Influence of Uneven Lighting on Quantitative Indicators of Surface Defects

Konovalenko, І. V.; Maruschak, Pavlo; Kozbur, Halyna; Brezinová, Janette; Brezina, Jakub; Nazarevich, Bohdan; Shkira, Yaroslav

doi:10.3390/machines10030194

Cited by 33 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset used in this study is obtained from the InfiRay Infrared Open Platform [20], which is an open dataset dedicated to infrared ships. The creation of an infrared dataset requires accurate camera calibration and proper positioning to obtain high-quality and precise infrared images [21]. This dataset is generated through on-site testing and adjustments, employing a fixed position and stable lighting conditions within the same scene.…”

Section: Infrared Ship Datasetmentioning

confidence: 99%

GT-YOLO: Nearshore Infrared Ship Detection Based on Infrared Images

Wang,

Huo

et al. 2024

JMSE

View full text Add to dashboard Cite

Traditional visible light target detection is usually applied in scenes with good visibility, while the advantage of infrared target detection is that it can detect targets at nighttime and in harsh weather, thus being able to be applied to ship detection in complex sea conditions all day long. However, in coastal areas where the density of ships is high and there is a significant difference in target scale, this can lead to missed detection of some dense and small targets. To address this issue, this paper proposes an improved detection model based on YOLOv5s. Firstly, this article designs a feature fusion module based on a fusion attention mechanism to enhance the feature fusion of the network and introduces SPD-Conv to improve the detection accuracy of small targets and low-resolution images. Secondly, by introducing Soft-NMS, the detection accuracy is improved while also addressing the issue of missed detections in dense occlusion situations. Finally, the improved algorithm in this article increased mAP0.5 by 1%, mAP0.75 by 5.7%, and mAP0.5:0.95 by 5% on the infrared ship dataset. A large number of comparative experiments have shown that the improved algorithm in this article is effective at improving detection capabilities.

show abstract

Section: Infrared Ship Datasetmentioning

confidence: 99%

GT-YOLO: Nearshore Infrared Ship Detection Based on Infrared Images

Wang,

Huo

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…Modern investigations showed that neural network-based defect detection methods allow high accuracy to be reached in the recognition of different classes of surface defects [22][23][24]. However, investigating and streamlining neural networks' capabilities and limitations in detecting, classifying, and calculating the parameters of the most common group defects appear crucial [25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Surface Illumination as a Factor Influencing the Efficacy of Defect Recognition on a Rolled Metal Surface Using a Deep Neural Network

Maruschak,

Konovalenko,

Osadtsa

et al. 2024

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Modern neural networks have made great strides in recognising objects in images and are widely used in defect detection. However, the output of a neural network strongly depends on both the training dataset and the conditions under which the image was acquired for analysis. We have developed a software–hardware method for evaluating the effect of variable lighting on the results of defect recognition using a neural network model. The proposed approach allows us to analyse the recognition results of an existing neural network model and identify the optimal range of illumination at which the desired defects are recognised most consistently. For this purpose, we analysed the variability in quantitative parameters (area and orientation) of damage obtained at different degrees of illumination for two different light sources: LED and conventional incandescent lamps. We calculated each image’s average illuminance and quantitative parameters of recognised defects. Each set of parameters represents the results of defect recognition for a particular illuminance level of a given light source. The proposed approach allows the results obtained using different light sources and illumination levels to be compared and the optimal source type/illuminance level to be figured out. This makes implementing a defect detection environment that allows the best recognition accuracy and the most controlled product quality possible. An analysis of a steel sheet surface showed that the best recognition result was achieved at an illuminance of ~200 lx. An illuminance of less than ~150 lx does not allow most defects to be recognised, whereas an illuminance larger than ~250 lx increases the number of small objects that are falsely recognised as defects.

show abstract

“…Therefore, it is important from the perspective of real-time execution to have a reduction in the size of fusion architectures while maintaining comparable performance [10]. Besides, reduced architectures may have different level of robustness to change in illumination level [11]. Furthermore, this reduction can also be used to extend the perception systems with uncertainty handling methods [12], [13].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Architecture Reduction on Camera-Lidar Fusion for Autonomous Vehicles

Geletu

Josso-Laurain

Devanne

et al. 2022

2022 2nd International Conference on Computers and Automation (CompAuto)

View full text Add to dashboard Cite

Autonomous vehicles (AVs) are the dream of the present era and are close to become reality. In AVs, perception is a challenging task. It gives understanding of the driving environment. One type of such task is road detection, where the goal is to segment the road area into drivable and nondrivable using multi-modal sensors like cameras and lidars. For their ability on a road detection task, deep neural networks, with an encoder-decoder architecture, are chosen in this paper. Since deep learning models have large size and AVs have constrained computational power, model reduction is important. Therefore, architecture reduction of a convolutional neural network is proposed on a deep learning based multi-modal fusion model. This model is used as the baseline of our work, and camera and lidar are its modalities. The baseline model's weights that are used to fuse the camera processing pipeline with the lidar pipeline are analysed. The analysis shows that the strength of fusion between the two modalities changes from layer to layer. Using this result and a support from generic encoder-decoder architecture, a reduced architecture is proposed. The latter is further processed by removing some layers of the baseline to produce a lite model. The reduced architectures are validated to show comparable performance with the baseline. Furthermore, both the reduced architectures outperform the baseline on a brightness adjusted camera image. These reduced architectures can be used from the perspective of embedded system, or they can be used to boost performance by appending additional algorithm.The training and validation are done on the KITTI dataset.

show abstract

Influence of Uneven Lighting on Quantitative Indicators of Surface Defects

Cited by 33 publications

References 20 publications

GT-YOLO: Nearshore Infrared Ship Detection Based on Infrared Images

GT-YOLO: Nearshore Infrared Ship Detection Based on Infrared Images

Surface Illumination as a Factor Influencing the Efficacy of Defect Recognition on a Rolled Metal Surface Using a Deep Neural Network

Deep Learning Based Architecture Reduction on Camera-Lidar Fusion for Autonomous Vehicles

Contact Info

Product

Resources

About