Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet
Video-based ship object detection has long been a popular research issue that has received attention in the water transportation industry. However, in low-illumination environments, such as at night or in fog, the water environment has a complex variety of light sources, video surveillance images ar...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/12/1996 |
| _version_ | 1797456898873622528 |
|---|---|
| author | Ruixin Ma Kexin Bao Yong Yin |
| author_facet | Ruixin Ma Kexin Bao Yong Yin |
| author_sort | Ruixin Ma |
| collection | DOAJ |
| description | Video-based ship object detection has long been a popular research issue that has received attention in the water transportation industry. However, in low-illumination environments, such as at night or in fog, the water environment has a complex variety of light sources, video surveillance images are often accompanied by noise, and information on the details of objects in images is worsened. These problems cause high rates of false detection and missed detection when performing object detection for ships in low-illumination environments. Thus, this paper takes the detection of ship objects in low-illumination environments at night as the research object. The technical difficulties faced by object detection algorithms in low-illumination environments are analyzed, and a dataset of ship images is constructed by collecting images of ships (in the Nanjing section of Yangtze River in China) in low-illumination environments. In view of the outstanding performance of the RetinaNet model in general object detection, a new multiscale feature fusion network structure for a feature extraction module is proposed based on the same network architecture, in such a way that the extraction of more potential feature information from low-illumination images can be realized. In line with the feature detection network, the regression and classification detection network for anchor boxes is improved by means of the attention mechanism, guiding the network structure in the detection of object features. Moreover, the design and optimization of the augmentation of multiple random images and prior bounding boxes in the training process are also carried out. Finally, on the basis of experimental validation analysis, the optimized detection model was able to improve ship detection accuracy by 3.7% with a limited decrease in FPS (frames per second), and has better results in application. |
| first_indexed | 2024-03-09T16:14:27Z |
| format | Article |
| id | doaj.art-f9df5f51f4de440793cf80a5de547ea0 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T16:14:27Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-f9df5f51f4de440793cf80a5de547ea02023-11-24T15:57:53ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-12-011012199610.3390/jmse10121996Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANetRuixin Ma0Kexin Bao1Yong Yin2Key Laboratory of Marine Simulation and Control, Dalian Maritime University, Dalian 116026, ChinaTianjin Research Institute for Water Transport Engineering, M.O.T., Tianjin 300456, ChinaKey Laboratory of Marine Simulation and Control, Dalian Maritime University, Dalian 116026, ChinaVideo-based ship object detection has long been a popular research issue that has received attention in the water transportation industry. However, in low-illumination environments, such as at night or in fog, the water environment has a complex variety of light sources, video surveillance images are often accompanied by noise, and information on the details of objects in images is worsened. These problems cause high rates of false detection and missed detection when performing object detection for ships in low-illumination environments. Thus, this paper takes the detection of ship objects in low-illumination environments at night as the research object. The technical difficulties faced by object detection algorithms in low-illumination environments are analyzed, and a dataset of ship images is constructed by collecting images of ships (in the Nanjing section of Yangtze River in China) in low-illumination environments. In view of the outstanding performance of the RetinaNet model in general object detection, a new multiscale feature fusion network structure for a feature extraction module is proposed based on the same network architecture, in such a way that the extraction of more potential feature information from low-illumination images can be realized. In line with the feature detection network, the regression and classification detection network for anchor boxes is improved by means of the attention mechanism, guiding the network structure in the detection of object features. Moreover, the design and optimization of the augmentation of multiple random images and prior bounding boxes in the training process are also carried out. Finally, on the basis of experimental validation analysis, the optimized detection model was able to improve ship detection accuracy by 3.7% with a limited decrease in FPS (frames per second), and has better results in application.https://www.mdpi.com/2077-1312/10/12/1996deep learningcomputer visionship object detectionRetinaNetlow-illumination environment |
| spellingShingle | Ruixin Ma Kexin Bao Yong Yin Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet Journal of Marine Science and Engineering deep learning computer vision ship object detection RetinaNet low-illumination environment |
| title | Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet |
| title_full | Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet |
| title_fullStr | Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet |
| title_full_unstemmed | Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet |
| title_short | Improved Ship Object Detection in Low-Illumination Environments Using RetinaMFANet |
| title_sort | improved ship object detection in low illumination environments using retinamfanet |
| topic | deep learning computer vision ship object detection RetinaNet low-illumination environment |
| url | https://www.mdpi.com/2077-1312/10/12/1996 |
| work_keys_str_mv | AT ruixinma improvedshipobjectdetectioninlowilluminationenvironmentsusingretinamfanet AT kexinbao improvedshipobjectdetectioninlowilluminationenvironmentsusingretinamfanet AT yongyin improvedshipobjectdetectioninlowilluminationenvironmentsusingretinamfanet |