Object detection is crucial in remote sensing, surveillance, and autonomous driving. Detecting small objects remains challenging due to limited pixels, redundant backgrounds, and noise from viewpoint and illumination variations. To address these, we propose ESGN-YOLO, a lightweight model with three improvements. The Efficient Feature Fusion Module (EFFM) enhances multi-scale and directional feature extraction. The Shift-Wise Convolution (SWC) Bottleneck refines fine-grained features and suppresses background redundancy. The Group Normalisation Scale Head (GNSH) further improves detection accuracy and efficiency. Experiments on VisDrone2019 and RS STOD show ESGN-YOLO achieves superior [email protected] (34.5% and 76%) with a compact size (3.7M parameters) and moderate computational cost (12.3 GFLOPs). Fast inference confirms its practicality for real-time UAV deployment and small-object detection under resource-constrained conditions.

A visual mechanical signal detection and loading platform with super-resolution based on deep learning is designed to improve the detection accuracy of mechanical signals. The visual mechanical signal detection and loading platform with super-resolution include three-dimensional (3D) biological force quantitative detection platform and the mechanical signal loading platform with 3D magnetic distortion and ultrahigh resolution. In the 3D biological force quantitative detection platform, four 3D force sensors are used to collect mechanical signals, and the improved fuzzy clustering fusion method is used to fuse the mechanical signals collected by 3D force sensors to improve the detection accuracy of mechanical signals. The mechanical signal loading platform of 3D magnetic distortion and ultrahigh resolution technology connects the 3D magnetic distortion instrument and microscope, collects images through high-speed scanning components and distorted magnetic field, reconstructs the collected images by deep learning method, obtains ultrahigh-resolution mechanical signal visual images, and triggers mechanical signal loading and release by synchronous interactive system. The consequences of the experiment demonstrate that the designed platform can display the super-resolution mechanical signals through the visual interface. The mechanical signals are loaded in different directions, and the detection accuracy of mechanical signals is higher than 99.5%.

For the past several years, semantic segmentation method based on deep learning, especially Unet, have achieved tremendous success in medical image processing. The U-shaped topology of Unet can well solve image segmentation tasks. However, due to the limitation of traditional convolution operations, Unet cannot realize global semantic information interaction. To address this problem, this paper proposes RT-Unet, which combines the advantages of Transformer and Residual network for accurate medical segmentation. In RT-Unet, the Residual block is taken as the image feature extraction layer to alleviate the problem of gradient degradation and obtain more effective features. Meanwhile, Skip-Transformer is proposed, which takes Multi-head Self-Attention as the main algorithm framework, instead of the original Skip-Connection layer in Unet to avoid the influence of shallow features on the network's performance. Besides, we add attention module at the decoder to reduce semantic differences. According to the experiments on MoNuSeg data set and ISBI_2018cell data set, RT-Unet achieves better segmentation performance than other deep learning-based algorithms. In addition, a series of further ablation experiments were conducted on Residual network and Skip-Transformer, which verified the effectiveness and efficiency of the proposed methods in this paper.

Currently, deep learning has become more and more mature in the field of medical image segmentation. Through using the computer, the deep learning models established can completely help doctors to perform medical image segmentation. Most of the current deep learning models are based on Unet. The U-shaped structure and the skip connection layer of Unet can effectively achieve precise image segmentation. However, for complicated images, the network structure of Unet is not sufficient enough. In response to this problem, some scholars have designed Unet++ by adding a denser skip connection layer to U-Net. Compared to U-Net, Unet++ is more effective in dealing with complex images, but it has drawbacks in many aspects, and there is still a large loss of eigenvalues in the skip connection and up-sampling processes. To address these issues, this paper uses the channel and attention mechanism to improve the Unet++ model to obtain better image segmentation efficiency and accuracy. Meanwhile, based on Unet++, this paper designs a new model called CA-Unet++. The proposed model uses the channel module and the attention module to solve the eigenvalues loses in the long-distance skip connection process and the up-sampling process, respectively. The experimental results and data analysis shows that our proposed CA-Unet++ can achieve better performance in medical computed tomography scan image segmentation.

Due to the complex structure of cytopathological images, data loss and low transmission efficiency may occur in the transmission of cytopathological images by common data stream transmission methods. To ensure the stable transmission of the data stream of the cytopathology image storage system and maintain the safe operation of the cytopathology image storage system, a safe transmission method of the data stream of the cytopathology image storage system was designed. The security threats faced by the data flow of the cytopathology image storage system were analyzed from the aspects of information network and control network, and the risk indexes of data flow and attack loss were constructed. The security risk indexes were quantified by the general vulnerability scoring system, and the data flow security transmission model of the cytopathology image storage system was constructed. Different transmission nodes and cytopathological image storage system devices were set as attack graph nodes to collect and configure data and optimize data flow transmission path. Deploy the network node equilibrium state, control the time slot window interval equilibrium, output transmission delay allocation, and ensure the confidentiality and integrity of the data stream transmission of the cytopathological image storage system. The simulation results show that the proposed method has a higher transmission efficiency of about 11.76 Mb/s. It is highly practical and can realize the safe transmission of data stream in the cytopathological image storage system.