UAV multitarget detection plays a pivotal role in civil and military fields. Although deep learning methods provide a more effective solution to this task, changes in target size, shape change, occlusion, and lighting conditions from the perspective of drones still bring great challenges to research in this field. Based on the above problems, this paper proposes an aerial image detection model with excellent performance and strong robustness. First, in view of the common problem that small targets in aerial images are prone to misdetection and missed detection, the idea of Bi-PAN-FPN is introduced to improve the neck part in YOLOv8-s. By fully considering and reusing multiscale features, a more advanced and complete feature fusion process is achieved while maintaining the parameter cost as much as possible. Second, the GhostblockV2 structure is used in the backbone of the benchmark model to replace part of the C2f module, which suppresses information loss during long-distance feature transmission while significantly reducing the number of model parameters; finally, WiseIoU loss is used as bounding box regression loss, combined with a dynamic nonmonotonic focusing mechanism, and the quality of anchor boxes is evaluated by using “outlier” so that the detector takes into account different quality anchor boxes to improve the overall performance of the detection task. The algorithm’s performance is compared and evaluated on the VisDrone2019 dataset, which is widely used worldwide, and a detailed ablation experiment, contrast experiment, interpretability experiment, and self-built dataset experiment are designed to verify the effectiveness and feasibility of the proposed model. The results show that the proposed aerial image detection model has achieved obvious results and advantages in various experiments, which provides a new idea for the deployment of deep learning in the field of UAV multitarget detection.

This paper aims to achieve real-time and accurate detection of surface defects by using a deep learning method. For this purpose, the Single Shot MultiBox Detector (SSD) network was adopted as the meta structure and combined with the base convolution neural network (CNN) MobileNet into the MobileNet-SSD. Then, a detection method for surface defects was proposed based on the MobileNet-SSD. Specifically, the structure of the SSD was optimized without sacrificing its accuracy, and the network structure and parameters were adjusted to streamline the detection model. The proposed method was applied to the detection of typical defects like breaches, dents, burrs and abrasions on the sealing surface of a container in the filling line. The results show that our method can automatically detect surface defects more accurately and rapidly than lightweight network methods and traditional machine learning methods. The research results shed new light on defect detection in actual industrial scenarios.

In the globalization trend, China’s cultural heritage is in danger of gradually disappearing. The protection and inheritance of these precious cultural resources has become a critical task. This paper focuses on the Miao batik culture in Guizhou Province, China, and explores the application of knowledge graphs, natural language processing, and deep learning techniques in the promotion and protection of batik culture. We propose a dual-channel mechanism that integrates semantic and visual information, aiming to connect batik pattern features with cultural connotations. First, we use natural language processing techniques to automatically extract batik-related entities and relationships from the literature, and construct and visualize a structured batik pattern knowledge graph. Based on this knowledge graph, users can textually search and understand the images, meanings, taboos, and other cultural information of specific patterns. Second, for the batik pattern classification, we propose an improved ResNet34 model. By embedding average pooling and convolutional operations into the residual blocks and introducing long-range residual connections, the classification performance is enhanced. By inputting pattern images into this model, their categories can be accurately identified, and then the underlying cultural connotations can be understood. Experimental results show that our model outperforms other mainstream models in evaluation metrics such as accuracy, precision, recall, and F1-score, achieving 94.46%, 94.47%, 93.62%, and 93.8%, respectively. This research provides new ideas for the digital protection of batik culture and demonstrates the great potential of artificial intelligence technology in cultural heritage protection.

Object detection (OD) for remote sensing images (RSIs) is an important research topic in remote sensing data analysis. Many efforts have been devoted to remote sensing OD (RSOD) tasks, most of which try to use attention mechanisms to improve the performance of detectors. However, the difference in information between the global features and local features of feature maps is ignored. In this article, we design a novel global and local enhanced attention mechanism (GLE-AM) to capture this different information. Then, we propose a global and local feature-enhanced network (GLE-Net) to fully utilize the features extracted by the GLE-AM. Furthermore, to make the path aggregation feature pyramid network (PAFPN) more suitable for extracting fused features and small OD tasks, we improve the cross-stage partial layer (CSP-Layer) and the spatial pyramid pooling (SPP), respectively. Experiments conducted on two publicly available remote sensing datasets demonstrate the effectiveness of our proposed methods. On the DIOR dataset, GLFE-YOLOX improved on the mAP metric by 3.19% compared to the YOLOX-m baseline, and on the NWPU VHR-10 dataset GLFE-YOLOX reaches 90.93% on mAP, which is 3.18% higher than YOLOX-l, comparing with the comparison algorithms, our proposed GLFE-YOLOX achieves the best results in mAP metric for both datasets.

To monitor product quality in the production process in real time, this thesis proposes a quality monitoring model based on PaddlePaddle You Only Look Once (PP-YOLO). First, in the preprocessing stage, the data enhancement method and the K-means++ method are used to improve the robustness of the algorithm, and the generated anchor box can screen more refined features earlier. Second, ResNet50-vd with the deformable convolution idea is selected as the backbone of the detection model, the feature pyramid network structure and the composition of the loss function are improved, and the feature learning ability of the model is enhanced to enable it to detect multiple scales of defects. Finally, pruning is performed on the basis of the trained model to reduce the number of model parameters so that it can be deployed in industrial scenarios with limited hardware conditions. Experimental results show that the proposed quality monitoring model can meet the requirements for detection speed and accuracy in actual production, providing a new concept for the deployment of deep learning models in the industrial field.