Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models
In the context of new geopolitical tensions due to the current armed conflicts, safety in terms of navigation has been threatened due to the large number of sea mines placed, in particular, within the sea conflict areas. Additionally, since a large number of mines have recently been reported to have...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/23/9536 |
| _version_ | 1797462021631901696 |
|---|---|
| author | Dan Munteanu Diana Moina Cristina Gabriela Zamfir Ștefan Mihai Petrea Dragos Sebastian Cristea Nicoleta Munteanu |
| author_facet | Dan Munteanu Diana Moina Cristina Gabriela Zamfir Ștefan Mihai Petrea Dragos Sebastian Cristea Nicoleta Munteanu |
| author_sort | Dan Munteanu |
| collection | DOAJ |
| description | In the context of new geopolitical tensions due to the current armed conflicts, safety in terms of navigation has been threatened due to the large number of sea mines placed, in particular, within the sea conflict areas. Additionally, since a large number of mines have recently been reported to have drifted into the territories of the Black Sea countries such as Romania, Bulgaria Georgia and Turkey, which have intense commercial and tourism activities in their coastal areas, the safety of those economic activities is threatened by possible accidents that may occur due to the above-mentioned situation. The use of deep learning in a military operation is widespread, especially for combating drones and other killer robots. Therefore, the present research addresses the detection of floating and underwater sea mines using images recorded from cameras (taken from drones, submarines, ships and boats). Due to the low number of sea mine images, the current research used both an augmentation technique and synthetic image generation (by overlapping images with different types of mines over water backgrounds), and two datasets were built (for floating mines and for underwater mines). Three deep learning models, respectively, YOLOv5, SSD and EfficientDet (YOLOv5 and SSD for floating mines and YOLOv5 and EfficientDet for underwater mines), were trained and compared. In the context of using three algorithm models, YOLO, SSD and EfficientDet, the new generated system revealed high accuracy in object recognition, namely the detection of floating and anchored mines. Moreover, tests carried out on portable computing equipment, such as Raspberry Pi, illustrated the possibility of including such an application for real-time scenarios, with the time of 2 s per frame being improved if devices use high-performance cameras. |
| first_indexed | 2024-03-09T17:31:27Z |
| format | Article |
| id | doaj.art-07f3af7c4984465f98f8470829c42be4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T17:31:27Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-07f3af7c4984465f98f8470829c42be42023-11-24T12:16:02ZengMDPI AGSensors1424-82202022-12-012223953610.3390/s22239536Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning ModelsDan Munteanu0Diana Moina1Cristina Gabriela Zamfir2Ștefan Mihai Petrea3Dragos Sebastian Cristea4Nicoleta Munteanu5Faculty of Automation, Computer Sciences, Electronics and Electrical Engineering, “Dunǎrea de Jos” University of Galaţi, No. 111 Street Domneascǎ, 800210 Galati, RomaniaFaculty of Automation, Computer Sciences, Electronics and Electrical Engineering, “Dunǎrea de Jos” University of Galaţi, No. 111 Street Domneascǎ, 800210 Galati, RomaniaFaculty of Economics and Business Administration, “Dunarea de Jos” University of Galati, 800008 Galati, RomaniaFaculty of Economics and Business Administration, “Dunarea de Jos” University of Galati, 800008 Galati, RomaniaFaculty of Economics and Business Administration, “Dunarea de Jos” University of Galati, 800008 Galati, RomaniaChildren’s Palace Galati, 800116 Galati, RomaniaIn the context of new geopolitical tensions due to the current armed conflicts, safety in terms of navigation has been threatened due to the large number of sea mines placed, in particular, within the sea conflict areas. Additionally, since a large number of mines have recently been reported to have drifted into the territories of the Black Sea countries such as Romania, Bulgaria Georgia and Turkey, which have intense commercial and tourism activities in their coastal areas, the safety of those economic activities is threatened by possible accidents that may occur due to the above-mentioned situation. The use of deep learning in a military operation is widespread, especially for combating drones and other killer robots. Therefore, the present research addresses the detection of floating and underwater sea mines using images recorded from cameras (taken from drones, submarines, ships and boats). Due to the low number of sea mine images, the current research used both an augmentation technique and synthetic image generation (by overlapping images with different types of mines over water backgrounds), and two datasets were built (for floating mines and for underwater mines). Three deep learning models, respectively, YOLOv5, SSD and EfficientDet (YOLOv5 and SSD for floating mines and YOLOv5 and EfficientDet for underwater mines), were trained and compared. In the context of using three algorithm models, YOLO, SSD and EfficientDet, the new generated system revealed high accuracy in object recognition, namely the detection of floating and anchored mines. Moreover, tests carried out on portable computing equipment, such as Raspberry Pi, illustrated the possibility of including such an application for real-time scenarios, with the time of 2 s per frame being improved if devices use high-performance cameras.https://www.mdpi.com/1424-8220/22/23/9536floating and underwater mine detectiondeep learningsynthetic imageobject recognition |
| spellingShingle | Dan Munteanu Diana Moina Cristina Gabriela Zamfir Ștefan Mihai Petrea Dragos Sebastian Cristea Nicoleta Munteanu Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models Sensors floating and underwater mine detection deep learning synthetic image object recognition |
| title | Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models |
| title_full | Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models |
| title_fullStr | Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models |
| title_full_unstemmed | Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models |
| title_short | Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models |
| title_sort | sea mine detection framework using yolo ssd and efficientdet deep learning models |
| topic | floating and underwater mine detection deep learning synthetic image object recognition |
| url | https://www.mdpi.com/1424-8220/22/23/9536 |
| work_keys_str_mv | AT danmunteanu seaminedetectionframeworkusingyolossdandefficientdetdeeplearningmodels AT dianamoina seaminedetectionframeworkusingyolossdandefficientdetdeeplearningmodels AT cristinagabrielazamfir seaminedetectionframeworkusingyolossdandefficientdetdeeplearningmodels AT stefanmihaipetrea seaminedetectionframeworkusingyolossdandefficientdetdeeplearningmodels AT dragossebastiancristea seaminedetectionframeworkusingyolossdandefficientdetdeeplearningmodels AT nicoletamunteanu seaminedetectionframeworkusingyolossdandefficientdetdeeplearningmodels |