CESI
M2 Internship – Improved calibration of industrial cameras positioned on robots H/F
Job Location
Saint-Etienne-du-Rouvray, France
Job Description
Works
This M2 internship is part of ongoing research on improving camera calibration techniques, focusing on optimizing datasets for intrinsic and extrinsic calibration in robotic manipulation contexts. Accurate camera calibration is essential for achieving precise perception and control in robotics, particularly in scenarios involving cameras mounted on robotic manipulators.
Context
Camera calibration is a critical step in computer vision applications, enabling accurate transformation between image and real-world coordinates. However, the performance of calibration algorithms can vary significantly depending on the datasets used. Previous studies carried on our laboratory highlight that dataset quality and diversity play a vital role in ensuring robust calibration results, especially in dynamic environments like industrial robotics. This internship will explore the disparity in calibration results across different datasets and investigate methods for creating optimized datasets tailored to robotic manipulators.
Details of the tasks
The primary objectives of the internship are as follows:
* Study Calibration Result Disparity :
Analyse the variability of intrinsic and extrinsic camera calibration results when using different datasets.
* Develop Synthetic Camera Datasets :
Generate datasets specifically for cameras mounted on the end-effectors of robotic manipulators.
* Optimize Dataset Creation:
Propose and implement an optimized methodology for creating calibration datasets, considering factors such as pattern design, robot pose diversity, and environmental conditions.
* Evaluate Calibration Quality:
Assess the quality of calibration achieved using the generated datasets, comparing synthetic, realworld, and hybrid datasets.
Laboratory Presentation
CESI LINEACT (UR 7527), the Digital Innovation Laboratory for Businesses and Learning in support of Territorial Competitiveness, anticipates and supports technological transformations in sectors and services related to industry and construction. CESI's historical ties with businesses are a determining factor in its research activities, leading to a focus on applied research in partnership with industry. A human-centered approach coupled with the use of technologies, as well as regional networking and links with education, have enabled cross-disciplinary research that centers on human needs and uses, addressing technological challenges through these contributions.
Its research is organized into two interdisciplinary scientific teams and two application domains:
* Team 1, "Learning and Innovating," is primarily focused on Cognitive Sciences, Social Sciences, Management Sciences, Education Science, and Innovation Sciences. The main scientific objectives are understanding the effects of the environment, particularly instrumented situations with technical objects (platforms, prototyping workshops, immersive systems), on learning, creativity, and innovation processes.
* Team 2, "Engineering and Digital Tools," is mainly focused on Digital Sciences and Engineering. Its main scientific objectives include modeling, simulation, optimization, and data analysis of cyber-physical systems. Research also covers decision-support tools and studies of humansystem interactions, especially through digital twins coupled with virtual or augmented environments.
These two teams cross and develop their research in the two application domains of Industry of the
Future and City of the Future, supported by research platforms, primarily the Rouen platform dedicated to the Factory of the Future and the Nanterre platform dedicated to the Factory and Building of the Future.
Location: Saint-Etienne-du-Rouvray, FR
Posted Date: 12/21/2024
This M2 internship is part of ongoing research on improving camera calibration techniques, focusing on optimizing datasets for intrinsic and extrinsic calibration in robotic manipulation contexts. Accurate camera calibration is essential for achieving precise perception and control in robotics, particularly in scenarios involving cameras mounted on robotic manipulators.
Context
Camera calibration is a critical step in computer vision applications, enabling accurate transformation between image and real-world coordinates. However, the performance of calibration algorithms can vary significantly depending on the datasets used. Previous studies carried on our laboratory highlight that dataset quality and diversity play a vital role in ensuring robust calibration results, especially in dynamic environments like industrial robotics. This internship will explore the disparity in calibration results across different datasets and investigate methods for creating optimized datasets tailored to robotic manipulators.
Details of the tasks
The primary objectives of the internship are as follows:
* Study Calibration Result Disparity :
Analyse the variability of intrinsic and extrinsic camera calibration results when using different datasets.
* Develop Synthetic Camera Datasets :
Generate datasets specifically for cameras mounted on the end-effectors of robotic manipulators.
* Optimize Dataset Creation:
Propose and implement an optimized methodology for creating calibration datasets, considering factors such as pattern design, robot pose diversity, and environmental conditions.
* Evaluate Calibration Quality:
Assess the quality of calibration achieved using the generated datasets, comparing synthetic, realworld, and hybrid datasets.
Laboratory Presentation
CESI LINEACT (UR 7527), the Digital Innovation Laboratory for Businesses and Learning in support of Territorial Competitiveness, anticipates and supports technological transformations in sectors and services related to industry and construction. CESI's historical ties with businesses are a determining factor in its research activities, leading to a focus on applied research in partnership with industry. A human-centered approach coupled with the use of technologies, as well as regional networking and links with education, have enabled cross-disciplinary research that centers on human needs and uses, addressing technological challenges through these contributions.
Its research is organized into two interdisciplinary scientific teams and two application domains:
* Team 1, "Learning and Innovating," is primarily focused on Cognitive Sciences, Social Sciences, Management Sciences, Education Science, and Innovation Sciences. The main scientific objectives are understanding the effects of the environment, particularly instrumented situations with technical objects (platforms, prototyping workshops, immersive systems), on learning, creativity, and innovation processes.
* Team 2, "Engineering and Digital Tools," is mainly focused on Digital Sciences and Engineering. Its main scientific objectives include modeling, simulation, optimization, and data analysis of cyber-physical systems. Research also covers decision-support tools and studies of humansystem interactions, especially through digital twins coupled with virtual or augmented environments.
These two teams cross and develop their research in the two application domains of Industry of the
Future and City of the Future, supported by research platforms, primarily the Rouen platform dedicated to the Factory of the Future and the Nanterre platform dedicated to the Factory and Building of the Future.
Location: Saint-Etienne-du-Rouvray, FR
Posted Date: 12/21/2024
Contact Information
| Contact | Human Resources CESI |
|---|