Manolis I. A. Lourakis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Manolis I. A. Lourakis has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Antonis Argyros
University of Crete
22 shared publications - Xenophon Zabulis
Foundation for Research and Technology Hellas, Heraklion, Greece, Greece
9 shared publications S.C. Orphanoudakis
6 shared publicationsIoannis Stamoulias
3 shared publicationsDamien Michel
2 shared publicationsDimitrios Soudris
2 shared publications
Latest Publications
- 30 March 2026
- Published by The R Foundation
sparseLM: Interface to the 'sparseLM' Levenberg-Marquardt Library
Provides an R interface to the 'sparseLM' C library for large-scale nonlinear least squares problems with arbitrarily sparse Jacobians. The underlying solver implements a sparse variant of the Levenberg-Marquardt algorithm for minimizing sum-of-squares objective functions, supports user-supplied analytic Jacobians or finite-difference approximation, and is designed to exploit sparsity for improved memory use and performance. This package exposes the solver in R and uses sparse matrix classes and the 'CHOLMOD' sparse Cholesky factorization routines through the 'Matrix' package interface. Methods from the C library are described in Lourakis (2010) .
- 30 March 2026
- Published by The R Foundation
sparseLM: Interface to the 'sparseLM' Levenberg-Marquardt Library
Provides an R interface to the 'sparseLM' C library for large-scale nonlinear least squares problems with arbitrarily sparse Jacobians. The underlying solver implements a sparse variant of the Levenberg-Marquardt algorithm for minimizing sum-of-squares objective functions, supports user-supplied analytic Jacobians or finite-difference approximation, and is designed to exploit sparsity for improved memory use and performance. This package exposes the solver in R and uses sparse matrix classes and the 'CHOLMOD' sparse Cholesky factorization routines through the 'Matrix' package interface. Methods from the C library are described in Lourakis (2010) .
- 9 December 2024
- Published by Springer Nature
- p. 297-304
Towards Behavior Trees Based Robotic Task Execution for Physical Human Robot Collaboration
- 9 December 2024
- Published by Springer Nature
- p. 297-304
Towards Behavior Trees Based Robotic Task Execution for Physical Human Robot Collaboration
- 3 December 2024
- Published by Springer Nature
- p. 97-112
Fast and Consistently Accurate Perspective-n-Line Pose Estimation
- 3 December 2024
- Published by Springer Nature
- p. 97-112
Fast and Consistently Accurate Perspective-n-Line Pose Estimation
- Open Access
- 16 March 2022
- Published by MDPI AG in Technologies
- Vol. 10 (2) , 42
Detection of Physical Strain and Fatigue in Industrial Environments Using Visual and Non-Visual Low-Cost Sensors
The detection and prevention of workers’ body straining postures and other stressing conditions within the work environment, supports establishing occupational safety and promoting well being and sustainability at work. Developed methods towards this aim typically rely on combining highly ergonomic workplaces and expensive monitoring mechanisms including wearable devices. In this work, we demonstrate how the input from low-cost sensors, specifically, passive camera sensors installed in a real manufacturing workplace, and smartwatches used by the workers can provide useful feedback on the workers’ conditions and can yield key indicators for the prevention of work-related musculo-skeletal disorders (WMSD) and physical fatigue. To this end, we study the ability to assess the risk for physical strain of workers online during work activities based on the classification of ergonomically sub-optimal working postures using visual information, the correlation and fusion of these estimations with synchronous worker heart rate data, as well as the prediction of near-future heart rate using deep learning-based techniques. Moreover, a new multi-modal dataset of video and heart rate data captured in a real manufacturing workplace during car door assembly activities is introduced. The experimental results show the efficiency of the proposed approach that exceeds 70% of classification rate based on the F1 score measure using a set of over 300 annotated video clips of real line workers during work activities. In addition a time lagging correlation between the estimated ergonomic risks for physical strain and high heart rate was assessed using a larger dataset of synchronous visual and heart rate data sequences. The statistical analysis revealed that imposing increased strain to body parts will results in an increase to the heart rate after 100–120 s. This finding is used to improve the short term forecasting of worker’s cardiovascular activity for the next 10 to 30 s by fusing the heart rate data with the estimated ergonomic risks for physical strain and ultimately to train better predictive models for worker fatigue.
- 16 March 2022
- Published by MDPI AG in Technologies
- Vol. 10 (2) , 42
Open AccessDetection of Physical Strain and Fatigue in Industrial Environments Using Visual and Non-Visual Low-Cost Sensors
The detection and prevention of workers’ body straining postures and other stressing conditions within the work environment, supports establishing occupational safety and promoting well being and sustainability at work. Developed methods towards this aim typically rely on combining highly ergonomic workplaces and expensive monitoring mechanisms including wearable devices. In this work, we demonstrate how the input from low-cost sensors, specifically, passive camera sensors installed in a real manufacturing workplace, and smartwatches used by the workers can provide useful feedback on the workers’ conditions and can yield key indicators for the prevention of work-related musculo-skeletal disorders (WMSD) and physical fatigue. To this end, we study the ability to assess the risk for physical strain of workers online during work activities based on the classification of ergonomically sub-optimal working postures using visual information, the correlation and fusion of these estimations with synchronous worker heart rate data, as well as the prediction of near-future heart rate using deep learning-based techniques. Moreover, a new multi-modal dataset of video and heart rate data captured in a real manufacturing workplace during car door assembly activities is introduced. The experimental results show the efficiency of the proposed approach that exceeds 70% of classification rate based on the F1 score measure using a set of over 300 annotated video clips of real line workers during work activities. In addition a time lagging correlation between the estimated ergonomic risks for physical strain and high heart rate was assessed using a larger dataset of synchronous visual and heart rate data sequences. The statistical analysis revealed that imposing increased strain to body parts will results in an increase to the heart rate after 100–120 s. This finding is used to improve the short term forecasting of worker’s cardiovascular activity for the next 10 to 30 s by fusing the heart rate data with the estimated ergonomic risks for physical strain and ultimately to train better predictive models for worker fatigue.
- Open Access
- 1 January 2022
- Published by University of Maribor
- p. 89-104
Applying SCRUM in a Physics II Undergraduate Course: Effect on Student Progression and Soft Skills Development
The everchanging higher education environment, especially after the impact of COVID-19, dictates the need of innovative, engaging, and efficient teaching methods along with promoting soft skills among the students. Scrum offers a framework for effective teamwork and it has been previously applied in higher education for enhancing collaborative learning and the development of skills. This paper will describe how Scrum was applied to a Physics II undergraduate course during the spring semester 2021, where classes were given online due to covid-19 imposed restrictions. The focus of this experiment was twofold. Firstly, we aimed at investigating the feasibility of Scrum under remote teaching conditions. Secondly, we observed the students’ progress with the learning objectives of the course, along with the advancement soft skills among the students participating in the experiment. We conclude our presentation with feedback collected both from the teachers and the students involved in the experiment.
- 1 January 2022
- Published by University of Maribor
- p. 89-104
Open AccessApplying SCRUM in a Physics II Undergraduate Course: Effect on Student Progression and Soft Skills Development
The everchanging higher education environment, especially after the impact of COVID-19, dictates the need of innovative, engaging, and efficient teaching methods along with promoting soft skills among the students. Scrum offers a framework for effective teamwork and it has been previously applied in higher education for enhancing collaborative learning and the development of skills. This paper will describe how Scrum was applied to a Physics II undergraduate course during the spring semester 2021, where classes were given online due to covid-19 imposed restrictions. The focus of this experiment was twofold. Firstly, we aimed at investigating the feasibility of Scrum under remote teaching conditions. Secondly, we observed the students’ progress with the learning objectives of the course, along with the advancement soft skills among the students participating in the experiment. We conclude our presentation with feedback collected both from the teachers and the students involved in the experiment.
- Open Access
- 12 October 2017
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 60 (3) , 422-442
Modified Rodrigues Parameters: An Efficient Representation of Orientation in 3D Vision and Graphics
- 12 October 2017
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 60 (3) , 422-442
Open AccessModified Rodrigues Parameters: An Efficient Representation of Orientation in 3D Vision and Graphics
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 350-355
Project HIPNOS: Case Study of High Performance Avionics for Active Debris Removal in Space
The Clean Space initiative of the European Space Agency (ESA) seeks to decrease the environmental impact of space programmes by focusing, among others, on Active Debris Removal (ADR) and eDeorbit. In this direction, one of the main challenges is to autonomously track and approach a big non-cooperative satellite such as ENVISAT. To achieve the high level of autonomy required in this phase of the ADR mission, vision based navigation will guide a chaser spacecraft in real-time based on high-definition images acquired and processed on-board at high frame-rates. The increased complexity of these computer vision algorithms mandates the development and use of high performance avionics to provide one order of magnitude faster execution than today's conventional space-grade processors. In the context of ESA's project HIPNOS (HIgh Performance avionics solutioN for advanced and complex GNC Systems), we study algorithms and avionics architectures suitable for ADR. The examined algorithms base on image feature extraction and the architectures base on COTS SoC-FPGA devices. Preliminary analysis highlights the benefits of employing this avionics solution in future space missions.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 350-355
Project HIPNOS: Case Study of High Performance Avionics for Active Debris Removal in Space
The Clean Space initiative of the European Space Agency (ESA) seeks to decrease the environmental impact of space programmes by focusing, among others, on Active Debris Removal (ADR) and eDeorbit. In this direction, one of the main challenges is to autonomously track and approach a big non-cooperative satellite such as ENVISAT. To achieve the high level of autonomy required in this phase of the ADR mission, vision based navigation will guide a chaser spacecraft in real-time based on high-definition images acquired and processed on-board at high frame-rates. The increased complexity of these computer vision algorithms mandates the development and use of high performance avionics to provide one order of magnitude faster execution than today's conventional space-grade processors. In the context of ESA's project HIPNOS (HIgh Performance avionics solutioN for advanced and complex GNC Systems), we study algorithms and avionics architectures suitable for ADR. The examined algorithms base on image feature extraction and the architectures base on COTS SoC-FPGA devices. Preliminary analysis highlights the benefits of employing this avionics solution in future space missions.
- Top Cited Papers
- 1 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 880-888
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects
We introduce T-LESS, a new public dataset for estimating the 6D pose, i.e. translation and rotation, of texture-less rigid objects. The dataset features thirty industry-relevant objects with no significant texture and no discriminative color or reflectance properties. The objects exhibit symmetries and mutual similarities in shape and/or size. Compared to other datasets, a unique property is that some of the objects are parts of others. The dataset includes training and test images that were captured with three synchronized sensors, specifically a structured-light and a time-of-flight RGB-D sensor and a high-resolution RGB camera. There are approximately 39K training and 10K test images from each sensor. Additionally, two types of 3D models are provided for each object, i.e. a manually created CAD model and a semi-automatically reconstructed one. Training images depict individual objects against a black background. Test images originate from twenty test scenes having varying complexity, which increases from simple scenes with several isolated objects to very challenging ones with multiple instances of several objects and with a high amount of clutter and occlusion. The images were captured from a systematically sampled view sphere around the object/scene, and are annotated with accurate ground truth 6D poses of all modeled objects. Initial evaluation results indicate that the state of the art in 6D object pose estimation has ample room for improvement, especially in difficult cases with significant occlusion. The T-LESS dataset is available online at cmp:felk:cvut:cz/t-less.
- 1 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 880-888
Top Cited PapersT-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects
We introduce T-LESS, a new public dataset for estimating the 6D pose, i.e. translation and rotation, of texture-less rigid objects. The dataset features thirty industry-relevant objects with no significant texture and no discriminative color or reflectance properties. The objects exhibit symmetries and mutual similarities in shape and/or size. Compared to other datasets, a unique property is that some of the objects are parts of others. The dataset includes training and test images that were captured with three synchronized sensors, specifically a structured-light and a time-of-flight RGB-D sensor and a high-resolution RGB camera. There are approximately 39K training and 10K test images from each sensor. Additionally, two types of 3D models are provided for each object, i.e. a manually created CAD model and a semi-automatically reconstructed one. Training images depict individual objects against a black background. Test images originate from twenty test scenes having varying complexity, which increases from simple scenes with several isolated objects to very challenging ones with multiple instances of several objects and with a high amount of clutter and occlusion. The images were captured from a systematically sampled view sphere around the object/scene, and are annotated with accurate ground truth 6D poses of all modeled objects. Initial evaluation results indicate that the state of the art in 6D object pose estimation has ample room for improvement, especially in difficult cases with significant occlusion. The T-LESS dataset is available online at cmp:felk:cvut:cz/t-less.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3816-3819
An efficient solution to absolute orientation
The absolute orientation problem arises often in vision and robotics. Despite that robust algorithmic solutions exist for quite some time, they all rely on matrix factorizations such as eigen or singular value decomposition. These factorizations are relatively expensive to compute, therefore might become a performance bottleneck when absolute orientation needs to be repeatedly computed on low-end hardware. The issue is exacerbated by implementations relying on standard numerical software libraries like LAPACK, since the linear algebra factorization routines they include are optimized for large matrices and thus are not the most efficient choice for small ones. Based on an attitude estimation algorithm originating from astronautics, this paper proposes a direct, factorization-free solution to the absolute orientation problem that is both computationally efficient and numerically accurate. Results from an experimental comparison with established methods demonstrate its superior performance.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3816-3819
An efficient solution to absolute orientation
The absolute orientation problem arises often in vision and robotics. Despite that robust algorithmic solutions exist for quite some time, they all rely on matrix factorizations such as eigen or singular value decomposition. These factorizations are relatively expensive to compute, therefore might become a performance bottleneck when absolute orientation needs to be repeatedly computed on low-end hardware. The issue is exacerbated by implementations relying on standard numerical software libraries like LAPACK, since the linear algebra factorization routines they include are optimized for large matrices and thus are not the most efficient choice for small ones. Based on an attitude estimation algorithm originating from astronautics, this paper proposes a direct, factorization-free solution to the absolute orientation problem that is both computationally efficient and numerically accurate. Results from an experimental comparison with established methods demonstrate its superior performance.
- 15 October 2016
- Published by Springer Nature in The Visual Computer
- Vol. 34 (2) , 193-211
Correspondence-free pose estimation for 3D objects from noisy depth data
- 15 October 2016
- Published by Springer Nature in The Visual Computer
- Vol. 34 (2) , 193-211
Correspondence-free pose estimation for 3D objects from noisy depth data