People detection measurement setup based on a DOA approach implemented on a sensorised social robot
A measurement setup for localising people in indoor environment based on a system characterized by acquisition of audio files and images implemented on a sensorised social robot is proposed. The audio signal processing for human voice identification applies the segmentation methodology for the direc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | Measurement: Sensors |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665917422002835 |
| _version_ | 1811176105775726592 |
|---|---|
| author | Ilaria Ciuffreda Gianmarco Battista Sara Casaccia Gian Marco Revel |
| author_facet | Ilaria Ciuffreda Gianmarco Battista Sara Casaccia Gian Marco Revel |
| author_sort | Ilaria Ciuffreda |
| collection | DOAJ |
| description | A measurement setup for localising people in indoor environment based on a system characterized by acquisition of audio files and images implemented on a sensorised social robot is proposed. The audio signal processing for human voice identification applies the segmentation methodology for the direction of arrival (DOA) estimation. The audio signal analysis evaluates the performance of beamforming algorithms and of Covariance Matrix Fitting (CMF) when optimization in beamforming algorithm and alternative microphones’ configurations have been evaluated by simulations. Tests shows an accuracy in people detection of the optimized beamforming algorithm comparable to CMF method (96.5% and 96.6% respectively) with a lower computational cost. An image acquisition procedure has been then activated on the robot and the localisation of the people is performed using YOLO-v3 algorithm. Monte Carlo method applied to evaluate the propagation of uncertainty of the whole processing system presents a global accuracy of 98.2 ± 0.8%. |
| first_indexed | 2024-04-10T19:47:47Z |
| format | Article |
| id | doaj.art-c9c5dbcf01ac4feca4db73e6141154c3 |
| institution | Directory Open Access Journal |
| issn | 2665-9174 |
| language | English |
| last_indexed | 2024-04-10T19:47:47Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Measurement: Sensors |
| spelling | doaj.art-c9c5dbcf01ac4feca4db73e6141154c32023-01-29T04:22:01ZengElsevierMeasurement: Sensors2665-91742023-02-0125100649People detection measurement setup based on a DOA approach implemented on a sensorised social robotIlaria Ciuffreda0Gianmarco Battista1Sara Casaccia2Gian Marco Revel3Dipartimento di Ingegneria Industriale e Scienze Matematiche, Università Politecnica delle Marche, Ancona, Italy; Corresponding author. Dipartimento di Ingegneria Industriale e Scienze Matematiche (DIISM), Università Politecnica delle Marche, Via Brecce Bianche, 60131, Ancona, Italy.Università di Parma, Department of Engineering and Architecture, Parco Area delle Scienze 181/A, 43124, Parma, ItalyDipartimento di Ingegneria Industriale e Scienze Matematiche, Università Politecnica delle Marche, Ancona, ItalyDipartimento di Ingegneria Industriale e Scienze Matematiche, Università Politecnica delle Marche, Ancona, ItalyA measurement setup for localising people in indoor environment based on a system characterized by acquisition of audio files and images implemented on a sensorised social robot is proposed. The audio signal processing for human voice identification applies the segmentation methodology for the direction of arrival (DOA) estimation. The audio signal analysis evaluates the performance of beamforming algorithms and of Covariance Matrix Fitting (CMF) when optimization in beamforming algorithm and alternative microphones’ configurations have been evaluated by simulations. Tests shows an accuracy in people detection of the optimized beamforming algorithm comparable to CMF method (96.5% and 96.6% respectively) with a lower computational cost. An image acquisition procedure has been then activated on the robot and the localisation of the people is performed using YOLO-v3 algorithm. Monte Carlo method applied to evaluate the propagation of uncertainty of the whole processing system presents a global accuracy of 98.2 ± 0.8%.http://www.sciencedirect.com/science/article/pii/S2665917422002835LocalisationRGB imageAudio signalsNon-invasive measurement |
| spellingShingle | Ilaria Ciuffreda Gianmarco Battista Sara Casaccia Gian Marco Revel People detection measurement setup based on a DOA approach implemented on a sensorised social robot Measurement: Sensors Localisation RGB image Audio signals Non-invasive measurement |
| title | People detection measurement setup based on a DOA approach implemented on a sensorised social robot |
| title_full | People detection measurement setup based on a DOA approach implemented on a sensorised social robot |
| title_fullStr | People detection measurement setup based on a DOA approach implemented on a sensorised social robot |
| title_full_unstemmed | People detection measurement setup based on a DOA approach implemented on a sensorised social robot |
| title_short | People detection measurement setup based on a DOA approach implemented on a sensorised social robot |
| title_sort | people detection measurement setup based on a doa approach implemented on a sensorised social robot |
| topic | Localisation RGB image Audio signals Non-invasive measurement |
| url | http://www.sciencedirect.com/science/article/pii/S2665917422002835 |
| work_keys_str_mv | AT ilariaciuffreda peopledetectionmeasurementsetupbasedonadoaapproachimplementedonasensorisedsocialrobot AT gianmarcobattista peopledetectionmeasurementsetupbasedonadoaapproachimplementedonasensorisedsocialrobot AT saracasaccia peopledetectionmeasurementsetupbasedonadoaapproachimplementedonasensorisedsocialrobot AT gianmarcorevel peopledetectionmeasurementsetupbasedonadoaapproachimplementedonasensorisedsocialrobot |