Search Results (4)

Accurate pavement crack detection under adverse weather conditions is essential for road safety and effective pavement maintenance. However, factors such as reduced visibility, background noise, and irregular crack morphology make this task particularly challenging in real-world environments. To address these challenges, we propose CrackNet-Weather, which is a robust and efficient detection method that systematically incorporates three key modules: a Haar Wavelet Downsampling Block (HWDB) for enhanced frequency information preservation, a Strip Pooling Bottleneck Block (SPBB) for multi-scale and context-aware feature fusion, and a Dynamic Sampling Upsampling Block (DSUB) for content-adaptive spatial feature reconstruction. Extensive experiments conducted on a challenging dataset containing both rainy and snowy weather demonstrate that CrackNet-Weather significantly outperforms mainstream baseline models, achieving notable improvements in mean Average Precision, especially for low-contrast, fine, and irregular cracks. Furthermore, our method maintains a favorable balance between detection accuracy and computational complexity, making it well suited for practical road inspection and large-scale deployment. These results confirm the effectiveness and practicality of CrackNet-Weather in addressing the challenges of real-world pavement crack detection under adverse weather conditions. Full article

Mulberry (Morus spp.), as an economically significant crop in sericulture and medicinal applications, faces severe threats to leaf yield and quality from pest and disease infestations. Traditional detection methods relying on chemical pesticides and manual observation prove inefficient and unsustainable. Although computer vision and deep learning technologies offer new solutions, existing models exhibit limitations in natural environments, including low recognition rates for small targets, insufficient computational efficiency, poor adaptability to occlusions, and inability to accurately identify structural features such as leaf veins. We propose Mamba-YOLO-ML, an optimized model addressing three key challenges in vision-based detection: Phase-Modular Design (PMSS) with dual blocks enhancing multi-scale feature representation and SSM selective mechanisms and Mamba Block, Haar wavelet downsampling preserving critical texture details, and Normalized Wasserstein Distance loss improving small-target robustness. Visualization analysis of the detection performance on the test set using GradCAM revealed that the enhanced Mamba-YOLO-ML model demonstrates earlier and more effective focus on characteristic regions of different diseases compared with its predecessor. The improved model achieved superior detection accuracy with 78.2% mAP50 and 59.9% mAP50:95, outperforming YOLO variants and comparable Transformer-based models, establishing new state-of-the-art performance. Its lightweight architecture (5.6 million parameters, 13.4 GFLOPS) maintains compatibility with embedded devices, enabling real-time field deployment. This study provides an extensible technical solution for precision agriculture, facilitating sustainable mulberry cultivation through efficient pest and disease management. Full article

Fire poses a serious threat to the global economy, environment, and social stability, highlighting the need for rapid and accurate fire detection. Remote sensing combined with deep learning has outperformed traditional fire assessment methods. However, in early fire stages, small flame areas, class imbalance, and weak feature extraction hinder detection accuracy. This study proposes an end-to-end segmentation model called Flame Detail Enhancement U-Net (FDE U-Net), using Landsat-8 multispectral remote sensing data. The model incorporates the self-Attention and Convolutional mixture (ACmix) module and the Convolutional Block Attention Module (CBAM) into the encoder of the Residual U-Net. ACmix integrates self-attention and convolution to capture global semantic features while maintaining computational efficiency, improving both contextual awareness and local detail. CBAM enhances flame recognition by weighting important channel features and focusing spatially on small flame areas, helping address the class imbalance problem. Additionally, Haar wavelet downsampling is applied to retain image detail and improve the detection of small-scale flame regions. Experimental results show that the FDE U-Net model exhibits robust performance in fire detection, accurately extracting flame regions even when their proportion is low and the background is complex. The F1 score reaches 95.97%, significantly improving the class imbalance problem. Full article

Modern high-intensity armed conflicts often lead to extensive damage to urban infrastructure. The use of high-resolution remote sensing images can clearly detect damage to individual buildings which is of great significance for monitoring war crimes and damage assessments that destroy civilian infrastructure indiscriminately. In this paper, we propose SOCA-YOLO (Sampling Optimization and Coordinate Attention–YOLO), an automatic detection method for destroyed buildings in high-resolution remote sensing images based on deep learning techniques. First, based on YOLOv8, Haar wavelet transform and convolutional blocks are used to downsample shallow feature maps to make full use of spatial details in high-resolution remote sensing images. Second, the coordinate attention mechanism is integrated with C2f so that the network can use the spatial information to enhance the feature representation earlier. Finally, in the feature fusion stage, a lightweight dynamic upsampling strategy is used to improve the difference in the spatial boundaries of feature maps. In addition, this paper obtained high-resolution remote sensing images of urban battlefields through Google Earth, constructed a dataset for the detection of objects on buildings, and conducted training and verification. The experimental results show that the proposed method can effectively improve the detection accuracy of destroyed buildings, and the method is used to map destroyed buildings in cities such as Mariupol and Volnovaja where violent armed conflicts have occurred. The results show that deep learning-based object detection technology has the advantage of fast and accurate detection of destroyed buildings caused by armed conflict, which can provide preliminary reference information for monitoring war crimes and assessing war losses. Full article