A novel approach for fracture skeleton extraction from rock surface images

Tang, Yudi; Liu, He; Lu, Wei; Huang, Xin; Wei, Hai; Xiao, Huaiguang

doi:10.1016/j.ijrmms.2021.104732

Cited by 25 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, optimizing image feature extraction by combining PSO and other algorithms is one of the most effective methods at present. In the literature [ 83 ], aiming at the problem of fault feature parameter extraction and parameter configuration in the batch diagnosis of power equipment infrared images, the combination of the particle swarm algorithm and the Niblack algorithm is used to segment the equipment thermal image from the background. The parameters, such as the minimum, maximum, and average temperature of the equipment, are extracted, and the sample feature space of the support vector machine is constructed by calculating the temperature rise characteristics of the equipment.…”

Section: Swarm Intelligence and Its Application In Image Processingmentioning

confidence: 99%

Application of Swarm Intelligence Optimization Algorithms in Image Processing: A Comprehensive Review of Analysis, Synthesis, and Optimization

Cao

et al. 2023

Biomimetics

View full text Add to dashboard Cite

Image processing technology has always been a hot and difficult topic in the field of artificial intelligence. With the rise and development of machine learning and deep learning methods, swarm intelligence algorithms have become a hot research direction, and combining image processing technology with swarm intelligence algorithms has become a new and effective improvement method. Swarm intelligence algorithm refers to an intelligent computing method formed by simulating the evolutionary laws, behavior characteristics, and thinking patterns of insects, birds, natural phenomena, and other biological populations. It has efficient and parallel global optimization capabilities and strong optimization performance. In this paper, the ant colony algorithm, particle swarm optimization algorithm, sparrow search algorithm, bat algorithm, thimble colony algorithm, and other swarm intelligent optimization algorithms are deeply studied. The model, features, improvement strategies, and application fields of the algorithm in image processing, such as image segmentation, image matching, image classification, image feature extraction, and image edge detection, are comprehensively reviewed. The theoretical research, improvement strategies, and application research of image processing are comprehensively analyzed and compared. Combined with the current literature, the improvement methods of the above algorithms and the comprehensive improvement and application of image processing technology are analyzed and summarized. The representative algorithms of the swarm intelligence algorithm combined with image segmentation technology are extracted for list analysis and summary. Then, the unified framework, common characteristics, different differences of the swarm intelligence algorithm are summarized, existing problems are raised, and finally, the future trend is projected.

show abstract

Section: Swarm Intelligence and Its Application In Image Processingmentioning

confidence: 99%

Application of Swarm Intelligence Optimization Algorithms in Image Processing: A Comprehensive Review of Analysis, Synthesis, and Optimization

Cao

et al. 2023

Biomimetics

View full text Add to dashboard Cite

show abstract

“…global thresholds [31], local thresholds [32], and the selfadaptive threshold method using the Otsu algorithm [33]. These methods are relatively fast in processing simple images with less noise but yield poor performance for complicated scenarios and even fail in crack segmentation.…”

Section: Related Workmentioning

confidence: 99%

Multi-CrackNet: A Fast Segmentation and Quantification Combined Method for Rock Discontinuity Traces by Capturing an Image

Lan

Deng

et al. 2022

Geofluids

View full text Add to dashboard Cite

Discontinuity investigation and characterization onsite is a labor-dependent work because current techniques cannot precisely handle multiple discontinuity identifications automatically under different work conditions. This paper proposes the multi-CrackNet which enables us to identify and segment linear discontinuities (joints and cracks) for random types of rock surface. A modified feature extraction network called the multiscale feature fusion pyramid network (MFFPN) has been developed based on FPN to capture and fuse more sensitive texture features of cracks across different types of background. With the help of a new training scheme by setting up 3 stages of training to simulate the human-based learning process, the established model can learn more features steadily and robustly from well-labelled databases. Additionally, a hybrid pixel-level quantification method is proposed to automatically compute the length, width, and inclination of cracks. Results show that the proposed method can achieve a detection accuracy of 87.1% for 1 to 9 sets of cracks on the rock surface across different types of rock. Case studies in Anshan West are provided to verify the reliability and accuracy of our method in macrolinear discontinuity identification and quantification, which sees great potentials in site investigation by saving a large amount of labor force.

show abstract

“…Some of the research studies on crack failure process images are qualitative studies, which only describe the crack distribution of broken coal bodies 26,27 . The other part of the study is semi‐quantitative, only at the partial time of crack growth, without a kind of continuous observation 28 …”

Section: Introductionmentioning

confidence: 99%

“…26,27 The other part of the study is semi-quantitative, only at the partial time of crack growth, without a kind of continuous observation. 28 The study of coal mass cracks is divided into laboratory tests and engineering field measurements. In the laboratory, the loading methods include different stress paths such as compression failure, cyclic loading, and graded loading 29 ; the loading machines are divided into single-axis and three-axis 30,31 ; the observation methods include camera shooting and CT scanning.…”

Section: Introductionmentioning

confidence: 99%

A new digital surface crack image monitoring technology for coal failure

Qiao

Nie

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

The experimental study on the variation law of coal fracture and stress was carried out in the laboratory and engineering fields, respectively. A multiparameter monitoring system including electromagnetic radiation and a high-speed camera was built, and three stress paths, uniaxial compression, cyclic loading, and graded loading, were used to monitor the dynamic expansion process of surface cracks during uniaxial compression failure of coal specimens. Through the quantitative analysis of the electromagnetic radiation signal in the crack propagation process, it is found that the electromagnetic radiation and the stress change trend are consistent, and the electromagnetic radiation signal is ahead of the failure of coal-generating rock mass 1-2 s. The surface crack changes after the peak value of electromagnetic radiation and presents a stepwise growth trend, crack length changes on the millisecond time scale, and the crack propagation speed is about 2000 mm/s. The surface cracks appear when the stress reaches a certain degree, and the propagation of the principal cracks is consistent with the failure of the specimen. The electromagnetic radiation value of the coal mass from static period to dynamic is analyzed by using electromagnetic radiation at the engineering site, and it was found that the electromagnetic radiation is consistent with the stress distribution of the mining face. Through normalization, the variation rule of electromagnetic radiation in laboratory and engineering sites is similar, but the peak value of electromagnetic radiation in engineering sites is more significant. Therefore, electromagnetic radiation has a good monitoring effect on the stress distribution and cracks propagation of underground coal mining working faces, which could guide the layout of underground drilling.

show abstract

A novel approach for fracture skeleton extraction from rock surface images

Cited by 25 publications

References 26 publications

Application of Swarm Intelligence Optimization Algorithms in Image Processing: A Comprehensive Review of Analysis, Synthesis, and Optimization

Application of Swarm Intelligence Optimization Algorithms in Image Processing: A Comprehensive Review of Analysis, Synthesis, and Optimization

Multi-CrackNet: A Fast Segmentation and Quantification Combined Method for Rock Discontinuity Traces by Capturing an Image

A new digital surface crack image monitoring technology for coal failure

Contact Info

Product

Resources

About