Leaf spot (LS) caused by Cercosporidium personatum is one of the most harmful peanut diseases in the late growth stage and severely affects the yield of peanuts. Hyperspectral disease detection technology is efficient, objective, and accurate and is suitable for large-scale crop management practices. To establish a multi-scale spectral index (SI) with high accuracy and stability for the detection of peanut LS disease, the spectral reflectance of different disease severity levels at leaf, plant, and field scales was collected, and the difference in wavelength caused by disease severity was analyzed using the mean, variance, and dispersion matrix of hyperspectral reflectance. Meanwhile, the feature weights at different scales were obtained using Relief-F, and the average feature weights identified 540, 660, and 770 nm as multi-scale sensitive wavelengths. Three new SIs were constructed by combining single, ratiometric, and normalized wavelengths. The new SIs were compared and analyzed with 35 commonly used SIs by correlation analysis and M-statistic values, and 6 SIs were significantly correlated with disease severity levels and had good separability. Finally, k-nearest neighbor (KNN) and multinomial logistic regression (MLR) were used to evaluate the ability of the above SIs to detect LS severity. The results showed that the leaf spot multi-scale spectral index (LS-MSSI) constructed in this study was superior to the other SIs and obtained high accuracy at different scales simultaneously. At the leaf and plant scales, the MLR obtained high accuracy, with the overall accuracy (OA) reaching 93.77% and 92.50% and Kappa reaching 91.59% and 89.97%, respectively. At the field scale, the KNN obtained high accuracy, with the OA and Kappa reaching 90.29% and 87.04%, respectively. The LS-MSSI proposed in this study has high accuracy, stability, and robustness in the detection of LS severity at multiple scales, providing a technical basis and scientific guidance for the detection and precise management of peanuts.

Remote sensing image classification plays a crucial role in the field of remote sensing interpretation. With the exponential growth of multi-source remote sensing data, accurately extracting target features and comprehending target attributes from complex images significantly impacts classification accuracy. To address these challenges, we propose a Canny edge-enhanced multi-level attention feature fusion network (CAF) for remote sensing image classification. The original image is specifically inputted into a convolutional network for the extraction of global features, while increasing the depth of the convolutional layer facilitates feature extraction at various levels. Additionally, to emphasize detailed target features, we employ the Canny operator for edge information extraction and utilize a convolution layer to capture deep edge features. Finally, by leveraging the Attentional Feature Fusion (AFF) network, we fuse global and detailed features to obtain more discriminative representations for scene classification tasks. The performance of our proposed method (CAF) is evaluated through experiments conducted across three openly accessible datasets for classifying scenes in remote sensing images: NWPU-RESISC45, UCM, and MSTAR. The experimental findings indicate that our approach based on incorporating edge detail information outperforms methods relying solely on global feature-based classifications.

Leaf spot disease is a dangerous disease that affects peanut growth, and its severity can significantly impact peanut yield. Hyperspectral-based disease detection technology is a popular non-destructive technique due to its high efficiency, objectivity, and accuracy. In this study, peanut leaf spectra at different levels of severity of leaf spot disease were collected in Liaoning Province, China, in mid-August. This study analyzed the differences in wavelengths using mean spectral reflectance and sensitivity. Using improved principal component analysis loading (I-PCA loading) based on the contribution weight assignment approach, we identified three feature wavelengths of 570 nm, 671 nm, and 750 nm. We evaluated the ability of these feature wavelengths to detect the severity of leaf spot disease using k-nearest neighbor (KNN), support vector machine (SVM), and back-propagation (BP) neural network classifiers. Our experimental results showed that our improved PCA loading method achieved higher classification accuracy with fewer wavelengths than the seven commonly used feature selection methods. Among these classifiers, the SVM achieved the highest accuracy, with an overall accuracy (OA) of 96.88% and a Kappa of 95.81%. Therefore, our proposed method can accurately detect the severity of peanut leaf spot disease and provide scientific and technical support for accurately managing peanut crops.

Superpixel-based hyperspectral unmixing (HU) can effectively reduce spectral variability’s influence on unmixing performance. In the superpixel-based HU method, this study proposes a segmentation scale determination method to improve the accuracy of endmembers and fully constrained least squares based on distance strategy (D-FCLS) to improve the efficiency of abundance estimation. In the segmentation-scale determination method, this study establishes a segmentation scale division criterion to divide segmented images with similar quality into the same segmentation scale. The optimal segmentation scale is selected according to the actual situation of hyperspectral images. Moreover, the distance strategy is applied to fully constrained least squares (FCLS) using the spatial relationship between endmembers and the mixed pixel in abundance estimation. The proposed methods are evaluated on the synthetic and real datasets. The results show that the validity of the segmentation-scale determination method is verified by quantitative and qualitative evaluation on all datasets. In terms of abundance estimation, compared with FCLS, D-FCLS improves the efficiency by more than 10.30% on the synthetic dataset and 18.71% on the real dataset. In addition, this study’s proposed abundance estimation method and unsupervised superpixel-based HU method are superior to the other comparison methods.

Remote sensing object detection faces significant challenges due to the varying resolutions of images and the diverse shapes of objects. In this paper, we introduce an innovative approach to enhance object detection networks in remote sensing images by addressing these issues through a novel two-stage training process. Our key contributions include the development of a combined low-resolution pretraining and high-resolution fine-tuning strategy, which significantly improves the model’s generalization capability across different resolutions.We have designed a Pretrained Detail Enhancement and Restoration (PDER) framework that enhances feature extraction from low-resolution images, thereby boosting the baseline network’s ability to handle blurred and intricate objects. Additionally, we propose an Energy-Efficient Shape Adaptive Convolution (EESA) that integrates a depthwise separable mechanism with shape-adaptive feature maps, enabling efficient capture of complex object edges without substantial computational overhead. Compared to state-of-the-art methods such as YOLOv7, our model achieves an absolute average precision improvement of 2.34% and 2.57% on the DIOR and xView datasets, respectively. Extensive experiments on multiple remote sensing datasets demonstrate our approach’s effectiveness, achieving significant improvements in detection accuracy and computational efficiency, thus highlighting its potential for practical applications.

Remote sensing object detection faces three challenges: extreme scale variation, arbitrary rotational orientations, and complex intermingled backgrounds. Although fusion of Convolutional Neural Networks (CNNs) and Transformers combines spatial precision with global modeling, it faces two limitations: (i) feature distribution misalignment between modalities, and (ii) ineffective exploitation of complementary discriminative strengths. To address these issues, we introduce DAAF (Dual-stream Adaptive Attention Fusion), a three-stage fusion framework that systematically aligns and integrates CNN and Transformer features. DAAF comprises three components: (1) The Unified Feature Distribution Calibration (UFDC) module applies instance normalization to align feature distributions, reducing Kullback-Leibler (KL) divergence by 94%; (2) The Heterogeneous Channel-wise Synergistic Selection (HCSS) module employs independent attention pathways for each stream, validated by zero overlap in top-10 channel weights between CNN and Transformer branches; (3) The Spatially Adaptive Discriminative-Preserving Gate (SADPG) module employs pixel-wise gating to adaptively balance fused and single-branch features. Experiments on three benchmarks (NWPU VHR-10, DOTA v1.0, DIOR) show consistent improvements averaging +2.05 percentage points (pp) in mean Average Precision (mAP) over the Add Fusion baseline, with substantial gains on structurally complex categories in NWPU (Bridge: + 17.36pp, Vehicle: + 13.18pp). These improvements are achieved with only 206K additional parameters (0.37% increase over baseline) and 7.2% latency rise compared to the baseline fusion method, demonstrating favorable efficiency for practical deployment.