Research on the development of illumination control system in machine vision measurement

Sifan, Qu; Zhou, Hu; Gaochao, Tan

doi:10.1109/isdea.2012.395

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The environment of the construction site also has an important impact on the monitoring of construction equipment, to avoid the effects of low light conditions such as shadows and night that reduce the accuracy model of target detection, researchers have worked to improve the model structure to improve the monitoring model for poor lighting conditions [20,21]. In the field of manufacturing, Huang et al [22] introduced a non-contact surface roughness detection method utilizing the adaptive depth fusion capsule network (ADFCNet) model.…”

Section: Introductionmentioning

confidence: 99%

BS-YOLOV8: an intelligent detection model for bearing pin support-piece states of high-rise building machine

Pan,

Zhao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

As the main support part of the working platform of a high-rise building machine, the bearing pin support (BPS) plays a crucial role in the safety and stability of the platform, the conventional method has the problems of low detection efficiency, low accuracy, and high cost. To improve the accuracy and robustness of the detection algorithm under weak light, this paper proposes an intelligent detection algorithm for the BPS-piece states of the BS-YOLOV8, to improve the feature map utilization and reduce the model leakage detection error detection rate, Swin transformer is used to improve the YOLOV8 backbone network. In addition, the BiFormer attention mechanism is used to weigh the feature map to solve the problem of feature information loss in different feature layers and weak lighting conditions, and then the Scylla-IOU loss function is used instead of the original localization loss function to guide the model to learn to generate a predicted bounding box closer to the real target bounding box. Finally, the BS-YOLOV8 algorithm is used to compare with its classical algorithm on the self-constructed dataset of this study, The results show that the mAP0.5, mAP0.5:0.95, and FPS values of the BS-YOLOV8 algorithm reach 97.9%, 96.3% and 40 under normal lighting. The mAP0.5 value reaches 87.6% under low light conditions, which effectively solves the problems of low detection efficiency and poor detection under low light conditions, and is superior compared to other algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

BS-YOLOV8: an intelligent detection model for bearing pin support-piece states of high-rise building machine

Pan,

Zhao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Study on Measuring Medium and Heavy Plate Flatness and Spot Center Extraction Algorithm

Yang

2014

AMR

View full text Add to dashboard Cite

Oblique incidence lasertriangulation was used to detect medium and heavy plate flatness in this paper.The article mainly focused on point laser spot center extraction algorithm. Infielddetection of medium and heavy plate flatness, according to the problem of thepoint laser spot center extraction difficulty in interference condition, andfor enhancing lightness of spot center filed, an extraction algorithm of pointlaser spot center is put forward in this paper which combines threshold methodand square-weighted gray level based on floor board effect and traditionalcentroid method. Under no interference condition, point laser spot centerextraction using traditional centroid method has high accuracy. In the fielddetection with dusts, oil drops, water drops or other interferences,measurement precision has since fallen sharply. On this background, accordingto a kind of point laser spot center with the interference of water drops oroil drops, classification extraction algorithm of point laser spot center wasput forward in this paper. At the first level, the spot and the drop contourwas extracted with Sobel Operators. At the second level, the spot area wasextracted. And then, this spot area center was extracted by a point laser spotcenter extraction algorithm which combines threshold method and square-weightedgray level. And the center we get is point laser spot center. The validationresults show that with the water drop interference, the accuracy with a pointlaser spot center extraction algorithm which combines threshold method andsquare-weighted gray level is obviously improved by 94.17% than the traditionalcentroid method.

show abstract

Research on the development of illumination control system in machine vision measurement

Cited by 2 publications

References 1 publication

BS-YOLOV8: an intelligent detection model for bearing pin support-piece states of high-rise building machine

BS-YOLOV8: an intelligent detection model for bearing pin support-piece states of high-rise building machine

Study on Measuring Medium and Heavy Plate Flatness and Spot Center Extraction Algorithm

Contact Info

Product

Resources

About