of the scene classification methods based on the deep learning, in the report, in order to improve the effective learning of the scene-representative features, a dual-stream architecture named SC-ETNet, which include the convolution stream and the transformation stream, was proposed for the remote sensing image scene classification. The convolution stream employed the spatial and channel reconstruction convolutions to separate and reconstruct features extracted by convolutional layers. The transformation stream used LightViT for the interaction between global tokens and image tokens to achieve local-global attention computation. The mean classification accuracy of the evaluation on the UC-Merced, AID, and NWPU-RESISC45 datasets was 99.61%, 97.81%, and 95.33%, respectively. These data suggested that compared with the existing advanced scene classification methods, SC-ETNet demonstrates superior classification performance.