Edge Detection Based on General Grey Correlation and LoG Operator

Zhang, Jianxin; Chang, Wei; Wu, Lang

doi:10.1109/aici.2010.106

Cited by 9 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, the correlation degree is small. Under the condition of limited experimental data and less workload, this method can obtain the results reflecting the inherent laws of the system under study [30]. As the model requires all data to be positive, the negative temperature is converted into a fraction according to the engineering characteristics.…”

Section: Gra Modelmentioning

confidence: 99%

Operation analysis of C3-MR process cold box by grey system theory

Yang

Xiao

Jia³

2021

SN Appl. Sci.

View full text Add to dashboard Cite

In this paper, the problems of high refrigerant line differential pressure and uneven distribution of cold energy in cold box regulation under C3-MR process are studied. Five reasons are predicted by engineering performance. Using gas chromatography experiment and grey system pure mathematics analysis, it is determined that the main causes of the problem are unreasonable distribution ratio of each group of mixed refrigerants and disordered latent heat of vaporization of refrigerants. Furthermore, the grey system model is used to study: 1. grey relation analysis model shows that the correlation degree of T3 temperature measuring point is 0.8552, which is the only main factor. The abnormal working condition is determined by the project to be caused by incorrect proportion of N2 components. 2. According to GM(1,N) model, the driving term of T3 temperature measuring point is 3.8304, which needs to be supplemented with N2 component to eliminate the problem. 3. After adding N2 to 10% (mol component), abnormal working conditions disappeared. The GM(1,N) model is used again to verify that the difference of driving results is small, the average relative error is 24.91%, and the accuracy of the model is in compliance.

show abstract

Section: Gra Modelmentioning

confidence: 99%

Operation analysis of C3-MR process cold box by grey system theory

Yang

Xiao

Jia³

2021

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…Automated processing techniques are divided into three categories: traditional image processing, machine learning, and deep learning. Traditional image processing-based methods (e.g., region growth [9][10][11], threshold segmentation [12], and edge detection [13,14]) and machine learning-based methods (e.g., supervised and unsupervised machine learning) cannot adapt to the complex background in the shield tunnel due to poor generalization capabilities along with the demand for manually designed features and adjusted parameters. On the other hand, the latest deep learning-based methods can automatically obtain rich and high-level features given their self-learning capability.…”

Section: Introductionmentioning

confidence: 99%

Improved SOLOv2 detection method for shield tunnel lining water leakages

Feng¹,

Zhang²,

Feng³

et al. 2023

Journal of Intelligent Construction

View full text Add to dashboard Cite

With the rapid development of urban metros, the detection of shield tunnel leakages has become an important research topic. Progressive technological innovations such as deep learning-based methods provide an effective way to detect tunnel leakages accurately and automatically. However, due to the complex shapes and sizes of leakages, it is challenging for existing algorithms to detect such defects. To address these issues, this paper proposes a novel deep learning-based model named segmenting objects by locations network v2 for tunnel leakages (SOLOv2-TL), which is enhanced by ResNeXt-50, deformable convolution, and path augmentation feature pyramid network (PAFPN). In the SOLOv2-TL, ResNeXt-50 coupled with deformable convolution is the backbone for boosting feature extraction ability that would enable the model sensitivity to leakages of different shapes. The PAFPN is introduced as the neck to reduce the loss of leakage information and more accurately assign leakages of different sizes to their corresponding feature levels. The superior performances of ResNeXt-50 with deformable convolution and PAFPN were validated by ablation tests. Moreover, the segmentation results obtained by SOLOv2-TL were compared with those by the mask region-based convolutional neural network (Mask R-CNN), Cascade Mask R-CNN, and SOLO which demonstrated that the mAP, mAP 50 , and mAP 75 of SOLOv2-TL are higher than those of the other methods, where mAP indicates the mean mask average precision (AP) at intersection over union (IoU) = 0.50:0.05:0.95, mAP 50 refers to the mean mask AP with an IoU threshold of 0.50, and mAP 75 denotes the mean mask AP with an IoU threshold of 0.75. Finally, a leakage area quantification method is presented.

show abstract

“…There are also geometric feature‐based segmentation methods which increase the complexity of the algorithm due to morphological variability. After separating the hand image, the contour extraction traditionally uses the Roberts operator, the Sobel operator, and the Laplacian of Gaussian operator [18]. These algorithms are simple, but the noise content of the extracted edge is large, and the forged edges generated by these noises make the detection accuracy low.…”

Section: Introductionmentioning

confidence: 99%

“…The colour domain is first selected by this model, and the colour domain is divided into blocks. The hand is separated according to the relative characteristics of the block, and the hand image is extracted and separated [18–20]. The hand image is used and the image is extracted by the adaptive threshold method to calculate the upper and lower thresholds for Canny gesture contour extraction.…”

Section: Introductionmentioning

confidence: 99%