Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations
For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective ‘Detect and Avoid’ systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based ‘Detect and Avoid’ system, composed of microphones and an emb...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/12/2076 |
| _version_ | 1797545632580239360 |
|---|---|
| author | Jorge Mariscal-Harana Víctor Alarcón Fidel González Juan José Calvente Francisco Javier Pérez-Grau Antidio Viguria Aníbal Ollero |
| author_facet | Jorge Mariscal-Harana Víctor Alarcón Fidel González Juan José Calvente Francisco Javier Pérez-Grau Antidio Viguria Aníbal Ollero |
| author_sort | Jorge Mariscal-Harana |
| collection | DOAJ |
| description | For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective ‘Detect and Avoid’ systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based ‘Detect and Avoid’ system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet’s optimal configuration, with >70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e., 10 Hz). While our proposed ‘Detect and Avoid’ system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance. |
| first_indexed | 2024-03-10T14:18:03Z |
| format | Article |
| id | doaj.art-f6f1b42843e44708b219c9f4745df6b9 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T14:18:03Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-f6f1b42843e44708b219c9f4745df6b92023-11-20T23:37:59ZengMDPI AGElectronics2079-92922020-12-01912207610.3390/electronics9122076Audio-Based Aircraft Detection System for Safe RPAS BVLOS OperationsJorge Mariscal-Harana0Víctor Alarcón1Fidel González2Juan José Calvente3Francisco Javier Pérez-Grau4Antidio Viguria5Aníbal Ollero6Avionics and Systems, Advanced Center for Aerospace Technologies (FADA-CATEC), 41309 Sevilla, SpainAvionics and Systems, Advanced Center for Aerospace Technologies (FADA-CATEC), 41309 Sevilla, SpainAvionics and Systems, Advanced Center for Aerospace Technologies (FADA-CATEC), 41309 Sevilla, SpainRPAS, Aertec Solutions, 41309 Sevilla, SpainAvionics and Systems, Advanced Center for Aerospace Technologies (FADA-CATEC), 41309 Sevilla, SpainAvionics and Systems, Advanced Center for Aerospace Technologies (FADA-CATEC), 41309 Sevilla, SpainRobotics, Vision and Control Group (GRVC), University of Seville, 41092 Seville, SpainFor the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective ‘Detect and Avoid’ systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based ‘Detect and Avoid’ system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet’s optimal configuration, with >70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e., 10 Hz). While our proposed ‘Detect and Avoid’ system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.https://www.mdpi.com/2079-9292/9/12/2076deep learningsound event detectionconvolutional neural networksaudio processingembedded systems |
| spellingShingle | Jorge Mariscal-Harana Víctor Alarcón Fidel González Juan José Calvente Francisco Javier Pérez-Grau Antidio Viguria Aníbal Ollero Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations Electronics deep learning sound event detection convolutional neural networks audio processing embedded systems |
| title | Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations |
| title_full | Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations |
| title_fullStr | Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations |
| title_full_unstemmed | Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations |
| title_short | Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations |
| title_sort | audio based aircraft detection system for safe rpas bvlos operations |
| topic | deep learning sound event detection convolutional neural networks audio processing embedded systems |
| url | https://www.mdpi.com/2079-9292/9/12/2076 |
| work_keys_str_mv | AT jorgemariscalharana audiobasedaircraftdetectionsystemforsaferpasbvlosoperations AT victoralarcon audiobasedaircraftdetectionsystemforsaferpasbvlosoperations AT fidelgonzalez audiobasedaircraftdetectionsystemforsaferpasbvlosoperations AT juanjosecalvente audiobasedaircraftdetectionsystemforsaferpasbvlosoperations AT franciscojavierperezgrau audiobasedaircraftdetectionsystemforsaferpasbvlosoperations AT antidioviguria audiobasedaircraftdetectionsystemforsaferpasbvlosoperations AT anibalollero audiobasedaircraftdetectionsystemforsaferpasbvlosoperations |