Vision-based industrial surface defect detection utilizing computer vision technologies to analyze defects in the appearance of industrial products has become popular in intelligent manufacturing. It makes inspectors move away from inefficient and labor-...

Unlike ordinary computer vision tasks that focus more on the semantic content of images, the image manipulation detection task pays more attention to the subtle information of image manipulation. In this paper, the noise image extracted by the improved ...

In the welding process, defects such as cracks, porosity, incomplete fusion, incomplete penetration, and slag inclusion may occur due to welding technology, environmental factors, and other influences, which directly affect the service life and ...

The purpose of this paper is to improve the detection accuracy of UAV small target in the high-voltage tower scene. Firstly, this paper constructs the small target data set of UAV with three different models and enhances the data set. Then, Mask R-CNN ...

Unsupervised person re-identification works mainly rely on feature representation learning. In recent years, many methods have used pseudo-labels generated from clustering and applied contrast learning techniques to train models. However, the existing ...

Identifying the space targets rapidly and accurately is a significant mission in defending national rights and maintaining space security. The continuous emergence of new space targets has led to a dramatic decrease of the performance of Inverse ...

This paper presents a robust video steganography algorithm based on secret sharing to prevent the loss of video information that may be encountered in bad channel transmission. To improve the robustness of the secret message, we split the embedded ...

Remote sensing images of buildings are due to the diversity of the structure of the building itself and the complexity of its surrounding environment, and due to the impact of factors such as lighting and shadows, there are problems with incomplete ...

In this paper, we study a real-time monitoring system in which distributed Internet of Things (IoT) devices are responsible for the sampling of an underlying physical process and sending update packets to a common base station (BS) in order to maintain ...

In view of the defects of the existing tower crane visual system in Cottonwood, this paper proposes a scheme to connect the video camera and PC to local area network through routers, switches, wireless bridges and other devices. The video data real-time ...

In the data management of complex products, relationship extraction of related texts can assist in constructing product data chains. This can realize the integration and fusion of data chains through nodes with relationships between different data ...

To address the problem of low accuracy of unimodal speech emotion recognition methods, a bimodal MCNN-BiLSTM-Attention speech emotion recognition algorithm is proposed. The algorithm adopts the Mel-spectrogram and text information in audio as input, ...

As one of the most mature application fields of artificial intelligence, face recognition system has been widely used in production and life. But at the same time as large-scale commercialization, face recognition technology also faces more challenges. ...

Human behavior recognition is one of the most important research directions in the field of computer vision, and it plays an important role in the fields of rehabilitative medicine, auxiliary security, and scene entertainment. To address the ...

Frequent flooding disasters occur in China, including a number of very heavy rainfall events have brought great losses to the country and the people, and these sudden extreme weather events seriously threaten the lives and property safety of the people. ...

Image retrieval is an important task in computer vision. Among various image retrieval approaches, deep hashing methods map input images to binary codes for nearest neighbor search, achieving advantages in both search time and space. In recent years, ...

With the advent of deep learning, convolution neural networks (CNN) based object detection plays a critical role in fields such as autonomous driving. Unlike the normal-lit scenario, the dark environment can be challenging for object detection due to ...

Abstract: Network covert timing channels (NCTCs) utilize Inter-Packet Delay (IPD) encoding to hide data. It can be used for spreading malware and data leakage, posing severe threats to network security. With the increasing risk, the research on NCTC ...

Abstract: Aiming at the problem that sequential diagnosis strategy optimization techniques for complex avionics systems are currently difficult to obtain optimal solutions quickly and effectively, this paper proposes an improved Quasi-Depth First Search ...

With the change of lifestyle, the incidence rate of breast diseases is also increasing. In some cases, there will also be malignant diseases, that is, breast cancer. It is a malignant tumor occurring in the epithelial tissue of the breast, with a very ...