A Multitarget Visual Attention Based Algorithm on Crack Detection of Industrial Explosives

Xu, Haibo; Shi, Buhai; Zhang, Qingming

doi:10.1155/2018/8738316

Cited by 3 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The peak signal-to-noise ratio is a standard for evaluating images, and its value is related to the mean square error of the original image and the result image. In general, the larger the value, the better the processing effect 25 . As shown in Fig.…”

Section: Real-time Detection Methods For Panoramic Multitargetmentioning

confidence: 93%

See 1 more Smart Citation

(Retracted) Real-time detection of panoramic multitargets based on machine vision and deep learning

2022

View full text Add to dashboard Cite

. With the continuous development of computer vision technology, moving object detection technology has been paid enough attention and made great progress. Many new methods and new equipment have been developed. As an important part of computer vision, it has important applications in battlefield reconnaissance, video surveillance, image compression and retrieval, human–computer interaction and other research fields, moving object detection and tracking algorithm has always been a research hotspot. We mainly study the panoramic multitarget real-time detection based on machine vision and deep learning. By studying the principle of multitarget real-time detection based on machine vision and deep learning, the panoramic multitarget real-time detection model based on machine vision and deep learning is determined. The principle and correction effect of existing image distortion correction algorithm are analyzed, and the existing problems are summarized. Aiming at the problem that the existing image distortion correction effect is not good, a new method based on machine vision and deep learning is proposed. A real-time panoramic multitarget detection method based on degree learning is proposed. The experimental results show that when the target is moving at medium speed and slow speed, the success rate of tracking is 97% and 95%, respectively; the probability of successful target detection is 100% and 97%, respectively. Experimental results show that the improved method can solve the problem of particle degradation and improve the accuracy of real-time detection.

show abstract

Section: Real-time Detection Methods For Panoramic Multitargetmentioning

confidence: 93%

“…In general, the larger the value, the better the processing effect. 25 As shown in Fig. 4 and Table 1, the peak signal-to-noise ratios of the two result images and the original image are 31.322472 and 31.2947, respectively, and the mean square errors are 45.3321 and 48.2487, respectively.…”

Section: Regularized Filter Recoverymentioning

confidence: 94%

(Retracted) Real-time detection of panoramic multitargets based on machine vision and deep learning

2022

View full text Add to dashboard Cite

show abstract

“…The accidental ignition of explosive charges in the launch environment is one of the primary reasons for bore bursts, the mechanism of which has been the focus of considerable research on the launch safety of explosive charges [3,4]. Many scholars [5][6][7][8][9][10] have examined the stress, action time, and hot-spot generation of an explosive charge in the launch environment, finding that factors influencing accidental ignition are the particle size, pores, bottom gaps, cracks, and other defects associated with the explosive charge [11][12][13][14][15]. Wu et al [11] analyzed the influence of particle size on the ignition process and showed that the ignition time increases monotonically with decreasing particle size (50-200 μm).…”

Section: Introductionmentioning

confidence: 99%

A Combustion Model for Explosive Charge Affected by a Bottom Gap in the Launch Environment

Wu,

Chen,

et al. 2024

CMES

View full text Add to dashboard Cite

Launch safety of explosive charges has become an urgent problem to be solved by all countries in the world as launch situation of ammunition becomes consistently worse. However, the existing numerical models have different defects. This paper formulates an efficient computational model of the combustion of an explosive charge affected by a bottom gap in the launch environment in the context of the material point method. The current temperature is computed accurately from the heat balance equation, and different physical states of the explosive charges are considered through various equations of state. Microcracks in the explosive charges are described with respect to the viscoelastic statistical crack mechanics (Visco-SCRAM) model. The method for calculating the temperature at the bottom of the explosive charge with respect to the bottom gap is described. Based on this combustion model, the temperature history of a Composition B (COM B) explosive charge in the presence of a bottom gap is obtained during the launch process of a 155-mm artillery. The simulation results show that the bottom gap thickness should be no greater than 0.039 cm to ensure the safety of the COM B explosive charge in the launch environment. This conclusion is consistent with previous results and verifies the correctness of the proposed model. Ultimately, this paper derives a mathematical expression for the maximum temperature of the COM B explosive charge with respect to the bottom gap thickness (over the range of 0.00-0.039 cm), and establishes a quantitative evaluation method for the launch safety of explosive charges. The research results provide some guidance for the assessment and detection of explosive charge safety in complex launch environments.

show abstract

Magnetic Tile Surface Defect Detection Methodology Based on Self-Attention and Self-Supervised Learning

Ling

Ali

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

As the core component of permanent magnet motor, the magnetic tile defects seriously affect the quality of industrial motor. Automatic recognition of the surface defects of the magnetic tile is a difficult job since the patterns of the defects are complex and diverse. The existing defect recognition methods result in difficulty in practical application due to the complicated system structure and the low accuracy of the image segmentation and the target detection for the diversity of the defect patterns. A self-supervised learning (SSL) method, which benefits from its nonlinear feature extraction performance, is proposed in this study to improve the existing approaches. We proposed an efficient multihead self-attention method, which can automatically locate single or multiple defect areas of magnetic tile and extract features of the magnetic tile defects. We also designed an accurate full-connection classifier, which can accurately classify different defects of magnetic tile defects. A knowledge distillation process without labeling is proposed, which simplifies the self-supervised training process. The process of our method is as follows. A feature extraction model consists of standard vision transformer (ViT) backbone, which is trained by contrast learning without labeled dataset that is used to extract global and local features from the input magnetic tile images. Then, we use a full-connection neural network, which is trained by using labeled dataset to classify the known defect types. Finally, we combined the feature extraction model and defect classification model together to form a relatively simple integrated system. The public magnetic tile surface defect dataset, which holds 5 defect categories and 1 nondefect category, is used in the process of training, validating, and testing. We also use online data augmentation techs to increase training samples to make the model converge and achieve high classification accuracy. The experimental results show that the features extracted by the SSL method can get richer and more detailed features than the supervised learning model gets. The composite model reaches to a high testing accuracy of 98.3%, and gains relatively strong robustness and good generalization ability.

show abstract

A Multitarget Visual Attention Based Algorithm on Crack Detection of Industrial Explosives

Cited by 3 publications

References 28 publications

(Retracted) Real-time detection of panoramic multitargets based on machine vision and deep learning

(Retracted) Real-time detection of panoramic multitargets based on machine vision and deep learning

A Combustion Model for Explosive Charge Affected by a Bottom Gap in the Launch Environment

Magnetic Tile Surface Defect Detection Methodology Based on Self-Attention and Self-Supervised Learning

Contact Info

Product

Resources

About