Object detection in images captured by unmanned aerial vehicles (UAVs) holds great potential in various domains, including civilian applications, urban planning, and disaster response. However, it faces several challenges, such as multi-scale variations, dense scenes, complex backgrounds, and tiny-sized objects. In this paper, we present a novel scale-adaptive YOLO framework called SMFF-YOLO, which addresses these challenges through a multi-level feature fusion approach. To improve the detection accuracy of small objects, our framework incorporates the ELAN-SW object detection prediction head. This newly designed head effectively utilizes both global contextual information and local features, enhancing the detection accuracy of tiny objects. Additionally, the proposed bidirectional feature fusion pyramid (BFFP) module tackles the issue of scale variations in object sizes by aggregating multi-scale features. To handle complex backgrounds, we introduce the adaptive atrous spatial pyramid pooling (AASPP) module, which enables adaptive feature fusion and alleviates the negative impact of cluttered scenes. Moreover, we adopt the Wise-IoU(WIoU) bounding box regression loss to enhance the competitiveness of different quality anchor boxes, which offers the framework a more informed gradient allocation strategy. We validate the effectiveness of SMFF-YOLO using the VisDrone and UAVDT datasets. Experimental results demonstrate that our model achieves higher detection accuracy, with AP50 reaching 54.3% for VisDrone and 42.4% for UAVDT datasets. Visual comparative experiments with other YOLO-based methods further illustrate the robustness and adaptability of our approach.

Optical coherence tomography angiography (OCTA) provides a detailed visualization of the vascular system to aid in the detection and diagnosis of ophthalmic disease. However, accurately extracting microvascular details from OCTA images remains a challenging task due to the limitations of pure convolutional networks. We propose a novel end-to-end transformer-based network architecture called TCU-Net for OCTA retinal vessel segmentation tasks. To address the loss of vascular features of convolutional operations, an efficient cross-fusion transformer module is introduced to replace the original skip connection of U-Net. The transformer module interacts with the encoder’s multiscale vascular features to enrich vascular information and achieve linear computational complexity. Additionally, we design an efficient channel-wise cross attention module to fuse the multiscale features and fine-grained details from the decoding stages, resolving the semantic bias between them and enhancing effective vascular information. This model has been evaluated on the dedicated Retinal OCTA Segmentation (ROSE) dataset. The accuracy values of TCU-Net tested on the ROSE-1 dataset with SVC, DVC, and SVC+DVC are 0.9230, 0.9912, and 0.9042, respectively, and the corresponding AUC values are 0.9512, 0.9823, and 0.9170. For the ROSE-2 dataset, the accuracy and AUC are 0.9454 and 0.8623, respectively. The experiments demonstrate that TCU-Net outperforms state-of-the-art approaches regarding vessel segmentation performance and robustness.

With the continuous development of deep learning, the face recognition field has also developed rapidly. However, with the massive popularity of COVID-19, face recognition with masks is a problem that is now about to be tackled in practice. In recognizing a face wearing a mask, the mask obscures most of the facial features of the face, resulting in the general face recognition model only capturing part of the facial information. Therefore, existing face recognition models are usually ineffective in recognizing faces wearing masks. This article addresses this problem in the existing face recognition model and proposes an improvement of Facenet. We use ConvNeXt-T as the backbone of the network model and add the ECA (Efficient Channel Attention) mechanism. This enhances the feature extraction of the unobscured part of the face to obtain more useful information, while avoiding dimensionality reduction and not increasing the model complexity. We design new face recognition models by investigating the effects of different attention mechanisms on face mask recognition models and the effects of different data set ratios on experimental results. In addition, we construct a large set of faces wearing masks so that we can efficiently and quickly train the model. Through experiments, our model proved to be 99.76% accurate for real faces wearing masks. A combined accuracy of 99.48% for extreme environments such as too high or lousy contrast and brightness.

Accurately identifying apple leaf diseases in complex field environments is a critical concern for intelligent agriculture, as early detection directly affects crop health and yield outcomes. However, accurate feature recognition remains a significant challenge due to the complexity of disease symptoms, background interference, and variations in lesion color and size. In this study, we propose an enhanced detection framework named DMN-YOLO. Specifically, the model integrates a multi-branch auxiliary feature pyramid network (MAFPN), along with Superficial Assisted Fusion (SAF) and Advanced Auxiliary Fusion (AAF) modules, to strengthen feature interaction, retain shallow-layer information, and improve high-level gradient transmission, thereby enhancing multi-scale lesion detection performance. Furthermore, the RepHDWConv module is incorporated into the neck network to increase the model’s representational capacity. To address difficulties in detecting small and overlapping lesions, a lightweight RT-DETR decoder and a dedicated detection layer (P2) are introduced. These enhancements effectively reduce both missed and false detections. Additionally, a normalized Wasserstein distance (NWD) loss function is introduced to mitigate localization errors, particularly for small or overlapping lesions. Experimental results demonstrate that DMN-YOLO achieves a 5.5% gain in precision, a 3.4% increase in recall, and a 5.0% improvement in mAP@50 compared to the baseline, showing consistent superiority across multiple performance metrics. This method offers a promising solution for robust disease monitoring in smart orchard applications.