Alejandro Magaña
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alejandro Magaña has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Philipp Bauer
Institute for Machine Tools and Industrial Management, Technical University of Munich, Garching, Germany
4 shared publications - Fridolin Fink
Institute for Machine Tools and Industrial Management, Technical University of Munich, Garching, Germany
2 shared publications Gunther Reinhart
TUM School of Engineering and Design, Department of Mechanical Engineering, Institute for Machine Tools and Industrial Management, Technical University of Munich, Garching, Germany
2 shared publications- Gunther Reinhart
Institute for Machine Tools and Industrial Management, Technical University of Munich, Garching, Germany
2 shared publications - Gunther Reinhart
Institute for Machine Tools and Industrial Management, Boltzmannstraße 15, 85747 Garching, Germany
2 shared publications Philipp Bauer
TUM School of Engineering and Design, Department of Mechanical Engineering, Institute for Machine Tools and Industrial Management, Technical University of Munich, Garching, Germany
2 shared publications
Latest Publications
- Open Access
- 26 December 2023
- Published by Springer Nature in Production Engineering
- Vol. 18 (3-4) , 403-434
Exposure time and point cloud quality prediction for active 3D imaging sensors using Gaussian process regression
Setting an optimal image exposure is crucial for acquiring dense point clouds using 3D active optical sensor systems such as structured light sensors [structured light sensors (SLSs)] and active stereo sensors. One of the most common and seamless ways to optimize the image brightness of an image exposure is to adjust the camera’s exposure time. However, optimizing the image exposure alone is ineffective for acquiring surfaces of large-scale objects with a complex topology if a spatial understanding of the scene is neglected. Hence, the present paper proposes a data-driven approach using two Gaussian processes [Gaussian processes (GPs)] regression models to select a proper exposure time considering the nonlinear correlations between image exposure and the scene spatial relationships. To model these correlations, our study introduces first the generic synthesization of seven inputs and two target variables. Then, based on these inputs, two independent GPs are designed: one for predicting the measurement quality and one for estimating the exposure time. The performance and generalizability of both models are thoroughly evaluated using an SLS and an active stereo sensor. The evaluation demonstrated that the point cloud quality models adequately matched observations with an R2 exceeding 90%. Specifically, the models predicted point cloud quality with an root mean square error (RMSE) of 10%. Additionally, the assessment of the performance of the exposure time models showed a model fit with an R2 above 97%. The exposure time prediction accuracy, as evidenced by the RMSE values, was within 10% of the corresponding exposure time range for each sensor. The present research shows the potential and effectiveness to completely automate the assessment of a point cloud quality and the selection of exposure times with the help of data-driven models.
- 26 December 2023
- Published by Springer Nature in Production Engineering
- Vol. 18 (3-4) , 403-434
Open AccessExposure time and point cloud quality prediction for active 3D imaging sensors using Gaussian process regression
Setting an optimal image exposure is crucial for acquiring dense point clouds using 3D active optical sensor systems such as structured light sensors [structured light sensors (SLSs)] and active stereo sensors. One of the most common and seamless ways to optimize the image brightness of an image exposure is to adjust the camera’s exposure time. However, optimizing the image exposure alone is ineffective for acquiring surfaces of large-scale objects with a complex topology if a spatial understanding of the scene is neglected. Hence, the present paper proposes a data-driven approach using two Gaussian processes [Gaussian processes (GPs)] regression models to select a proper exposure time considering the nonlinear correlations between image exposure and the scene spatial relationships. To model these correlations, our study introduces first the generic synthesization of seven inputs and two target variables. Then, based on these inputs, two independent GPs are designed: one for predicting the measurement quality and one for estimating the exposure time. The performance and generalizability of both models are thoroughly evaluated using an SLS and an active stereo sensor. The evaluation demonstrated that the point cloud quality models adequately matched observations with an R2 exceeding 90%. Specifically, the models predicted point cloud quality with an root mean square error (RMSE) of 10%. Additionally, the assessment of the performance of the exposure time models showed a model fit with an R2 above 97%. The exposure time prediction accuracy, as evidenced by the RMSE values, was within 10% of the corresponding exposure time range for each sensor. The present research shows the potential and effectiveness to completely automate the assessment of a point cloud quality and the selection of exposure times with the help of data-driven models.
- Open Access
Viewpoint Planning for Range Sensors Using Feature Cluster Constrained Spaces for Robot Vision Systems
The efficient computation of viewpoints for solving vision tasks comprising multi-features (regions of interest) represents a common challenge that any robot vision system (RVS) using range sensors faces. The characterization of valid and robust viewpoints is even more complex within real applications that require the consideration of various system constraints and model uncertainties. Hence, to address some of the challenges, our previous work outlined the computation of valid viewpoints as a geometrical problem and proposed feature-based constrained spaces (-spaces) to tackle this problem efficiently for acquiring one feature. The present paper extends the concept of -spaces to consider multi-feature problems using feature cluster constrained spaces (-spaces). A -space represents a closed-form, geometrical solution that provides an infinite set of valid viewpoints for acquiring a cluster of features satisfying diverse viewpoint constraints. Furthermore, the current study outlines a generic viewpoint planning strategy based on -spaces for solving vision tasks comprising multi-feature scenarios effectively and efficiently. The applicability of the proposed framework is validated on two different industrial vision systems used for dimensional metrology tasks.Open AccessViewpoint Planning for Range Sensors Using Feature Cluster Constrained Spaces for Robot Vision Systems
The efficient computation of viewpoints for solving vision tasks comprising multi-features (regions of interest) represents a common challenge that any robot vision system (RVS) using range sensors faces. The characterization of valid and robust viewpoints is even more complex within real applications that require the consideration of various system constraints and model uncertainties. Hence, to address some of the challenges, our previous work outlined the computation of valid viewpoints as a geometrical problem and proposed feature-based constrained spaces (-spaces) to tackle this problem efficiently for acquiring one feature. The present paper extends the concept of -spaces to consider multi-feature problems using feature cluster constrained spaces (-spaces). A -space represents a closed-form, geometrical solution that provides an infinite set of valid viewpoints for acquiring a cluster of features satisfying diverse viewpoint constraints. Furthermore, the current study outlines a generic viewpoint planning strategy based on -spaces for solving vision tasks comprising multi-feature scenarios effectively and efficiently. The applicability of the proposed framework is validated on two different industrial vision systems used for dimensional metrology tasks. - Open Access
Viewpoint Generation Using Feature-Based Constrained Spaces for Robot Vision Systems
The efficient computation of viewpoints while considering various system and process constraints is a common challenge that any robot vision system is confronted with when trying to execute a vision task. Although fundamental research has provided solid and sound solutions for tackling this problem, a holistic framework that poses its formal description, considers the heterogeneity of robot vision systems, and offers an integrated solution remains unaddressed. Hence, this publication outlines the generation of viewpoints as a geometrical problem and introduces a generalized theoretical framework based on Feature-Based Constrained Spaces (-spaces) as the backbone for solving it. A -space can be understood as the topological space that a viewpoint constraint spans, where the sensor can be positioned for acquiring a feature while fulfilling the constraint. The present study demonstrates that many viewpoint constraints can be efficiently formulated as -spaces, providing geometric, deterministic, and closed solutions. The introduced -spaces are characterized based on generic domain and viewpoint constraints models to ease the transferability of the present framework to different applications and robot vision systems. The effectiveness and efficiency of the concepts introduced are verified on a simulation-based scenario and validated on a real robot vision system comprising two different sensors.Open AccessViewpoint Generation Using Feature-Based Constrained Spaces for Robot Vision Systems
The efficient computation of viewpoints while considering various system and process constraints is a common challenge that any robot vision system is confronted with when trying to execute a vision task. Although fundamental research has provided solid and sound solutions for tackling this problem, a holistic framework that poses its formal description, considers the heterogeneity of robot vision systems, and offers an integrated solution remains unaddressed. Hence, this publication outlines the generation of viewpoints as a geometrical problem and introduces a generalized theoretical framework based on Feature-Based Constrained Spaces (-spaces) as the backbone for solving it. A -space can be understood as the topological space that a viewpoint constraint spans, where the sensor can be positioned for acquiring a feature while fulfilling the constraint. The present study demonstrates that many viewpoint constraints can be efficiently formulated as -spaces, providing geometric, deterministic, and closed solutions. The introduced -spaces are characterized based on generic domain and viewpoint constraints models to ease the transferability of the present framework to different applications and robot vision systems. The effectiveness and efficiency of the concepts introduced are verified on a simulation-based scenario and validated on a real robot vision system comprising two different sensors. - 1 November 2021
- Published by Elsevier in Measurement
- Vol. 185
Registration strategy of point clouds based on region-specific projections and virtual structures for robot-based inspection systems
- 1 November 2021
- Published by Elsevier in Measurement
- Vol. 185
Registration strategy of point clouds based on region-specific projections and virtual structures for robot-based inspection systems
- Open Access
- 9 June 2021
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 116 (3-4) , 1385
Correction to: Spatial interactive projections in robot-based inspection systems
- 9 June 2021
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 116 (3-4) , 1385
Open AccessCorrection to: Spatial interactive projections in robot-based inspection systems
- Open Access
- 30 March 2020
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 107 (5-6) , 2889-2900
Spatial interactive projections in robot-based inspection systems
Due to major technological improvements over the last decades and a significant decrease in costs, electronic projection systems show great potential for providing innovative applications across industries. In most cases, projectors are used to display entire images onto contiguous plane surfaces, but with no active consideration of their three-dimensional environment. Since spatial interactive projections promise new possibilities to display information in the manufacturing industry, we developed a practical approach to how common projection systems can be integrated into a working space and interact with their environment. In order to display information in a spatially dependent manner, a projection model was introduced along with a calibration method for mapping. Subsequently, the approach was validated in the context of robot-based optical inspection systems where texture projections are applied onto sheet metal parts as references features, exclusively to designated regions. The results show that accurate region-specific projections were possible within the calibrated projection volume. In addition, the accuracy and computing speed were investigated to identify limitations. Our approach for interactive projections supports the transfer to other application areas, enables us to rethink current manual and automated procedures and processes in which visualized information benefits the task of interest, and provides new functionalities for manufacturing industries.
- 30 March 2020
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 107 (5-6) , 2889-2900
Open AccessSpatial interactive projections in robot-based inspection systems
Due to major technological improvements over the last decades and a significant decrease in costs, electronic projection systems show great potential for providing innovative applications across industries. In most cases, projectors are used to display entire images onto contiguous plane surfaces, but with no active consideration of their three-dimensional environment. Since spatial interactive projections promise new possibilities to display information in the manufacturing industry, we developed a practical approach to how common projection systems can be integrated into a working space and interact with their environment. In order to display information in a spatially dependent manner, a projection model was introduced along with a calibration method for mapping. Subsequently, the approach was validated in the context of robot-based optical inspection systems where texture projections are applied onto sheet metal parts as references features, exclusively to designated regions. The results show that accurate region-specific projections were possible within the calibrated projection volume. In addition, the accuracy and computing speed were investigated to identify limitations. Our approach for interactive projections supports the transfer to other application areas, enables us to rethink current manual and automated procedures and processes in which visualized information benefits the task of interest, and provides new functionalities for manufacturing industries.
- Open Access
- 11 July 2018
- Published by Springer Nature in BMC Musculoskeletal Disorders
- Vol. 19 (1) , 215
Single cut distal femoral osteotomy for correction of femoral torsion and valgus malformity in patellofemoral malalignment - proof of application of new trigonometrical calculations and 3D-printed cutting guides
The purpose of this study was to perform a derotational osteotomy at the distal femur, as is done in cases of patellofemoral instability, and demonstrate the predictability of three-dimensional (3D) changes on axes in a cadaveric model by the use of a new mathematical approach. Ten human cadaveric femurs, with increased antetorsion, underwent a visually observed derotational osteotomy at the distal femur by 20°, as is commonly done in clinics. For surgery, a single cut osteotomy with a defined cutting angle was calculated and given using a simple 3D-printed cutting guide per specimen, based on a newly-created trigonometrical model. To simulate post-operative straight frontal alignment in a normal range, a goal for the mechanical lateral distal femur angle (mLDFA) was set to 87.0° for five specimens (87-goal group) and 90.0° for five specimens (90-goal group). Specimens underwent pre- and post-operative radiographic analysis with CT scan for torsion and frontal plane x-ray for alignment measurements of mLDFA and anatomical mechanical angle (AMA). Performed derotation showed a mean of 19.69° ±1.08°SD (95% CI: 18.91° to 20.47°). Regarding frontal alignment, a mean mLDFA of 86.9° ±0.66°SD (87-goal-group) and 90.42° ±0.25° SD (90-goal group), was observed (p = 0.008). Overall, the mean difference between intended mLDFA-goal and post-operatively achieved mLDFA was 0.14° ±0.56° SD (95% CI: -0.26° to 0.54°). A preoperative calculated angle for single cut derotational osteotomy at the distal femur leads to a clinically precise post-operative result on torsion and frontal alignment when using this approach.
- 11 July 2018
- Published by Springer Nature in BMC Musculoskeletal Disorders
- Vol. 19 (1) , 215
Open AccessSingle cut distal femoral osteotomy for correction of femoral torsion and valgus malformity in patellofemoral malalignment - proof of application of new trigonometrical calculations and 3D-printed cutting guides
The purpose of this study was to perform a derotational osteotomy at the distal femur, as is done in cases of patellofemoral instability, and demonstrate the predictability of three-dimensional (3D) changes on axes in a cadaveric model by the use of a new mathematical approach. Ten human cadaveric femurs, with increased antetorsion, underwent a visually observed derotational osteotomy at the distal femur by 20°, as is commonly done in clinics. For surgery, a single cut osteotomy with a defined cutting angle was calculated and given using a simple 3D-printed cutting guide per specimen, based on a newly-created trigonometrical model. To simulate post-operative straight frontal alignment in a normal range, a goal for the mechanical lateral distal femur angle (mLDFA) was set to 87.0° for five specimens (87-goal group) and 90.0° for five specimens (90-goal group). Specimens underwent pre- and post-operative radiographic analysis with CT scan for torsion and frontal plane x-ray for alignment measurements of mLDFA and anatomical mechanical angle (AMA). Performed derotation showed a mean of 19.69° ±1.08°SD (95% CI: 18.91° to 20.47°). Regarding frontal alignment, a mean mLDFA of 86.9° ±0.66°SD (87-goal-group) and 90.42° ±0.25° SD (90-goal group), was observed (p = 0.008). Overall, the mean difference between intended mLDFA-goal and post-operatively achieved mLDFA was 0.14° ±0.56° SD (95% CI: -0.26° to 0.54°). A preoperative calculated angle for single cut derotational osteotomy at the distal femur leads to a clinically precise post-operative result on torsion and frontal alignment when using this approach.