Detección de Defectos en Carrocerías de Vehículos Basado en Visión Artificial: Diseño e Implantación

Tornero, Josep; Armesto, Leopoldo; Mora, Marta C.; Montés, Nicolás; Herráez, Álvaro; Asensio, José L. Gómez

doi:10.1016/j.riai.2011.11.010

Cited by 18 publications

(30 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…First, note how our proposal uses the difference between two consecutive frames (i k − i k−1 ), thereby reducing the effect of the diffuse light counterpart. In AppendixA we empirically demonstrate this statement, comparing the result obtained with our method with the result described in [5,6]. On the other hand, with the square of this difference, we try to maximize the effect of the contrast between low and high levels of pixel intensity.…”

Section: Pre-processing Stepmentioning

confidence: 77%

“…This means that the approach is able to detect defects in areas that are very difficult to inspect, such as handles for example, assuming of course that the area is well illuminated. Thus, the paper describes a two-step algorithm: a new pre-processing step (image fusion algorithm), which is more robust when faced with environmental illumination pollution (or diffuse light) than, for example, and as is proved in this paper, the one used in [5,6]; and subsequently, we present a new post-processing step to extract the image background using a local directional blurring in order to make it possible to detect defects on style lines, edges and corners.…”

Section: Introductionmentioning

confidence: 94%

“…4 shows the difference between the fusion image resulting from the proposed fusion strategy Fig. 4(b) and that obtained by one of the most successful systems in the automotive industry [6] to date Fig. 4(a).…”

Section: Pre-processing Stepmentioning

confidence: 99%

“…This system, described in [5,6], uses a moving structure made up of several light bars (fluorescent tubes at high-frequency) and a set of cameras in fixed positions around the stationary car body, and is able to detect defects of up to 0.2mm in diameter, speeding up and improving the quality of the manual inspection carried out until that point. Unfortunately, as with previous research, only flat surfaces and those with smooth slope changes are inspected, meaning again that all style lines, edges and corners are excluded.…”

Section: Introductionmentioning

confidence: 99%

“…This approach tries to cover as much area as possible by bringing the vision and illumination systems close to the body surface, but the details of the detection algorithm are not clear or well explained. In this approach, the area that is not expected can be reduced and the system could cover a much larger area compared with [5,6]. The main problem of this approach is with regard to cycle time production requirements, since it takes a long time to cover the entire surface of the car body and, as far as we are aware, it is still currently an industrial prototype.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

On the detection of defects on specular car body surfaces

Molina

Solanes

Arnal

et al. 2017

Robotics and Computer-Integrated Manufacturing

Self Cite

View full text Add to dashboard Cite

The automatic detection of small defects (of up to 0.2mm in diameter) on car body surfaces following the painting process is currently one of the greatest issues facing quality control in the automotive industry. Although several systems have been developed during the last decade to provide a solution to this problem, these, to the best of our knowledge, have been focused solely on flat surfaces and have been unable to inspect other parts of the surfaces, namely style lines, edges and corners as well as deep concavities. This paper introduces a novel approach using deflectometry-and vision-based technologies in order to overcome this problem and ensure that the whole area is inspected. Moreover, since our approach, together with the system used, computes defects in less than 15 seconds, it satisfies cycle time production requirements (usually of around 30 seconds per car). Hence, a two-step algorithm is presented here: in the first step, a new pre-processing step (image fusion algorithm) is introduced to enhance the contrast between pixels with a low level of intensity (indicating the presence of defects) and those with a high level of intensity (indicating the absence of defects); for the second step, we present a novel post-processing step with an image background extraction approach based on a local directional blurring method and a modified image contrast enhancement, which enables detection of defects in the entire illuminated area. In addition, the post-processing step is processed several times using a multi-level structure, with computed image backgrounds of different resolution. In doing so, it is possible to detect larger defects, given that each level identifies defects of 1 Corresponding author. different sizes. Experimental results presented in this paper are obtained from the industrial automatic quality control system QEyeTunnel employed in the production line at the Mercedes-Benz factory in Vitoria, Spain. A complete analysis of the algorithm performance will be shown here, together with several tests proving the robustness and reliability of our proposal.

show abstract

Section: Pre-processing Stepmentioning

confidence: 77%

Section: Introductionmentioning

confidence: 94%

Section: Pre-processing Stepmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On the detection of defects on specular car body surfaces

Molina

Solanes

Arnal

et al. 2017

Robotics and Computer-Integrated Manufacturing

Self Cite

View full text Add to dashboard Cite

show abstract

Defect inspection of coated automobile roofs using a single camera

Zhang

Kikuta

Zhang

et al. 2020

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Automobile surface defects, such as scratches and dents, can largely affect the first impressions of consumers. These defects are likely to occur during the processes of manufacturing and painting. Most global automobile companies still rely on visual inspection to detect the defects, which results in instability and inefficiency in the inspection procedure. In this paper, a low‐cost detection system is proposed. The hardware part of the system consists of only light emitting diode (LED) tubes and a single camera. The software part of the system first obtains defect candidates greedily by thresholding binarization result. Then, candidates in each frame are filtered using a differential image. Finally, as the main contribution, our algorithm further filters the candidates using tracking trajectories of defect candidates over multiple frames. Experimental results demonstrate that our method is able to detect defects while suppressing false‐positive detections and is effective in real‐world situations. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract