The rapid increase in spatial resolution of remote sensing scene images (RSIs) has led to a concomitant increase in the complexity of the spatial contextual information contained therein. The coexistence of numerous smaller features makes it challenging to accurately locate and mine these features, which in turn makes accurate interpretation difficult. In order to address the aforementioned issues, this paper proposes a dynamic convolution covariance network (ODFMN) based on omni-dimensional dynamic convolution (ODConv), which can extract multi-dimensional and multi-scale features from RSIs and perform statistical higher-order representation of feature information. First, in order to fully exploit the complex spatial context information of RSIs and at the same time improve the limitation of a single static convolution kernel for feature extraction, we constructed a omni-dimensional feature extraction module (ODFE) based on dynamic convolution, which fully extracts the four-dimensional information within the convolution kernel. Then, to make full use of the full-dimensional feature information extracted from each level in the network, the feature representation is enriched by constructing multi-scale feature fusion module (MFM) to establish relationships from local to global. Finally, higher-order statistical information is employed to address the challenge of representing first-order information for smaller object features, which is inherently difficult to do. Experiments conducted on publicly available datasets have demonstrated that the method achieves high classification accuracies of 99.04%, 95.34%, and 92.50%, respectively. Furthermore, the method has been verified to have high capture accuracy for feature target contours, shapes, and spatial context information through feature visualisation.

Remote sensing scene classification is a crucial task in the field of remote sensing technology, as it helps identify and categorize various geographical features on the Earth's surface. Recently, convolutional neural networks (CNNs) have been widely employed for scene classification in remote sensing images, leading to significant performance improvements. However, current CNN methods have certain limitations, primarily manifested in their tendency to overly focus on extracting high-level features, often overlooking essential information at different levels within the images. Furthermore, some approaches attempt to directly merge features from different levels, potentially resulting in issues of information redundancy or mutual exclusion. To address these challenges, this paper proposes an efficient method for remote sensing scene classification. Our approach involves three main contributions. First, we introduce a feature extraction module called multi-stream feature extraction, which effectively utilizes features at various scales and extracts features at different levels and depths. Second, we propose a dense residual connection feature fusion technique that enables comprehensive feature interactions and improves overall accuracy. Additionally, we introduce a correlated attention network to learn powerful feature representations at multiple levels, further improving classification performance. The method outperforms existing algorithms in terms of effectiveness and accuracy, achieving state-of-the-art results on four widely used remote sensing scene classification benchmarks.