A Robotics Inspection System for Detecting Defects on Semi-specular Painted Automotive Surfaces

Akhtar, Sohail; Tandiya, Adarsh; Moussa, Medhat; Tarry, Cole

doi:10.1109/icra40945.2020.9196980

Cited by 5 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to geometry, the reflectivity of the surface has also been studied by researchers. [7] developed a method that visually analyzed the reflection of a known projection pattern over the surface, where both the pattern generator and the camera were manipulated by a robot. Based on sensor fusion, [8] addressed the automatic defect detection on car body surfaces during a painting process, where only flat regions with smooth changes in slope, concavities, edges, and corners were considered.…”

Section: Problemmentioning

confidence: 99%

A Sensor-Based Robotic Line Scan System With Adaptive ROI for Inspection of Defects Over Convex Free-Form Specular Surfaces

et al. 2022

View full text Add to dashboard Cite

In this paper, we present a novel sensor-based system to perform defect inspection tasks automatically over free-form specular surfaces. The inspection procedure is performed by a robotic manipulator equipped with a line scanner system. Taking the geometric and optical parameters into consideration, our algorithm computes a flexible scanning path. Based on a mesh model, the system segments the convex surface into areas with similar curvatures, then adaptively adjusts the line sensor's scanning range to ensure the complete coverage of the surface. We consider the scanning efficiency through constrained optimization. To align the computed scanning path with the specular object, a real-time workpiece localization algorithm in a coarse-to-fine manner is developed. Our control framework synchronizes the motion of the manipulator and the acquisition of the line scanner for robotic inspection. We also provide an image processing pipeline for automatic defect detection. To validate the proposed formal methodology, we report a detailed experimental study with the developed robotic inspection prototype.

show abstract

Section: Problemmentioning

confidence: 99%

A Sensor-Based Robotic Line Scan System With Adaptive ROI for Inspection of Defects Over Convex Free-Form Specular Surfaces

et al. 2022

View full text Add to dashboard Cite

show abstract

“…With the development of automation and Informa ionization, the assembly line has been transferred from manual assembly line to automatic assembly line, and the identification of the positive and negative faces of fine blanking pinion gears from manual identification to automatic identification has become an important and imminent task. In recent years, non-contact image recognition technology is widely used in the detection of the surface of the parts, Zhou Dinghe [1] used an industrial camera to obtain images of automotive plate-like painted parts, using defect extraction algorithms based on morphology Blob well classified defects identified; Wang Dongsheng [2] used machine vision technology to detect defects on rotary class toothed painted parts, for its rotary class parts size irregularities, the Developing a new inspection equipment for rotary toothed parts; Priyanka Khandelwal [5] achieved noise removal and extraction of crack defects on the surface of automotive parts by using the similar gray value filling method; Yuan Xiao Cui [4] proposed the interclass variance defect segmentation method with target variance weighting, which weights the target variance of the interclass variance of an image to ensure a high detection rate of the defects and a low misdetection rate, the Sohail Akhtar, Tatsuya Yamazaki, Jyotismita Chaki, Adarsh Tandiya, M Dhivya, BLAYVAS I, Carsten Steger and others [5][6][7][8][9][10][11][12][13][14] have done a lot of research in the detection of defects on surfaces such as circuit boards, metals, and so on, and have done a lot of research in the areas of image enhancement, region segmentation, edge extraction, Blob detection etc. many algorithms are proposed.…”

Section: Introductionmentioning

confidence: 99%

Research on the Method of Identifying the Collapsed Angle Surface of Fine Punching Small Gear

Tang,

Chen,

Song

et al. 2024

IJEH

View full text Add to dashboard Cite

Aiming at the requirement of automatic assembly of automobile rear wiper for automatic identification of the collapsed corner surface of finely-punched pinion, this paper proposes a method based on the mean value of the area of multi-toothed region of finely-punched pinion as the characteristic parameter, which can better identify the collapsed corner surface. Firstly, the industrial camera is used to obtain the pinion image, and the Halcon operator is used to fit the circle in the pre-segmented region to obtain the pinion circle position parameter, and the parameter is used as the reference to accurately segment the toothed annulus ROI, and then carry out the dynamic thresholding of the region, merging the regions, shape convex package transformation, and the conditional filtering to obtain the multiple toothed regions, and then rank the toothed regions, and the maximum top three toothed regions area mean value is the feature parameter to achieve the fine blanking pinion surface automatic identification of the collapsed corner surface. The mean value of the area of the first three tooth-shaped areas is used as the characteristic parameter to achieve the identification of the collapsed angle surface of the fine blanking pinion gear. The application on the assembly line shows that the recognition accuracy of this method reaches 99.9%, with good robustness and stable operation, which meets the production requirements, and also provides a method for the recognition of collapsed corner surfaces of other fine blanking parts.

show abstract

A Digital Twin-Based Intelligent Robotic Measurement System for Freeform Surface Parts

Tang

Wang

Tan

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

A Robotics Inspection System for Detecting Defects on Semi-specular Painted Automotive Surfaces

Cited by 5 publications

References 29 publications

A Sensor-Based Robotic Line Scan System With Adaptive ROI for Inspection of Defects Over Convex Free-Form Specular Surfaces

A Sensor-Based Robotic Line Scan System With Adaptive ROI for Inspection of Defects Over Convex Free-Form Specular Surfaces

Research on the Method of Identifying the Collapsed Angle Surface of Fine Punching Small Gear

A Digital Twin-Based Intelligent Robotic Measurement System for Freeform Surface Parts

Contact Info

Product

Resources

About