Capítols de llibre
http://hdl.handle.net/2117/3757
2024-03-28T23:57:59ZAutomated chlorine dosage in a simulated drinking water treatment plant: a real case study
http://hdl.handle.net/2117/365103
Automated chlorine dosage in a simulated drinking water treatment plant: a real case study
Gámiz Caro, Javier Francisco; Grau Saldes, Antoni; Martínez García, Herminio; Bolea Monte, Yolanda
In recent decades, increasing attention has been paid to the sustainability of products and processes, including activities aimed at environmental protection, site reclamation or treatment of contaminated ef¿uents, as well as the valorization of waste through the recovery of resources. Although implemented with ‘noble intentions’, these processes are often highly invasive, unsustain-able and socially unacceptable, as they involve signi¿cant use of chemical products or energy. This Special Issue is aimed at collecting research activities focused on the development of new processes to replace the above-cited obsolete practices. Taking inspiration from real problems and the need to face real cases of contamination or prevent potentially harmful situations, the development and opti-mization of ‘smart’ solutions, i.e., sustainable not only from an environmental point of view but also economically, are discussed in order to encourage as much as possible their actual implementation.
2022-03-31T13:11:22ZGámiz Caro, Javier FranciscoGrau Saldes, AntoniMartínez García, HerminioBolea Monte, YolandaIn recent decades, increasing attention has been paid to the sustainability of products and processes, including activities aimed at environmental protection, site reclamation or treatment of contaminated ef¿uents, as well as the valorization of waste through the recovery of resources. Although implemented with ‘noble intentions’, these processes are often highly invasive, unsustain-able and socially unacceptable, as they involve signi¿cant use of chemical products or energy. This Special Issue is aimed at collecting research activities focused on the development of new processes to replace the above-cited obsolete practices. Taking inspiration from real problems and the need to face real cases of contamination or prevent potentially harmful situations, the development and opti-mization of ‘smart’ solutions, i.e., sustainable not only from an environmental point of view but also economically, are discussed in order to encourage as much as possible their actual implementation.Odometry estimation for aerial manipulation
http://hdl.handle.net/2117/182409
Odometry estimation for aerial manipulation
Santamaria Navarro, Àngel; Solà Ortega, Joan; Andrade-Cetto, Juan
This chapter explains a fast and low-cost state localization estimation method for small-sized UAVs, that uses an IMU, a smart camera and an infrared time-of-flight range sensor that act as an odometer providing absolute attitude, velocity, orientation, angular rate and acceleration at a rate higher than 100 Hz. This allows estimating almost continuously the localization of the aerial robot, when GPS or other methods can at most reach 5 Hz. This technique does not require creating a map for localization.
The final publication is available at link.springer.com
2020-03-31T11:03:36ZSantamaria Navarro, ÀngelSolà Ortega, JoanAndrade-Cetto, JuanThis chapter explains a fast and low-cost state localization estimation method for small-sized UAVs, that uses an IMU, a smart camera and an infrared time-of-flight range sensor that act as an odometer providing absolute attitude, velocity, orientation, angular rate and acceleration at a rate higher than 100 Hz. This allows estimating almost continuously the localization of the aerial robot, when GPS or other methods can at most reach 5 Hz. This technique does not require creating a map for localization.Perception for detection and grasping
http://hdl.handle.net/2117/182404
Perception for detection and grasping
Guerra Paradas, Edmundo; Pumarola Peris, Albert; Grau Saldes, Antoni; Sanfeliu Cortés, Alberto
This research presents a methodology for the detection of the crawler used in the project AEROARMS. The approach consisted on using a two-step progressive strategy, going from rough detection and tracking, for approximation maneuvers, to an accurate positioning step based on fiducial markers. Two different methods are explained for the first step, one using efficient image segmentation approach; and the second one using Deep Learning techniques to detect the center of the crawler. The fiducial markers are used for precise localization of the crawler in a similar way as explained in earlier chapters. The methods can run in real-time.
The final publication is available at link.springer.com
2020-03-31T10:53:06ZGuerra Paradas, EdmundoPumarola Peris, AlbertGrau Saldes, AntoniSanfeliu Cortés, AlbertoThis research presents a methodology for the detection of the crawler used in the project AEROARMS. The approach consisted on using a two-step progressive strategy, going from rough detection and tracking, for approximation maneuvers, to an accurate positioning step based on fiducial markers. Two different methods are explained for the first step, one using efficient image segmentation approach; and the second one using Deep Learning techniques to detect the center of the crawler. The fiducial markers are used for precise localization of the crawler in a similar way as explained in earlier chapters. The methods can run in real-time.Precise localization for aerial inspection using augmented reality markers
http://hdl.handle.net/2117/182400
Precise localization for aerial inspection using augmented reality markers
Amor Martínez, Adrián; Ruiz García, Alberto; Moreno-Noguer, Francesc; Sanfeliu Cortés, Alberto
This chapter is devoted to explaining a method for precise localization using augmented reality markers. This method can achieve precision of less of 5 mm in position at a distance of 0.7 m, using a visual mark of 17 mm × 17 mm, and it can be used by controller when the aerial robot is doing a manipulation task. The localization method is based on optimizing the alignment of deformable contours from textureless images working from the raw vertexes of the observed contour. The algorithm optimizes the alignment of the XOR area computed by means of computer graphics clipping techniques. The method can run at 25 frames per second.
The final publication is available at link.springer.com
2020-03-31T10:44:18ZAmor Martínez, AdriánRuiz García, AlbertoMoreno-Noguer, FrancescSanfeliu Cortés, AlbertoThis chapter is devoted to explaining a method for precise localization using augmented reality markers. This method can achieve precision of less of 5 mm in position at a distance of 0.7 m, using a visual mark of 17 mm × 17 mm, and it can be used by controller when the aerial robot is doing a manipulation task. The localization method is based on optimizing the alignment of deformable contours from textureless images working from the raw vertexes of the observed contour. The algorithm optimizes the alignment of the XOR area computed by means of computer graphics clipping techniques. The method can run at 25 frames per second.Relative localization for aerial manipulation with PL-SLAM
http://hdl.handle.net/2117/182388
Relative localization for aerial manipulation with PL-SLAM
Pumarola Peris, Albert; Vakhitov, A.; Agudo Martínez, Antonio; Moreno-Noguer, Francesc; Sanfeliu Cortés, Alberto
This chapter explains a precise SLAM technique, PL-SLAM, that allows to simultaneously process points and lines and tackle situations where point-only based methods are prone to fail, like poorly textured scenes or motion blurred images where feature points are vanished out. The method is remarkably robust against image noise, and that it outperforms state-of-the-art methods for point based contour alignment. The method can run in real-time and in a low cost hardware.
The final publication is available at link.springer.com
2020-03-31T10:20:24ZPumarola Peris, AlbertVakhitov, A.Agudo Martínez, AntonioMoreno-Noguer, FrancescSanfeliu Cortés, AlbertoThis chapter explains a precise SLAM technique, PL-SLAM, that allows to simultaneously process points and lines and tackle situations where point-only based methods are prone to fail, like poorly textured scenes or motion blurred images where feature points are vanished out. The method is remarkably robust against image noise, and that it outperforms state-of-the-art methods for point based contour alignment. The method can run in real-time and in a low cost hardware.Visual servoing of aerial manipulators
http://hdl.handle.net/2117/182370
Visual servoing of aerial manipulators
Santamaria Navarro, Àngel; Andrade-Cetto, Juan; Lippiello, Vincenzo
This chapter describes the classical techniques to control an aerial manipulator by means of visual information and presents an uncalibrated image-based visual servo method to drive the aerial vehicle. The proposed technique has the advantage that it contains mild assumptions about the principal point and skew values of the camera, and it does not require prior knowledge of the focal length, in contrast to traditional image-based approaches.
The final publication is available at link.springer.com
2020-03-31T10:05:30ZSantamaria Navarro, ÀngelAndrade-Cetto, JuanLippiello, VincenzoThis chapter describes the classical techniques to control an aerial manipulator by means of visual information and presents an uncalibrated image-based visual servo method to drive the aerial vehicle. The proposed technique has the advantage that it contains mild assumptions about the principal point and skew values of the camera, and it does not require prior knowledge of the focal length, in contrast to traditional image-based approaches.Robust perception for aerial inspection: Adaptive and on-line techniques
http://hdl.handle.net/2117/178159
Robust perception for aerial inspection: Adaptive and on-line techniques
Villamizar Vergel, Michael Alejandro; Sanfeliu Cortés, Alberto
This chapter explains an adaptive on-line object detection and classification technique for robust perception due to varying scene conditions, for example partial cast shadows, change on the illumination conditions or changes in the angle of the object target view. This approach continuously updates the target model upon arrival of new data, being able to adapt to dynamic situations. The method uses an on-line learning technique that works on real-time and it is continuously updated in order to adapt to potential changes undergone by the target object. The method can run in real-time.
2020-02-20T10:37:54ZVillamizar Vergel, Michael AlejandroSanfeliu Cortés, AlbertoThis chapter explains an adaptive on-line object detection and classification technique for robust perception due to varying scene conditions, for example partial cast shadows, change on the illumination conditions or changes in the angle of the object target view. This approach continuously updates the target model upon arrival of new data, being able to adapt to dynamic situations. The method uses an on-line learning technique that works on real-time and it is continuously updated in order to adapt to potential changes undergone by the target object. The method can run in real-time.Esclatec: recerca + desenvolupament + innovació x inclusió
http://hdl.handle.net/2117/118323
Esclatec: recerca + desenvolupament + innovació x inclusió
Cabré Garcia, José M.; Climent Vilaró, Joan; López Álvarez, David; Martín Escofet, Carme; Sánchez Carracedo, Fermín; Vidal López, Eva María
2018-06-21T18:48:17ZCabré Garcia, José M.Climent Vilaró, JoanLópez Álvarez, DavidMartín Escofet, CarmeSánchez Carracedo, FermínVidal López, Eva MaríaDesign and development of aerial robotic systems for sampling operations in industrial environment
http://hdl.handle.net/2117/110256
Design and development of aerial robotic systems for sampling operations in industrial environment
Munguía Alcalá, Rodrigo Francisco; Guerra Paradas, Edmundo; Urzua, Sarquis; Bolea Monte, Yolanda; Grau Saldes, Antoni
This chapter describes the development of an autonomous fluid sampling system for outdoor facilities, and the localization solution to be used. The automated sampling system will be based on collaborative robotics, with a team of a UAV and a UGV platform travelling through a plant to collect water samples. The architecture of the system is described, as well as the hardware present in the UAV and the different software frameworks used. A visual simultaneous localization and mapping (SLAM) technique is proposed to deal with the localization problem, based on authors’ previous works, including several innovations: a new method to initialize the scale using unreliable global positioning system (GPS) measurements, integration of attitude and heading reference system (AHRS) measurements into the recursive state estimation, and a new technique to track features during the delayed feature initialization process. These procedures greatly enhance the robustness and usability of the SLAM technique as they remove the requirement of assisted scale initialization, and they reduce the computational effort to initialize features. To conclude, results from experiments performed with simulated data and real data captured with a prototype UAV are presented and discussed.
2017-11-10T12:33:43ZMunguía Alcalá, Rodrigo FranciscoGuerra Paradas, EdmundoUrzua, SarquisBolea Monte, YolandaGrau Saldes, AntoniThis chapter describes the development of an autonomous fluid sampling system for outdoor facilities, and the localization solution to be used. The automated sampling system will be based on collaborative robotics, with a team of a UAV and a UGV platform travelling through a plant to collect water samples. The architecture of the system is described, as well as the hardware present in the UAV and the different software frameworks used. A visual simultaneous localization and mapping (SLAM) technique is proposed to deal with the localization problem, based on authors’ previous works, including several innovations: a new method to initialize the scale using unreliable global positioning system (GPS) measurements, integration of attitude and heading reference system (AHRS) measurements into the recursive state estimation, and a new technique to track features during the delayed feature initialization process. These procedures greatly enhance the robustness and usability of the SLAM technique as they remove the requirement of assisted scale initialization, and they reduce the computational effort to initialize features. To conclude, results from experiments performed with simulated data and real data captured with a prototype UAV are presented and discussed.Dense segmentation-aware descriptors
http://hdl.handle.net/2117/85171
Dense segmentation-aware descriptors
Trulls Fortuny, Eduard; Kokkinos, Iasonas; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc
Dense descriptors are becoming increasingly popular in a host of tasks, such as dense image correspondence, bag-of-words image classification, and label transfer. However, the extraction of descriptors on generic image points, rather than selecting geometric features, requires rethinking how to achieve invariance to nuisance parameters. In this work we pursue invariance to occlusions and background changes by introducing segmentation information within dense feature construction. The core idea is to use the segmentation cues to downplay the features coming from image areas that are unlikely to belong to the same region as the feature point. We show how to integrate this idea with dense SIFT, as well as with the dense scale- and rotation-invariant descriptor (SID). We thereby deliver dense descriptors that are invariant to background changes, rotation, and/or scaling. We explore the merit of our technique in conjunction with large displacement motion estimation and wide-baseline stereo, and demonstrate that exploiting segmentation information yields clear improvements.
2016-04-05T08:27:39ZTrulls Fortuny, EduardKokkinos, IasonasSanfeliu Cortés, AlbertoMoreno-Noguer, FrancescDense descriptors are becoming increasingly popular in a host of tasks, such as dense image correspondence, bag-of-words image classification, and label transfer. However, the extraction of descriptors on generic image points, rather than selecting geometric features, requires rethinking how to achieve invariance to nuisance parameters. In this work we pursue invariance to occlusions and background changes by introducing segmentation information within dense feature construction. The core idea is to use the segmentation cues to downplay the features coming from image areas that are unlikely to belong to the same region as the feature point. We show how to integrate this idea with dense SIFT, as well as with the dense scale- and rotation-invariant descriptor (SID). We thereby deliver dense descriptors that are invariant to background changes, rotation, and/or scaling. We explore the merit of our technique in conjunction with large displacement motion estimation and wide-baseline stereo, and demonstrate that exploiting segmentation information yields clear improvements.