Tiago Loureiro Figaro da Costa Pinto

Tiago Loureiro Figaro da Costa Pinto

Auto-generated profile, based on publicly available information

Tiago Loureiro Figaro da Costa Pinto

Federal University of Santa Catarina

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2025 in Journal of Intelligent Manufacturing
Verified
Journal Article
Open access
PDF file
HZHans Aoyang Zhou
Hans Aoyang Zhou
DWDominik Wolfschläger
Dominik Wolfschläger
CFConstantinos Florides
Constantinos Florides
JWJonas Werheid
Jonas Werheid
HBHannes Behnen
Hannes Behnen
Robert SchmittRobert Schmitt
Robert Schmitt
Machine vision enhances automation, quality control, and operational efficiency in industrial applications by enabling machines to interpret and act on visual data. While traditional computer vision algorithms and approaches remain widely utilized, machine learning has become pivotal in current research activities. In particular, generative Artificial Intelligence (AI) demonstrates promising potential by improving pattern recognition capabilities, through data augmentation, increasing image resolution, and identifying anomalies for quality control. However, the application of generative AI in machine vision is still in its early stages due to challenges in data diversity, computational requirements, and the necessity for robust validation methods. A comprehensive literature review is essential to understand the current state of generative AI in industrial machine vision, focusing on recent advancements, applications, and research trends. Thus, a literature review based on the PRISMA guidelines was conducted, analyzing over 1,200 papers on generative AI in industrial machine vision. Our findings reveal various patterns in current research, with the primary use of generative AI being data augmentation, for machine vision tasks such as classification and object detection. Furthermore, we gather a collection of application challenges together with data requirements to enable a successful application of generative AI in industrial machine vision. This overview aims to provide researchers with insights into the different areas and applications within current research, highlighting significant advancements and identifying opportunities for future work.

1 September 2015 in Measurement
Verified
Journal Article
Closed access
MHMaryah Elisa Morastoni Haertel
Maryah Elisa Morastoni Haertel
TPTiago Loureiro Figaro da Costa Pinto
Tiago Loureiro Figaro da Costa Pinto
AJArmando Albertazzi Gonçalves Júnior
Armando Albertazzi Gonçalves Júnior

18 June 2007
Verified
Conference Paper
Closed access
PDF file
AFA V Fantin
A V Fantin
AAArmando Albertazzi
Armando Albertazzi
TPTiago L Pinto
Tiago L Pinto
Fringe projection has been widely used for 3D geometry measurement in several classes of applications. The basic system is formed by a fringe projector and a camera. A triangulation algorithm is frequently used for retrieving 3D information from a scene. Alternatively, two cameras can be used in combination with one fringe projector. This configuration produces a significant measurement uncertainty improvement since only phase information encoded in the fringe pattern is used to locate homologue points in the triangulation algorithm and lack of linearity or imperfections of the fringe projector does not induce measurement errors. However, some parts with complex geometry can not easily been seen from both cameras in a convenient angle, what limits the applicability of this configuration. Frequently the clouds of points acquired from such systems are non-structured and, consequently, a non-regular mesh is obtained. This paper presents a very simple and effective procedure to combine data from multiple cameras to produce clouds of points in a regular mesh. The main idea starts by setting two independent coordinates for a node of a regular mesh. The third coordinate is found by scanning the dependent coordinate across the measurement volume until the phase values of the fringe patterns, acquired for the multiple cameras, reach the same common value. That approach naturally produces structured clouds of points independently of the number of cameras used. As an example, a 3D shape is acquired by an ordinary multimedia projector and a set of four low cost webcams. A calibration is necessary to reference the four webcams into the same coordinate system. For that, a reference object, composed by a set of small spheres in calibrated positions, is used.

20 March 2018 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
TPT. C. Pinto
T. C. Pinto
GMG. Matos
G. Matos
Proper positioning of a friction stir welding head for pin insertion, driven by a closed chain robot, is important to ensure quality repair of cracks. A multi-line off-axis laser triangulation sensor was designed to be integrated to the robot, allowing relative measurements of the surface to be repaired. This work describes the sensor characteristics, its evaluation and the measurement process for tool positioning to a surface point of interest. The developed process uses a point of interest image and a measured point cloud to define the translation and rotation for tool positioning. Sensor evaluation and tests are described. Keywords: laser triangulation, 3D measurement, tool positioning, robotics.

21 August 2024 in arXiv
Verified
Preprint
Open access
PDF file
HZHans Aoyang Zhou
Hans Aoyang Zhou
DWDominik Wolfschläger
Dominik Wolfschläger
CFConstantinos Florides
Constantinos Florides
JWJonas Werheid
Jonas Werheid
HBHannes Behnen
Hannes Behnen
Robert SchmittRobert Schmitt
Robert Schmitt
Machine vision enhances automation, quality control, and operational efficiency in industrial applications by enabling machines to interpret and act on visual data. While traditional computer vision algorithms and approaches remain widely utilized, machine learning has become pivotal in current research activities. In particular, generative AI demonstrates promising potential by improving pattern recognition capabilities, through data augmentation, increasing image resolution, and identifying anomalies for quality control. However, the application of generative AI in machine vision is still in its early stages due to challenges in data diversity, computational requirements, and the necessity for robust validation methods. A comprehensive literature review is essential to understand the current state of generative AI in industrial machine vision, focusing on recent advancements, applications, and research trends. Thus, a literature review based on the PRISMA guidelines was conducted, analyzing over 1,200 papers on generative AI in industrial machine vision. Our findings reveal various patterns in current research, with the primary use of generative AI being data augmentation, for machine vision tasks such as classification and object detection. Furthermore, we gather a collection of application challenges together with data requirements to enable a successful application of generative AI in industrial machine vision. This overview aims to provide researchers with insights into the different areas and applications within current research, highlighting significant advancements and identifying opportunities for future work.

1 January 2026 in IEEE Journal of Oceanic Engineering
Verified
Journal Article
Open access
DRDaniel Juchem Regner
Daniel Juchem Regner
MWMoacir Wendhausen
Moacir Wendhausen
CMCarla Marinho
Carla Marinho
GWGierri Waltrich
Gierri Waltrich
TPTiago Loureiro Figaro da Costa Pinto
Tiago Loureiro Figaro da Costa Pinto