The biomass of rice at maturity serves as a vital indicator for assessing overall productivity, and its accurate estimation holds significant importance for ensuring food security and promoting sustainable agriculture. To improve the precision of current biomass estimation methods for mature rice, this study employed support vector regression to integrate RGB vegetation indices from rice canopy images with growth parameters, thereby developing a biomass estimation model. The model was validated by applying it to the experimental area. The results indicated that screening RGB vegetation indices and combining them with growth parameters enhanced estimation accuracy. Specifically, the model integrating RGB vegetation indices (g, RGBVI) with rice plant height and moisture content demonstrated high estimation accuracy (R2 = 0.78, RMSE = 0.32 kg/m2). The absolute difference between the estimated and measured biomass values ranged from 0.15 to 0.39 kg/m2. Additionally, the estimated biomass showed a strong correlation with yield (R2 = 0.86), with a fitted equation of y = 0.04x + 0.59. These results suggest that the model is reliable for large-area estimation of mature rice biomass. However, the degree of rice maturity and the lodging phenomenon were identified as the primary factors influencing the precision of model application. Overall, integrating RGB vegetation indices of the rice canopy, obtained via UAV-based remote sensing technology, with growth parameters provides an effective method for estimating mature rice biomass and offers a valuable reference for efficient yield estimation.

Maritime search and rescue is an important component of emergency response frameworks and primarily relies on Unmanned Aerial Vehicles (UAVs) for maritime object detection. However, maritime accidents frequently occur in low-visibility environments, such as foggy or low-light conditions, which lead to low contrast, blurred object boundaries, and degraded texture representations. Most existing maritime object detection algorithms are developed for natural light scenes, and their performance deteriorates markedly when deployed directly in low-visibility environments, primarily due to reduced image quality that hinders feature extraction and semantic information aggregation. Although several studies incorporate image enhancement techniques prior to detection to improve image quality, these approaches often introduce significant additional computational overhead, limiting their practical deployment on UAV platforms. To tackle these challenges, this paper proposes a lightweight model built upon a recent YOLO framework, termed Multi-Scale Adaptive YOLO (MSA-YOLO), for maritime detection using UAVs in low-visibility environments. The proposed model systematically optimizes the backbone, neck, and detection head networks. Specifically, an improved StarNet backbone is designed by integrating Efficient Channel Attention (ECA) mechanisms and multi-scale convolutional kernels, which strengthen feature extraction capability while maintaining low computational overhead. In the neck network, a high-frequency enhanced residual block branch is inserted into the C3k2 module to capture richer detailed information, while depthwise separable convolution is utilized to further reduce computational cost. Moreover, a non-parametric attention module is incorporated into the detection head to adaptively optimize features in the classification and regression branches. Finally, a joint loss function that combines bounding box regression, classification, and distribution focal losses is utilized to improve detection accuracy and training stability. Experimental results on the constructed AFO, Zhoushan Island, and Shandong Province datasets demonstrate that, relative to YOLOv11-s, MSA-YOLO reduces model parameters and FLOPs by 52.07% and 41.36%, respectively, while achieving improvements of 1.11% and 1.33% in mAP@0.5:0.95 and mAP@0.5. These results indicate that the proposed method effectively balances computational efficiency and detection accuracy, rendering it suitable for practical maritime search and rescue applications in low-visibility environments.

Maritime search and rescue is an important component of emergency response frameworks and primarily relies on UAVs for maritime object detection. However, maritime accidents frequently occur in low-visibility environments, such as foggy or low-light conditions, which lead to low contrast, blurred object boundaries, and degraded texture representations. Most existing maritime object detection algorithms are developed for natural light scenes, and their performance deteriorates markedly when deployed directly in low-visibility environments, primarily due to reduced image quality that hinders feature extraction and semantic information aggregation. Although several studies incorporate image enhancement techniques prior to detection to improve image quality, these approaches often introduce significant additional computational overhead, limiting their practical deployment on UAV platforms. To tackle these challenges, this paper proposes a lightweight model built upon a recent YOLO framework, termed Multi-Scale Adaptive YOLO (MSA-YOLO), for maritime detection using UAVs in low-visibility environments. The proposed model systematically optimizes the backbone, neck, and detection head networks. Specifically, an improved StarNet backbone is designed by integrating ECA mechanisms and multi-scale convolutional kernels, which strengthen feature extraction capability while maintaining low computational overhead. In the neck network, a high-frequency enhanced residual block branch is inserted into the C3k2 module to capture richer detailed information, while depthwise separable convolution is utilized to further reduce computational cost. Moreover, a non-parametric attention module is incorporated into the detection head to adaptively optimize features in the classification and regression branches. Finally, a joint loss function that combines bounding box regression, classification, and distribution focal losses is utilized to improve detection accuracy and training stability. Experimental results on the constructed AFO, Zhoushan Island, and Shandong Province datasets demonstrate that, relative to YOLOv11-s, MSA-YOLO reduces model parameters and FLOPs by 52.07% and 41.36%, respectively, while achieving improvements of 1.11% and 1.33% in mAP@0.5:0.95 and mAP@0.5. These results indicate that the proposed method effectively balances computational efficiency and detection accuracy, rendering it suitable for for practical maritime search and rescue applications in low-visibility environments.

Segmenting building areas from synthetic aperture radar (SAR) images holds significant research value and practical application potential. However, the complexity of the environment, the diversity of building shapes, and the interference from speckle noise have made building area segmentation from SAR images a challenging research topic. Compared to traditional methods, deep learning-driven approaches exhibit superiority in the aspect of stability and efficiency. Currently, most segmentation methods use a single neural network to encode SAR images, then decode them through interpolation or transpose convolution operations, and finally obtain the segmented building area images using a loss function. Although effective, the methods result in the loss of detailed information and do not fully extract the deep-level features of building areas. Therefore, we propose an innovative network named PSANet. First, two sets of deep-level features of building areas were extracted using ResNet-18 and ResNet-34, with five encoded features of varying scales obtained through a fusion algorithm. Meanwhile, information on the deepest-level encoded features was enriched utilizing an atrous spatial pyramid pooling module. Next, the encoded features were reconstructed through skip connections and transposed convolution operations to obtain discriminative features of the building areas. Finally, the model was optimized using the combined CE-Dice loss function to achieve superior performance. The experimental results of the SAR images from regions with different geographical characteristics demonstrate that the proposed PSANet outperforms several recent State-of-the-Art methods.