Processing 3D Data from Laser Sensor into Visual Content Using Pattern Recognition

Klarák, Jaromír; Kuric, Ivan; Císar, Miroslav; Stanček, Ján; Hajdučík, Adrián; Tucki, Karol

doi:10.1109/iciea52957.2021.9436712

Cited by 3 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a procedure took approximately 10 min on an Intel Core i7-8700. Better results were obtained by considering the pattern recognition of visual content [2], where the convolution principle was used through the function MatchTemplate, integrated into the OpenCV library [35]. The task time was reduced to 3 s, including GUI procedures, using similar hardware as in the case of matrix matching.…”

Section: Point Cloud From the Laser Sensormentioning

confidence: 99%

“…According to previous works [18,23,44], existing defect detection methods have mainly been based on deep learning (supervised learning) using specifically designed or pre-trained CNN architecture, such as AlexNet [45], Resnet-50 [46], or VGG-16 [18]. For this reason, evaluations have been performed using these methods on specific data, such as visual content generated from laser sensor data [2]. We chose to test the VGG-16 CNN architecture, based on results presented in [18,47,48].…”

Section: Defect Detection By Rcnn With Vgg-16 Networkmentioning

confidence: 99%

“…From the view of quality assurance, there are many requirements, due to the high demands during vehicle operations and safety of the vehicle operator and crew. Inspection tasks and requirements have mainly been described in terms of processing 3D data obtained from laser sensors into visual content using pattern recognition [2,3]. A closer description of tire defects has been described in a Ph.D. thesis [4] conducted by the Department of Automation and Production Systems at the University of Zilina.…”

Section: Introductionmentioning

confidence: 99%

“…Conditions were normalized matrices and filtered values, mainly in missing data. In matched scans (e.g., Scan 1 and Scan 3 mentioned in [2]), the differences mainly ranged between −0.2 and 0.2 mm, as displayed in Figure 15. There were occurrences of larger absolute differences, almost up to 3 mm, in which the number of these values corresponded with the number of differences to 0.4 mm.…”

mentioning

confidence: 99%

“…To simplify categorizing the most frequent defects, we defined six basic categories of defects (Figure 1): The defects can be captured by a camera, such as those manufactured by the Balluff company. These images, with a resolution of 12 Mpx, were integrated into the experimental inspection stand described in [2] and used in the paper "Design of laser scanners data processing and their use in a visual inspection system," which will be presented at the ICIE2020 conference (2021). In this thesis, we demonstrate the capturing of defined defects through the use of MATLAB 2020a software (MathWorks company), for which a convolutional neural network (CNN) was trained using a transfer learning method based on the AlexNet network [5].…”

mentioning

confidence: 99%

See 4 more Smart Citations

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

Kuric

Klarák

Sága

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.

show abstract

Section: Point Cloud From the Laser Sensormentioning

confidence: 99%

Section: Defect Detection By Rcnn With Vgg-16 Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

Kuric

Klarák

Sága

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

A Ship Firefighting Training Simulator with Physics-Based Smoke

Tao

Ren

Zhou

2022

JMSE

View full text Add to dashboard Cite

Under the current background of navigation education, students generally lack a comprehensive grasp of ship firefighting equipment’s operation. Therefore, we develop a novel ship firefighting training simulator with a multi-sensory human–computer interaction function for teaching and training marine students. In the simulator, we consider a container ship of 1.8w containers as the prototype ship, and the entire ship models are built using three-dimensional modeling technology. We design various interactive modes and realize a full-process operation simulation of several standard ship firefighting equipment. Furthermore, we propose a purely Lagrangian vortex dynamics framework to simulate smoke and flame in fire scenarios. In this framework, we model fluids using velocity and vorticity fields discretized on discrete vortex segments. The main components of the framework include a stable geometric stretching solution and particle strength exchange method for solving the diffusion term. The simulation results show that the simulator has good behavioral realism and scene immersion and can be applied to ship firefighting training. To the best of our knowledge, this is the first study on real-time smoke simulation using a physics-based method in a firefighting training simulator.

show abstract

A Method of Verifying the Robot's Trajectory for Goals With a Shared Workspace

Anczarski

GŁĄB

Jachowicz

et al. 2022

acs

View full text Add to dashboard Cite

The latest market research (Fanuc Polska 2019) shows that the robotization of the Polish industry is accelerating. More and more companies are investing in robotic production lines, which enable greater efficiency of implemented processes and reduce labour costs. The article presents the possibilities of using virtual reality (VR) for behavioural analysis in open robotic systems with a shared workspace. The aim of the article is to develop a method of verification of programmed movements of an industrial robot in terms of safety and efficiency in systems with a shared workspace. The method of the robot program verification on the digital model of the working cell made in VR will be checked. The obtained research results indicate a great potential of this method in industrial applications as well as for educational purposes.

show abstract

Processing 3D Data from Laser Sensor into Visual Content Using Pattern Recognition

Cited by 3 publications

References 15 publications

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

A Ship Firefighting Training Simulator with Physics-Based Smoke

A Method of Verifying the Robot's Trajectory for Goals With a Shared Workspace

Contact Info

Product

Resources

About