Automatic Rebar Counting using Image Processing and Machine Learning

Wang, Han; Polden, Joseph; Jirgens, Josiah; Yu, Ziping; Pan, Zengxi

doi:10.1109/cyber46603.2019.9066509

Cited by 14 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xiaohu et al [2] proposed a contour-based rebar detection and counting method, using morphological processing and contour detection to obtain the positions and quantity of rebars. Wang et al [3] used image processing methods such as Canny edge detection and Hough transform and machine learning methods such as support vector machines and decision trees to convert the object detection problem into an image classification problem to count steel bars. However, since traditional image processing methods are sensitive to changes in ambient illumination, and there are problems such as irregular shapes of rebar end faces in applications, it is difficult to improve accuracy and robustness.…”

Section: Introductionmentioning

confidence: 99%

Dense rebar end face segmentation based on YOLACT_REBAR instance segmentation network

Yuan,

Zhou,

Deng

et al. 2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

Automatic rebar counting in the bundled steel bar image require urgent solution in the steel and construction application scenarios. Traditional image processing methods perform badly because the rebar end faces are in irregular shape and highly dense. Focusing on the characteristics of dense small objects in the bundled rebar images, this paper proposes YOLACT_REBAR instance segmentation network. We make improvements from two aspects: network structure and inference process. For network structure improvement, in view of the characteristics of the steel bar end face being a small target, we optimize the original model by connecting the second layer of its backbone network to FPN (Feature Pyramid Network) to obtain larger feature maps, thereby enhancing the model's accuracy in dense small target segmentation. For the inference process, in view of the dense characteristics of steel bar end faces, traditional Non-Maximum value Suppression is used to replace the fast Non-Maximum value Suppression, and the IOU (Intersection-Over-Union) deduplication strategy is used to remove redundant bounding boxes, thereby reducing the network's false detection. Experimental results on self-constructed dataset show that compared with the original YOLACT model and other object detection models, our proposed model demonstrate improved Precision, Recall and mIOU performance. The proposed YOLACT_REBAR model can make a precise segmentation of each rebar end face, which will facilitate subsequent applications such as rebar counting and automatic plate welding.

show abstract

Section: Introductionmentioning

confidence: 99%

Dense rebar end face segmentation based on YOLACT_REBAR instance segmentation network

Yuan,

Zhou,

Deng

et al. 2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

show abstract

“…Since research on deep learning was carried out in various sub-branches of civil engineering, a limited number of studies are included here for information purposes only. Yang et al [14], Fan et al [15], and Wang et al [16] developed deep learning-based methods for counting rebars in stock using images. These three studies are the closest ones to the subject considered in this work.…”

Section: Introductionmentioning

confidence: 99%

An Approach for Brick Wall Quantity Take-Off by U-Net Method Based on Deep Learning

BAŞAĞA,

HACIEFENDİOĞLU

2024

Turkish Journal of Civil Engineering

View full text Add to dashboard Cite

This study presents a deep learning-based method for the quantity take-off in the construction industry. In this context, the brick wall quantity calculation was performed automatically over two-dimensional (2D) pictures by the U-Net method. 280 photos were first taken in the field at different distances and angles. 1960 images were, then, obtained by augmentation to increase the training accuracy. Pixel calculation of the automatically masked area in the images was made for wall estimation. The wall area was calculated by comparing this pixel value with that of the reference brick surface area. The method was tested on four sample photos including different wall images. A parametric study was carried out to reduce the errors. In the study, it has been shown that the proposed method is suitable for brick quantity calculation. In addition, it was concluded that the photo should be taken as close as possible, and more than one brick should be taken as a reference in close-up photos to increase the accuracy.

show abstract

“…Wang H et al [15] combined Canny edge detection, circular Hough transform, and a CNN model to calculate the number of rebars; the highest detection accuracy of this model was 95.99%. Zhu Y et al [16] proposed a CNN-based fusion model for rebar localization and segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…One essential task in the intelligent application is the detection of the number of rebars, which requires high detection accuracy because a rebar is expensive and there are many of them in actual use, and both misdetection and omission need to be identified manually in a large number of marked points; therefore, current rebars are still manually inventoried. It is proposed in the literature [12,15] that traditional image processing techniques can be used to preprocess the input image and combine the area and morphology for matching counts, but they do not perform well in dense or occluded situations. To further improve the efficiency and accuracy of rebar counting, a study on rebar identification using a neural network was proposed in the literature [18], which significantly improved the detection efficiency but was slightly inferior in accuracy.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism

Zheng

Zhou

2023

Applied Sciences

View full text Add to dashboard Cite

With the rapid development of computer vision and machine vision, methods based on deep learning have achieved good results in the field of object detection, identification, and tracking. However, for the detection and identification of rebars in smart construction sites, it is very difficult to perform accurate real-time detection of rebars by using object detection technology on the equipment in the field because of the problems of the dense cross-section between bundled bars, the mutual adhesion of cross-section boundaries, and mutual occlusion between cross-sections. To address the above problems, we propose a multi-scale rebar detection network RebarNet with an embedded attention mechanism based on YOLOv5, combining the K-means++ algorithm, attention mechanism, a newly designed SD_IoU Loss, and multi-scale feature fusion, aiming to solve the problems of missed and false detection in dense small object detection. Due to the problems of scarce rebar cross-section datasets, no publicly available large datasets, and weak rebar cross-sectional features, we constructed a new rebar cross-sectional dataset, used a semi-automatic annotation method to annotate part of the dataset, and then used the data enhancement algorithm to expand the rebar dataset. The experimental results show that the average accuracy (mAP) of our proposed RebarNet network is 97.9%, which is comparable to mainstream target detection algorithms such as Faster R-CNN, SSD, RetinaNet, CenterNet, CornerNet, YOLOv3, YOLOv4, and YOLOv5s. mAP0.5 is improved by 8.1%, 13%, 26.4%, 25.8%, 26.2%, 11.7%, 7.6%, and 9%, respectively. In addition, the frames per second (FPS) transmission reaches 89 frames per second, the model weight is only 17.0 MB. In summary, the proposed RebarNet can effectively reduce missed and false detections in the rebar counting detection task based on real-time detection.

show abstract

Automatic Rebar Counting using Image Processing and Machine Learning

Cited by 14 publications

References 8 publications

Dense rebar end face segmentation based on YOLACT_REBAR instance segmentation network

Dense rebar end face segmentation based on YOLACT_REBAR instance segmentation network

An Approach for Brick Wall Quantity Take-Off by U-Net Method Based on Deep Learning

A Multi-Scale Rebar Detection Network with an Embedded Attention Mechanism

Contact Info

Product

Resources

About