Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment
Accurate detection of sea-surface objects is vital for the safe navigation of autonomous ships. With the continuous development of artificial intelligence, electro-optical (EO) sensors such as video cameras are used to supplement marine radar to improve the detection of objects that produce weak rad...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/11/1783 |
| _version_ | 1797464877299662848 |
|---|---|
| author | Zeyuan Shao Hongguang Lyu Yong Yin Tao Cheng Xiaowei Gao Wenjun Zhang Qianfeng Jing Yanjie Zhao Lunping Zhang |
| author_facet | Zeyuan Shao Hongguang Lyu Yong Yin Tao Cheng Xiaowei Gao Wenjun Zhang Qianfeng Jing Yanjie Zhao Lunping Zhang |
| author_sort | Zeyuan Shao |
| collection | DOAJ |
| description | Accurate detection of sea-surface objects is vital for the safe navigation of autonomous ships. With the continuous development of artificial intelligence, electro-optical (EO) sensors such as video cameras are used to supplement marine radar to improve the detection of objects that produce weak radar signals and small sizes. In this study, we propose an enhanced convolutional neural network (CNN) named VarifocalNet * that improves object detection in harsh maritime environments. Specifically, the feature representation and learning ability of the VarifocalNet model are improved by using a deformable convolution module, redesigning the loss function, introducing a soft non-maximum suppression algorithm, and incorporating multi-scale prediction methods. These strategies improve the accuracy and reliability of our CNN-based detection results under complex sea conditions, such as in turbulent waves, sea fog, and water reflection. Experimental results under different maritime conditions show that our method significantly outperforms similar methods (such as SSD, YOLOv3, RetinaNet, Faster R-CNN, Cascade R-CNN) in terms of the detection accuracy and robustness for small objects. The maritime obstacle detection results were obtained under harsh imaging conditions to demonstrate the performance of our network model. |
| first_indexed | 2024-03-09T18:13:27Z |
| format | Article |
| id | doaj.art-1053ce13382e4ad996a226b19b5e7f55 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T18:13:27Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-1053ce13382e4ad996a226b19b5e7f552023-11-24T08:52:52ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-11-011011178310.3390/jmse10111783Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime EnvironmentZeyuan Shao0Hongguang Lyu1Yong Yin2Tao Cheng3Xiaowei Gao4Wenjun Zhang5Qianfeng Jing6Yanjie Zhao7Lunping Zhang8Navigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaSpaceTimeLab, Department of Civil, Environmental and Geomatic Engineering, University College London (UCL), Gower Street, London WC1E 6BT, UKSpaceTimeLab, Department of Civil, Environmental and Geomatic Engineering, University College London (UCL), Gower Street, London WC1E 6BT, UKNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaChina Ship Scientific Research Center, Wuxi 214082, ChinaChina Ship Scientific Research Center, Wuxi 214082, ChinaAccurate detection of sea-surface objects is vital for the safe navigation of autonomous ships. With the continuous development of artificial intelligence, electro-optical (EO) sensors such as video cameras are used to supplement marine radar to improve the detection of objects that produce weak radar signals and small sizes. In this study, we propose an enhanced convolutional neural network (CNN) named VarifocalNet * that improves object detection in harsh maritime environments. Specifically, the feature representation and learning ability of the VarifocalNet model are improved by using a deformable convolution module, redesigning the loss function, introducing a soft non-maximum suppression algorithm, and incorporating multi-scale prediction methods. These strategies improve the accuracy and reliability of our CNN-based detection results under complex sea conditions, such as in turbulent waves, sea fog, and water reflection. Experimental results under different maritime conditions show that our method significantly outperforms similar methods (such as SSD, YOLOv3, RetinaNet, Faster R-CNN, Cascade R-CNN) in terms of the detection accuracy and robustness for small objects. The maritime obstacle detection results were obtained under harsh imaging conditions to demonstrate the performance of our network model.https://www.mdpi.com/2077-1312/10/11/1783autonomous shipssea-surfaceobject detectioncomputer visionconvolutional neural network (CNN)VarifocalNet |
| spellingShingle | Zeyuan Shao Hongguang Lyu Yong Yin Tao Cheng Xiaowei Gao Wenjun Zhang Qianfeng Jing Yanjie Zhao Lunping Zhang Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment Journal of Marine Science and Engineering autonomous ships sea-surface object detection computer vision convolutional neural network (CNN) VarifocalNet |
| title | Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment |
| title_full | Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment |
| title_fullStr | Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment |
| title_full_unstemmed | Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment |
| title_short | Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment |
| title_sort | multi scale object detection model for autonomous ship navigation in maritime environment |
| topic | autonomous ships sea-surface object detection computer vision convolutional neural network (CNN) VarifocalNet |
| url | https://www.mdpi.com/2077-1312/10/11/1783 |
| work_keys_str_mv | AT zeyuanshao multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT hongguanglyu multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT yongyin multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT taocheng multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT xiaoweigao multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT wenjunzhang multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT qianfengjing multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT yanjiezhao multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment AT lunpingzhang multiscaleobjectdetectionmodelforautonomousshipnavigationinmaritimeenvironment |