Vision-Based Detection of Bolt Loosening Using YOLOv5

Sun, Yuhang; Li, Mengxuan; Dong, Ruiwen; Chen, Wei-Yu; Jiang, Dong

doi:10.3390/s22145184

Cited by 29 publications

(16 citation statements)

References 44 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This idea omits the complex candidate box selection and calculation steps in the two-stage algorithm. Therefore, the running speed of the algorithm is far faster than that of the two-stage detection algorithm [ 27 , 28 , 29 ]. The representative algorithms are the YOLO algorithm and the SSD algorithm.…”

Section: Introductionmentioning

confidence: 99%

YOLOv7-RAR for Urban Vehicle Detection

Zhang

Sun

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

Aiming at the problems of high missed detection rates of the YOLOv7 algorithm for vehicle detection on urban roads, weak perception of small targets in perspective, and insufficient feature extraction, the YOLOv7-RAR recognition algorithm is proposed. The algorithm is improved from the following three directions based on YOLOv7. Firstly, in view of the insufficient nonlinear feature fusion of the original backbone network, the Res3Unit structure is used to reconstruct the backbone network of YOLOv7 to improve the ability of the network model architecture to obtain more nonlinear features. Secondly, in view of the problem that there are many interference backgrounds in urban roads and that the original network is weak in positioning targets such as vehicles, a plug-and-play hybrid attention mechanism module, ACmix, is added after the SPPCSPC layer of the backbone network to enhance the network’s attention to vehicles and reduce the interference of other targets. Finally, aiming at the problem that the receptive field of the original network Narrows, with the deepening of the network model, leads to a high miss rate of small targets, the Gaussian receptive field scheme used in the RFLA (Gaussian-receptive-field-based label assignment) module is used at the connection between the feature fusion area and the detection head to improve the receptive field of the network model for small objects in the image. Combining the three improvement measures, the first letter of the name of each improvement measure is selected, and the improved algorithm is named the YOLOv7-RAR algorithm. Experiments show that on urban roads with crowded vehicles and different weather patterns, the average detection accuracy of the YOLOv7-RAR algorithm reaches 95.1%, which is 2.4% higher than that of the original algorithm; the AP50:90 performance is 12.6% higher than that of the original algorithm. The running speed of the YOLOv7-RAR algorithm reaches 96 FPS, which meets the real-time requirements of vehicle detection; hence, the algorithm can be better applied to vehicle detection.

show abstract

Section: Introductionmentioning

confidence: 99%

YOLOv7-RAR for Urban Vehicle Detection

Zhang

Sun

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Zhang (2020) et al proposed a bolt loosening detection method based on Fast-RCNN algorithm, using the bolt thread heights under different loosening states. Sun et al (2022) identified the marks on the nut and the screw to determine the loosening of bolt based on YOLOv5.…”

Section: Introductionmentioning

confidence: 99%

Image-based bolt self-localization and bolt-loosening detection using deep learning and an improved homography-based prospective rectification method

Xie

Luo

Tang

et al. 2023

Advances in Structural Engineering

View full text Add to dashboard Cite

The bolt loosening detection method has been paid attention by engineering and academic scholars. The presented methods only focus on the identification of the bolt based on deep learning, and the problem of bolt localization and the influence of shadow on distortion correction is seldom studied. In this paper, a bolt self-localization method based on YOLOv4 deep learning algorithm is proposed. A bolt numbering rule is established and the deep learning is introduced to identify the number and locate the bolt. A new square bolt gasket is proposed and four corner points are used for distortion correction. In order to reduce the influence of shadows, a grayscale enhancement strategy is proposed to improve the correction stability. Finally, a laboratory flange joint is used to verify the proposed method. The results show that the bolt self-localization method is feasible and the new bolt gasket can effectively improve the stability of distortion correction and bolt loosening detection.

show abstract

“…Pan et al 35 combine target detection algorithm and target tracking algorithm to detect and track bolt looseness. Sun et al 36 use YOLOv5 algorithm to detect bolts and marks on bolts, and calculate the bolt loosening angle according to the central coordinates of two types of boundary frames. Huynh et al 37 detected and cut the bolt area through convolutional neural network, and then identified the bolt loosening angle based on Hough transform.…”

Section: Introductionmentioning

confidence: 99%

Bolt looseness detection based on Canny edge detection algorithm

Song

Cui

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryAiming at current serious problems that the bolt looseness can cause heavy damages and the manual bolt looseness detection is ineffective, this study presents a bolt looseness detection method based on Canny edge detector. First, HSV (hue, saturation, value) color space is used to extract the area of mark bar. Then, after expanding, eroding and median filtering the image, Canny edge detector is used to segment the marker area to extract its edge. Last, the fitted slope of edge is used to judge whether the bolt is loose. The experimental results show that the proposed method has F1 score of 88.37%, contributing to the automated detection of bolt looseness.

show abstract

Vision-Based Detection of Bolt Loosening Using YOLOv5

Cited by 29 publications

References 44 publications

YOLOv7-RAR for Urban Vehicle Detection

YOLOv7-RAR for Urban Vehicle Detection

Image-based bolt self-localization and bolt-loosening detection using deep learning and an improved homography-based prospective rectification method

Bolt looseness detection based on Canny edge detection algorithm

Contact Info

Product

Resources

About