Corrosion and coating defect assessment of coal handling and preparation plants (CHPP) using an ensemble of deep convolutional neural networks and decision-level data fusion

Yu, Yang; Hoshyar, Azadeh Noori; Samali, Bijan; Zhang, Guang; Rashidi, Maria; Mohammadi, Masoud

doi:10.1007/s00521-023-08699-3

Cited by 38 publications

(16 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FNR = FN TP + FN (13) where TP (true positive) is the number of correctly detected buildings; FP (false positive) represents the number of incorrectly detected buildings. FN (false negative) stands for the number of undetected buildings.…”

Section: Building Detection Results Comparisonmentioning

confidence: 99%

“…On the other hand, deep learning algorithms are typically used in the second category. In recent years, deep learning [12,13] has become a crucial technique for remote sensing, and has been extensively used in various remote sensing applications, including image processing. This study in [14] analyzes the approaches and trends in the field of deep learning for remote sensing, highlighting its potential and its wide application range.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Building Detection in High-Resolution Remote Sensing Images by Enhancing Superpixel Segmentation and Classification Using Deep Learning Approaches

et al. 2023

View full text Add to dashboard Cite

Accurate building detection is a critical task in urban development and digital city mapping. However, current building detection models for high-resolution remote sensing images are still facing challenges due to complex object characteristics and similarities in appearance. To address this issue, this paper proposes a novel algorithm for building detection based on in-depth feature extraction and classification of adaptive superpixel shredding. The proposed approach consists of four main steps: image segmentation into homogeneous superpixels using a modified Simple Linear Iterative Clustering (SLIC), in-depth feature extraction using an variational auto-encoder (VAE) scale on the superpixels for training and testing data collection, identification of four classes (buildings, roads, trees, and shadows) using extracted feature data as input to an Convolutional Neural Network (CNN), and extraction of building shapes through regional growth and morphological operations. The proposed approach offers more stability in identifying buildings with unclear boundaries, eliminating the requirement for extensive prior segmentation. It has been tested on two datasets of high-resolution aerial images from the New Zealand region, demonstrating superior accuracy compared to previous works with an average F1 score of 98.83%. The proposed approach shows potential for fast and accurate urban monitoring and city planning, particularly in urban areas.

show abstract

Section: Building Detection Results Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Building Detection in High-Resolution Remote Sensing Images by Enhancing Superpixel Segmentation and Classification Using Deep Learning Approaches

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Combined with the analysis of Design Expert software [28,29], the optimum values were achieved within the experimentally set process parameters of 25 kHz ultrasonic frequency, 300 W ultrasonic power, and 4 mm action distance. In this case the porosity was 2.99%, fracture rate was 3.36%, tensile strength was 108.73 MPa, bending strength was 116.81 MPa, and impact strength was The porosity was 5.68%, the fracture rate was 2.79%, the tensile strength was 98.36 kJ•m −2 , the bending strength was 106.52 MPa, and the impact strength was 49.22 kJ•m −2 without ultrasonic impregnation.…”

Section: Effect Of Ultrasonic Parameters On Mechanical Propertiesmentioning

confidence: 99%

Experimental investigation on effects of ultrasonic process parameters on the degree of impregnation of BF/PP composites

Liu,

Yang,

et al. 2024

Mater. Res. Express

Self Cite

View full text Add to dashboard Cite

The properties of basalt fiber reinforced polypropylene composites (BF/PP) were improved by ultrasonic treatment of resin building pressure to assist melt impregnation. Combined with the study of ultrasonic pressure building theory, the mechanical properties of the modified composites were analyzed using the characterization of tensile, flexural and impact strengths in response to porosity and fracture rate. The effects of ultrasonic power, frequency and distance of action on resin building pressure and composite properties were investigated. The results showed that the best effect was achieved when the ultrasonic frequency was 25 kHz, the ultrasonic power was 300 W, and the action distance was 4 mm, at which time the porosity of the prepreg was reduced to 2.99%, the fracture rate was 3.36%, and the tensile, flexural, and impact strengths were 108.73 MPa, 116.81 MPa, and 51.59 KJ.m-2.

show abstract

“…A new round of scientific and technological industrial change with intelligence as the core is emerging. The continuous integration of artificial intelligence technology with various fields of society is already a general trend, which is gradually changing the existing industrial forms, business models, and lifestyles [1,2]. The current methods for the motorcycle indirect vision test typically necessitate manual testing at a fixed testing site with multiple individuals working in unison, and the outcomes are frequently subjective.…”

Section: Introductionmentioning

confidence: 99%

A visual area detection algorithm based on mirror splicing for motorcycle indirect vision test

Li,

Liu,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Motorcycle indirect vision devices are important safety components, and the visual area is required to meet industry standards. There is a need for effective algorithms to detect and analyze the relevant visual areas within these mirrors to enhance motorcycle safety. However, it is a challenge to test rearview mirror vision in unstructured environments given variations in illumination, occlusion, and object scale. We propose a visual area detection algorithm based on mirror stitching for a motorcycle indirect vision test. First, an edge-based VGG16-Unet (EBV16-Unet) network is employed to extract binocular mirror information and eliminate the complex background. Second, gradient-based topology-preserving image stitching and multi-band hybrid Laplacian pyramid-based image blending algorithms are utilized to complete binocular mirror information acquisition. Finally, a sequential detection method for adaptive marker color and shape features is used to establish the visual area. The EBV16-Unet algorithm achieved an accuracy of 98.63% for precision, 98.71% for recall, 98.58% for F1, and 98.37% for mean intersection-over-union (MIOU), surpassing the comparative models of PSPNet, DeepLab v3+, and HRNet and exhibited superior generalization ability. The binocular vision splicing effect experiment revealed a horizontal splicing error of 0.114322 ± 0.0674 and vertical splicing error of 0.124287 ± 0.063302, calculated using a standard checkerboard. The rearview mirror vision test operation experiment results confirm that the Motorcycle Indirect Vision Test System (MIVTS) offers convenience, simplicity and high accuracy. MIVTS successfully accomplishes the unstructured motorcycle rearview mirror vision test, thereby establishing an advanced theoretical foundation for computer vision-based automated vehicle inspection.

show abstract

Corrosion and coating defect assessment of coal handling and preparation plants (CHPP) using an ensemble of deep convolutional neural networks and decision-level data fusion

Cited by 38 publications

References 39 publications

Building Detection in High-Resolution Remote Sensing Images by Enhancing Superpixel Segmentation and Classification Using Deep Learning Approaches

Building Detection in High-Resolution Remote Sensing Images by Enhancing Superpixel Segmentation and Classification Using Deep Learning Approaches

Experimental investigation on effects of ultrasonic process parameters on the degree of impregnation of BF/PP composites

A visual area detection algorithm based on mirror splicing for motorcycle indirect vision test

Contact Info

Product

Resources

About