Accurate fig detection in complex environments is a significant challenge. Small targets, occlusion, and similar backgrounds are considered the main obstacles in intelligent harvesting. To address this, this study proposes Fig-YOLO, an improved YOLOv11n-based detection algorithm with multiple targeted architectural innovations. First, a Spatial–Frequency Selective Convolution (SFSConv) module is introduced into the backbone to replace conventional convolution, enabling joint modeling of spatial structures and frequency-domain texture features for more effective discrimination of figs from visually similar backgrounds. Second, an enhanced bi-branch attention mechanism (EBAM) is incorporated at the network’s terminal stage to strengthen the representation of key regions and improve robustness under severe occlusion. Third, a multi-branch dynamic sampling convolution (MFCV) module replaces the original C3k2 structure in the feature fusion stage, capturing figs of varying sizes through dynamic sampling and residual deep-feature fusion. Experimental results show that Fig-YOLO achieves precision, recall, and mAP@0.5 of 89.2%, 78.4%, and 87.3%, respectively, substantially outperforming the baseline YOLOv11n. Further evaluation confirms that the model maintains stable performance across varying fruit sizes, occlusion levels, lighting conditions, and data sources. Fig-YOLO’s innovations offer solid support for intelligent orchard monitoring and harvesting.

Cotton is susceptible to Verticillium wilt (VW) during its growth. Early and accurate detection of VW can facilitate targeted pesticide treatment and reduce the potential spread of the disease. However, accurately detecting VW in cotton before symptoms appear (the asymptomatic period) after infection by Verticillium dahliae remains challenging. This study proposes an early detection method for cotton wilt disease using hyperspectral imaging and recurrence plots (RP) combined with machine learning techniques. First, spectral curves were collected and analyzed under three conditions of cotton plants: healthy, asymptomatic, and symptomatic. Then, the one-dimensional spectral curve was transformed into two-dimensional recurrence plots to enhance the detail differences in the original spectral curve of cotton plants in various states. Hyperspectral recurrence plots contain rich texture information; fifteen texture features were extracted from the spectral recurrence plots using the Gray-Level Gradient Co-occurrence Matrix (GLGCM). Eleven of these texture features showed a strong correlation with the class labels of the cotton plants. In order to reduce redundant information between features, principal component analysis (PCA) was used to extract the first five principal components, which explained 99.02% of the information from the 11 features. The final principal component dataset was then input into KNN, SVM, ELM, and XGBoost classifiers to assess the accuracy of early detection of VW in cotton. The results showed that the XGBoost model, based on the first five principal components obtained from the texture features, achieved accuracy, precision, recall, and F1-score of 96.3%, 95.6%, 96%, and 95.8%, demonstrating a high classification capability. The results of this study confirm the feasibility of converting spectral curves into recurrence plots and extracting image texture features for the accurate identification of VW in cotton during the asymptomatic period. This method also provides a new strategy for early disease detection of cotton and other plants in the future.

Accurate detection of cattle and sheep is a core task in precision livestock farming. However, the complexity of agricultural settings, where visible light images perform poorly under low-light or occluded conditions and infrared images are limited in resolution, poses significant challenges for current smart monitoring systems. To tackle these challenges, this study aims to develop a robust multimodal fusion detection network for the accurate and reliable detection of cattle and sheep in complex scenes. To achieve this, we propose YOLO-MSLT, a multimodal fusion detection network based on YOLOv10, which leverages the complementary nature of visible light and infrared data. The core of YOLO-MSLT incorporates a Cross Flatten Fusion Transformer (CFFT), composed of the Linear Cross-modal Spatial Transformer (LCST) and Deep-wise Enhancement (DWE), designed to enhance modality collaboration by performing complementary fusion at the feature level. Furthermore, a Content-Guided Attention Feature Pyramid Network (CGA-FPN) is integrated into the neck to improve the representation of multi-scale object features. Validation was conducted on a cattle and sheep dataset built from 5056 pairs of multimodal images (visible light and infrared) collected in the Manas River Basin, Xinjiang. Results demonstrate that YOLO-MSLT performs robustly in complex terrain, low-light, and occlusion scenarios, achieving an mAP@0.5 of 91.8% and a precision of 93.2%, significantly outperforming mainstream detection models. This research provides an impactful and practical solution for cattle and sheep detection in challenging agricultural environments.

Geographical origin identification of fragrant pears is crucial for ensuring fruit quality, protecting regional brand value, and maintaining market order. However, pears from different origins often exhibit highly similar appearance and physicochemical properties, making rapid and nondestructive identification challenging for traditional methods. This study proposes a hyperspectral origin identification method based on an enhanced one-dimensional convolutional neural network (ECNN-1D) incorporating an Efficient Channel Attention (ECA) mechanism, using visible–near-infrared (Vis–NIR) and short-wave infrared (SWIR) spectral data. To address the technical challenges of highly similar spectra, redundant features, and complex information distribution, ECNN-1D enhances discriminative spectral feature representation, overcoming limitations of conventional machine learning and standard deep learning models in feature extraction and classification stability. Systematic comparisons with machine learning models (LDA, RF, KNN, SVM) and deep learning models (VGG-1D, ResNet-1D, CNN-1D) showed that while all models performed well on Vis–NIR spectra, ECNN-1D achieved the highest test accuracy of 98.94% and F1 score of 98.95% on the more challenging SWIR spectra, outperforming other approaches. These results indicate that ECNN-1D enables high-precision, nondestructive origin identification of fragrant pears, with potential cost advantages, providing a reliable technical solution for fruit traceability and quality supervision.

High-throughput plant phenotyping with hyperspectral imaging (HSI) is pivotal for accelerating crop improvement to address global food security. Adoption is limited by a data-processing bottleneck, forcing a trade-off between costly, inflexible commercial software and programming-intensive open-source libraries. To overcome this barrier, we developed PlantSpecLab, an open-source, no-code platform that unifies the HSI workflow from image processing to modeling within a single interactive interface. The platform introduces spectrally guided segmentation strategies (Range Averaging, Difference Enhancement) and a spectral Fractional-Order Differencing (FOD) preprocessor to enhance extraction of subtle, physiologically relevant features. Across diverse in-house and public datasets, FOD-preprocessed spectra improved model performance over conventional pipelines, yielding a mean classification accuracy of 82.86 % for tomato maturity and average R² = 0.8638 for fruit firmness. In cross-software benchmarks, PlantSpecLab matched the accuracy of ENVI and code-based Python pipelines while reducing end-to-end workflow time by over 90 % (from approximately 80 minutes to about 8 minutes). PlantSpecLab provides a transparent, efficient analytical environment that lowers the technical barrier to HSI analysis. This enables researchers to prioritize biological interpretation while minimizing computational overhead.