Scene classification in remote sensing images is one of the urgent tasks that requires an improvement in recognition accuracy due to complex spatial structures and high inter-class similarity. Although feature extraction using convolutional neural networks provides high efficiency, combining deep features obtained from different architectures in a semantically consistent manner remains an important scientific problem. In this study, a DMCCA + SVM model is proposed, in which Discriminative Multiple Canonical Correlation Analysis (DMCCA) is applied to fuse multi-source deep features, and final classification is performed using a Support Vector Machine (SVM). Unlike conventional fusion methods, DMCCA projects heterogeneous features into a unified low-dimensional latent space by maximizing within-class correlation and minimizing between-class correlation, resulting in a more separable and compact feature space. The proposed approach was evaluated on three widely used benchmark datasets—NWPU-RESISC45, AID, and PatternNet—and achieved accuracy scores of 92.75%, 93.92%, and 99.35%, respectively. The results showed that the model outperforms modern individual CNN architectures. Additionally, the model’s stability and generalization capability were confirmed through K-fold cross-validation. Overall, the proposed DMCCA + SVM model was experimentally validated as an effective and reliable solution for high-accuracy classification of remote sensing scenes.
Pansharpening is a method of image fusion that combines a panchromatic (PAN) image with high spatial resolution and multispectral (MS) images which possess different spectral characteristics and are frequently obtained from satellite sensors. Despite the development of numerous pansharpening methods in recent years, a key challenge continues to be the maintenance of both spatial details and spectral accuracy in the combined image. To tackle this challenge, we introduce a new approach that enhances the component substitution-based Adaptive IHS method by integrating the YUV color model along with weighting coefficients influenced by the multispectral data. In our proposed approach, the conventional IHS color model is substituted with the YUV model to enhance spectral consistency. Additionally, Lanczos interpolation is used to upscale the MS image to match the spatial resolution of the PAN image. Each channel of the MS image is fused using adaptive weights derived from the influence of multispectral data, leading to the final pansharpened image. Based on the findings from experiments conducted on the PairMax and PanCollection datasets, our proposed method exhibited superior spectral and spatial performance when compared to several existing pansharpening techniques.
Rapid urban expansion has heightened the demand for accurate, scalable, and real-time methods to assess tree health and the provision of ecosystem services. Urban trees are the major contributors to air-quality improvement and climate change mitigation; however, their monitoring is mostly constrained to inherently subjective and inefficient manual inspections. In order to break this barrier, we put forward a lightweight multimodal deep-learning framework that fuses RGB imagery with environmental and biometric sensor data for a combined evaluation of tree-health condition as well as the estimation of the daily oxygen production and CO2 absorption. The proposed architecture features an EfficientNet-B0 vision encoder upgraded with Mobile Inverted Bottleneck Convolutions (MBConv) and a squeeze-and-excitation attention mechanism, along with a small multilayer perceptron for sensor processing. A common multimodal representation facilitates a three-task learning set-up, thus allowing simultaneous classification and regression within a single model. Our experiments with a carefully curated dataset of segmented tree images accompanied by synchronized sensor measurements show that our method attains a health-classification accuracy of 92.03% while also lowering the regression error for O2 (MAE = 1.28) and CO2 (MAE = 1.70) in comparison with unimodal and multimodal baselines. The proposed architecture, with its 5.4 million parameters and an inference latency of 38 ms, can be readily deployed on edge devices and real-time monitoring platforms.