This paper uses the combination of information and class separability as a new evaluation criterion for hyperspectral imagery. Moreover, the correlation between bands is used as a constraint condition. The differential evolution algorithm is adopted during the search of optimal band combination. In addition, the game theory is introduced into the band selection to coordinate the potential conflict of searching the optimal band combination using information and class separability these two evaluation criteria. The experimental results show that the proposed method is effective.
27 February 2025 in IEEE Geoscience and Remote Sensing Letters
In remote sensing image (RSI) change detection (CD), the binary CD is crucial for identifying change objects but lacks semantic information, leading to issues with intraclass similarity and differentiation. This paper proposes a graph-semantic guided Transformer network (GGTNet), by leveraging semantic information and graph convolution networks. Our framework integrates CNNs and Transformer layers in a multi-layered parallel and serial manner and introduces a novel graph semantic module (GSM) to guide detailed feature extraction through graph semantic features. In this module, each channel of the feature map is treated as a feature node, and their relationships are represented by an adjacency matrix, with multi-hop neighbor aggregation enhancing the model’s ability to capture long-range dependencies, resulting in richer graph semantic features. These features are then utilized in the subsequent semantic fusion Transformer module (SFTM) to guide the backbone features extracted by the network. Experimental results demonstrate that our method is competitive compared to several state-of-the-art CD methods.
Underwater scenes are often affected by issues such as blurred details, color distortion, and low contrast, which are primarily caused by wavelength-dependent light scattering; these factors significantly impact human visual perception. Convolutional neural networks (CNNs) have recently displayed very promising performance in underwater super-resolution (SR). However, the nature of CNN-based methods is local operations, making it difficult to reconstruct rich features. To solve these problems, we present an efficient and lightweight dual-aware integrated network (DAIN) comprising a series of dual-aware enhancement modules (DAEMs) for underwater SR tasks. In particular, DAEMs primarily consist of a multi-scale color correction block (MCCB) and a swin transformer layer (STL). These components work together to incorporate both local and global features, thereby enhancing the quality of image reconstruction. MCCBs can use multiple channels to process the different colors of underwater images to restore the uneven underwater light decay-affected real color and details of the images. The STL captures long-range dependencies and global contextual information, enabling the extraction of neglected features in underwater images. Experimental results demonstrate significant enhancements with a DAIN over conventional SR methods.
To fuse multispectral images and panchromatic images, this paper proposes a new fused method using fuzzy integral based on fast intensity-hue-saturation (IHS) transform. The proposed method enables fast, easy implementation. We choose the fuzzy density according to the importance of the spectral and spatial resolution in the fused images respectively. With an appropriate fuzzy density, the new approach can update the spatial detail quality of the fused image while minimizing the spectral distortion relative to the original low-resolution multispectral images. The experiment results carried out on Landsat-7 ETM+ mutlispectral and panchromatic image show the proposed approach effective.
We propose a fast progressive transductive support vector machine (FPTSVM) method for detecting changes in bitemporal multispectral images. Our method differs from other transductive SVM methods in that much fewer unlabelled data vectors need to be considered in each iteration for the determination of transductive samples. As a result, the computational cost of the method is reduced. To improve the change detection results, our method incorporates the spectral angle (SA) as an extra component to each input data vector. Experimental results on Landsat dataset show that our method gives the smallest overall error and the fastest run time.