An Approach to Accurate Ship Image Recognition in a Complex Maritime Transportation Environment
Abstract
:1. Introduction
- (1)
- This paper proposes a Soft-DIOU-NMS with weighted box fusion to improve the accuracy and recall of ship detection.
- (2)
- This paper proposes a hybrid weighted feature fusion method, which can reduce the miss detection and error detection of ships in complex background environment and improve the localization accuracy of ships.
2. Related Works
3. Methodologies
3.1. Network Architecture
3.2. Soft-DIOU-NMS with Weighted Box Fusion
Algorithm 1 Pseudocode of Soft-DIOU-NMS with weighted fusion box. Soft-DIOU-NMS with weighted fusion box | |
Input: | |
B is the list of one class initial detection boxes | |
S contains corresponding detection scores | |
is bounding box location information fusion threshold | |
Output: | |
1 | D |
2 | whiledo |
3 | |
4 | |
5 | if then |
6 | |
7 | end if |
8 | D; B |
9 | for in B do |
10 | if then |
11 | |
12 | end if |
13 | end for |
14 | end while |
3.3. Hybrid Weighted Feature Fusion
4. Experiments and Results
4.1. Dataset Description
4.2. Evaluation Metrics
4.3. Experimental Environment and Parameter Settings
4.4. Experimental Results and Analysis
4.4.1. Soft-DIOU-NMS with Weighted Box Fusion Experiment
4.4.2. Hybrid Weighted Feature Fusion Experiment
4.4.3. Combination Experiment of Two Methods
4.4.4. Visual Comparative Analysis
4.4.5. Comparative Analysis of the Detection Results of the Two Methods under Different Backgrounds
4.4.6. Compare with Other Methods
5. Discussion
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Zhang, M.; Zhang, D.; Fu, S.; Kujala, P.; Hirdaris, S. A predictive analytics method for maritime traffic flow complexity estimation in inland waterways. Reliab. Eng. Syst. Saf. 2022, 220, 108317. [Google Scholar] [CrossRef]
- Qin, X.; Yan, M.; Zhu, D. Research on information fusion structure of radar and AIS. In Proceedings of the 2018 Chinese Control And Decision Conference (CCDC), Shenyang, China, 9–11 June 2018; pp. 3316–3322. [Google Scholar]
- Lazarowska, A. Verification of ship’s trajectory planning algorithms using real navigational data. TransNav Int. J. Mar. Navig. Saf. Sea Transp. 2019, 13, 559–564. [Google Scholar] [CrossRef]
- Nosov, V.N.; Kaledin, S.B.; Ivanov, S.G.; Timonin, V.I. Remote Tracking to Monitor Ship Tracks at or near the Water Surface. Opt. Spectrosc. 2019, 127, 669–674. [Google Scholar] [CrossRef]
- Zhang, M.; Conti, F.; Le Sourne, H.; Vassalos, D.; Kujala, P.; Lindroth, D.; Hirdaris, S. A method for the direct assessment of ship collision damage and flooding risk in real conditions. Ocean Eng. 2021, 237, 109605. [Google Scholar] [CrossRef]
- Zhang, M.; Kujala, P.; Hirdaris, S. A machine learning method for the evaluation of ship grounding risk in real operational conditions. Reliab. Eng. Syst. Saf. 2022, 226, 108697. [Google Scholar] [CrossRef]
- Zhang, M.; Montewka, J.; Manderbacka, T.; Kujala, P.; Hirdaris, S. A Big Data Analytics Method for the Evaluation of Ship—Ship Collision Risk reflecting Hydrometeorological Conditions. Reliab. Eng. Syst. Saf. 2021, 213, 107674. [Google Scholar] [CrossRef]
- Wolsing, K.; Roepert, L.; Bauer, J.; Wehrle, K. Anomaly Detection in Maritime AIS Tracks: A Review of Recent Approaches. J. Mar. Sci. Eng. 2022, 10, 112. [Google Scholar] [CrossRef]
- Li, L.; Liu, G.; Li, Z.; Ding, Z.; Qin, T. Infrared ship detection based on time fluctuation feature and space structure feature in sun-glint scene. Infrared Phys. Technol. 2021, 115, 103693. [Google Scholar] [CrossRef]
- Farahnakian, F.; Heikkonen, J. Deep Learning Based Multi-Modal Fusion Architectures for Maritime Vessel Detection. Remote Sens. 2020, 12, 2509. [Google Scholar] [CrossRef]
- Wang, Y. Development of AtoN Real-time Video Surveillance System Based on the AIS Collision Warning. In Proceedings of the 2019 5th International Conference on Transportation Information and Safety (ICTIS), Liverpool, UK, 14–17 July 2019; pp. 393–398. [Google Scholar]
- Nalamati, M.; Sharma, N.; Saqib, M.; Blumenstein, M. Automated Monitoring in Maritime Video Surveillance System. In Proceedings of the 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), Wellington, New Zealand, 25–27 November 2020; pp. 1–6. [Google Scholar]
- Song, H.; Lee, K.; Kim, D.H. Obstacle Avoidance System with LiDAR Sensor Based Fuzzy Control for an Autonomous Unmanned Ship. In Proceedings of the 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS), Toyama, Japan, 5–8 December 2018; pp. 718–722. [Google Scholar]
- Tassetti, A.N.; Galdelli, A.; Pulcinella, J.; Mancini, A.; Bolognini, L. Addressing Gaps in Small-Scale Fisheries: A Low-Cost Tracking System. Sensors 2022, 22, 839. [Google Scholar] [CrossRef]
- Galdelli, A.; Mancini, A.; Tassetti, A.N.; Ferrà Vega, C.; Armelloni, E.; Scarcella, G.; Fabi, G.; Zingaretti, P. A cloud computing architecture to map trawling activities using positioning data. In Proceedings of the International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Anaheim, CA, USA, 18–21 August 2019; American Society of Mechanical Engineers: New York, NY, USA, 2019; Volume 59292, p. V009T12A035. [Google Scholar]
- Kanjir, U.; Greidanus, H.; Oštir, K. Vessel detection and classification from spaceborne optical images: A literature survey. Remote Sens. Environ. 2018, 207, 1–26. [Google Scholar] [CrossRef] [PubMed]
- Chen, Z.; Chen, D.; Zhang, Y.; Cheng, X.; Zhang, M.; Wu, C. Deep learning for autonomous ship-oriented small ship detection. Saf. Sci. 2020, 130, 104812. [Google Scholar] [CrossRef]
- Li, Z.; Zhang, Q.; Long, T.; Zhao, B. Ship target detection and recognition method on sea surface based on multi-level hybrid network. J. BEIJING Inst. Technol. 2021, 30, 1–10. [Google Scholar]
- Chen, X.; Qi, L.; Yang, Y.; Postolache, O.; Yu, Z.; Xu, X. Port Ship Detection in Complex Environments. In Proceedings of the 2019 International Conference on Sensing and Instrumentation in IoT Era (ISSI), Lisbon, Portugal, 29–30 August 2019; pp. 1–6. [Google Scholar]
- Sun, J.; Xu, Z.; Liang, S. NSD-SSD: A Novel Real-Time Ship Detector Based on Convolutional Neural Network in Surveillance Video. Comput. Intell. Neurosci. 2021, 2021, 7018035. [Google Scholar] [CrossRef]
- Liu, R.W.; Yuan, W.; Chen, X.; Lu, Y. An enhanced CNN-enabled learning method for promoting ship detection in maritime surveillance system. Ocean Eng. 2021, 235, 109435. [Google Scholar] [CrossRef]
- Chang, L.; Chen, Y.-T.; Wang, J.-H.; Chang, Y.-L. Modified Yolov3 for Ship Detection with Visible and Infrared Images. Electronics 2022, 11, 739. [Google Scholar] [CrossRef]
- Zhang, Y.; Li, Q.-Z.; Zang, F.-N. Ship detection for visual maritime surveillance from non-stationary platforms. Ocean Eng. 2017, 141, 53–63. [Google Scholar] [CrossRef]
- Chen, Z.; Li, B.; Tian, L.F.; Chao, D. Automatic detection and tracking of ship based on mean shift in corrected video sequences. In Proceedings of the 2017 2nd International Conference on Image, Vision and Computing (ICIVC), Chengdu, China, 2–4 June 2017; pp. 449–453. [Google Scholar]
- Shan, X.; Zhao, D.; Pan, M.; Wang, D.; Zhao, L. Sea–Sky Line and Its Nearby Ships Detection Based on the Motion Attitude of Visible Light Sensors. Sensors 2019, 19, 4004. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Liu, L.; Liu, G.; Chu, X.M.; Jiang, Z.L.; Zhang, M.Y.; Ye, J. Ship Detection and Tracking in Nighttime Video Images Based on the Method of LSDT. J. Phys. Conf. Ser. 2019, 1187, 42074. [Google Scholar] [CrossRef]
- You, X.; Yu, N. An Automatic Matching Algorithm Based on SIFT Descriptors for Remote Sensing Ship Image. In Proceedings of the 2011 Sixth International Conference on Image and Graphics, Hefei, China, 12–15 August 2011; pp. 377–381. [Google Scholar]
- Shafer, S.; Harguess, J.; Forero, P.A. Sparsity-driven anomaly detection for ship detection and tracking in maritime video. In Proceedings of the Automatic Target Recognition XXV, SPIE, Baltimore, MD, USA, 22 May 2015; Volume 9476, pp. 75–82. [Google Scholar]
- Girshick, R.; Donahue, J.; Darrell, T.; Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 580–587. [Google Scholar]
- Zhang, L.; Lin, L.; Liang, X.; He, K. Is faster R-CNN doing well for pedestrian detection? In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 443–457. [Google Scholar]
- He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2961–2969. [Google Scholar]
- Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 779–788. [Google Scholar]
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.-Y.; Berg, A.C. SSD: Single Shot MultiBox Detector. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 21–37. [Google Scholar]
- Law, H.; Deng, J. Cornernet: Detecting objects as paired keypoints. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 734–750. [Google Scholar]
- Duan, K.; Bai, S.; Xie, L.; Qi, H.; Huang, Q.; Tian, Q. Centernet: Keypoint triplets for object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea, 27 October–2 November 2019; pp. 6569–6578. [Google Scholar]
- Wang, L.; Fan, S.; Liu, Y.; Li, Y.; Fei, C.; Liu, J.; Liu, B.; Dong, Y.; Liu, Z.; Zhao, X. A Review of Methods for Ship Detection with Electro-Optical Images in Marine Environments. J. Mar. Sci. Eng. 2021, 9, 1408. [Google Scholar] [CrossRef]
- Shao, Z.; Wang, L.; Wang, Z.; Du, W.; Wu, W. Saliency-aware convolution neural network for ship detection in surveillance video. IEEE Trans. Circuits Syst. Video Technol. 2019, 30, 781–794. [Google Scholar] [CrossRef]
- Kim, K.; Hong, S.; Choi, B.; Kim, E. Probabilistic ship detection and classification using deep learning. Appl. Sci. 2018, 8, 936. [Google Scholar] [CrossRef] [Green Version]
- Chen, J.; Xie, F.; Lu, Y.; Jiang, Z. Finding arbitrary-oriented ships from remote sensing images using corner detection. IEEE Geosci. Remote Sens. Lett. 2019, 17, 1712–1716. [Google Scholar] [CrossRef]
- Qi, L.; Li, B.; Chen, L.; Wang, W.; Dong, L.; Jia, X.; Huang, J.; Ge, C.; Xue, G.; Wang, D. Ship target detection algorithm based on improved faster R-CNN. Electronics 2019, 8, 959. [Google Scholar] [CrossRef] [Green Version]
- Lin, T.-Y.; Dollár, P.; Girshick, R.; He, K.; Hariharan, B.; Belongie, S. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2117–2125. [Google Scholar]
- Hosang, J.; Benenson, R.; Schiele, B. Learning non-maximum suppression. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4507–4515. [Google Scholar]
- Bodla, N.; Singh, B.; Chellappa, R.; Davis, L.S. Soft-NMS-improving object detection with one line of code. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 5561–5569. [Google Scholar]
- Zheng, Z.; Wang, P.; Liu, W.; Li, J.; Ye, R.; Ren, D. Distance-IoU loss: Faster and better learning for bounding box regression. In Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 7–12 February 2020; Volume 34, pp. 12993–13000. [Google Scholar]
- Zeiler, M.D.; Fergus, R. Visualizing and understanding convolutional networks. In Proceedings of the European Conference on Computer Vision, Zurich, Switzerland, 6–12 September 2014; pp. 818–833. [Google Scholar]
- Wang, Q.; Wu, B.; Zhu, P.; Li, P.; Hu, Q. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. arXiv 2020, arXiv:1910.03151. [Google Scholar]
- Tan, M.; Pang, R.; Le, Q.V. Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 10781–10790. [Google Scholar]
- Chen, K.; Wang, J.; Pang, J.; Cao, Y.; Xiong, Y.; Li, X.; Sun, S.; Feng, W.; Liu, Z.; Xu, J.; et al. MMDetection: Open MMLab Detection Toolbox and Benchmark. arXiv 2019, arXiv:1906.07155. [Google Scholar] [CrossRef]
- Liu, S.; Qi, L.; Qin, H.; Shi, J.; Jia, J. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 8759–8768. [Google Scholar]
AP | AP50 | AP75 | APS | APM | APL | ARall-100 | |
---|---|---|---|---|---|---|---|
Baseline | 51.0 | 78.4 | 55.3 | 6.1 | 23.0 | 58.8 | 60.8 |
Soft-NMS (Gaussian) | 52.1 | 78.1 | 57.9 | 6.4 | 23.6 | 60.2 | 67.0 |
Soft-NMS (DIOU) | 52.2 | 78.0 | 58.1 | 6.4 | 23.6 | 60.2 | 67.7 |
Candidate box fusion (α = 0.70) | 52.5 | 78.0 | 57.6 | 6.1 | 23.9 | 60.6 | 66.4 |
Candidate box fusion (α = 0.75) | 52.8 | 78.0 | 58.0 | 6.2 | 23.9 | 60.9 | 66.9 |
Candidate box fusion (α = 0.80) | 53.1 | 78.0 | 57.8 | 6.3 | 24.0 | 61.3 | 67.6 |
Candidate box fusion (α = 0.85) | 53.1 | 77.9 | 57.8 | 6.3 | 23.3 | 61.4 | 67.9 |
Candidate box fusion (α = 0.90) | 52.9 | 78.0 | 57.8 | 6.3 | 24.0 | 61.1 | 68.2 |
AP | AP50 | AP75 | APS | APM | APL | ARall-100 | |
---|---|---|---|---|---|---|---|
Baseline | 51.0 | 78.4 | 55.3 | 6.1 | 23.0 | 58.8 | 60.8 |
PAFPN | 52.8 | 79.4 | 57.1 | 6.7 | 24.7 | 60.5 | 61.8 |
A-FPN | 52.0 | 78.4 | 55.4 | 5.2 | 22.4 | 60.2 | 61.2 |
B-FPN | 53.5 | 79.0 | 57.3 | 7.1 | 25.2 | 61.4 | 62.3 |
C-FPN | 52.2 | 78.3 | 56.2 | 5.8 | 23.6 | 60.3 | 61.2 |
D-FPN | 52.5 | 78.7 | 56.8 | 6.2 | 24.4 | 60.6 | 61.7 |
AP | AP50 | AP75 | APS | APM | APL | ARall-100 | |
---|---|---|---|---|---|---|---|
Baseline | 51.0 | 78.4 | 55.3 | 6.1 | 23.0 | 58.8 | 60.8 |
Only_ Normalized | 52.4 | 78.6 | 56.1 | 7.2 | 23.2 | 60.4 | 61.7 |
Only_ECA-based | 52.7 | 79.0 | 57.1 | 7.3 | 23.5 | 60.6 | 62.0 |
B-FPN | 53.5 | 79.0 | 57.3 | 7.1 | 25.2 | 61.4 | 62.3 |
Method1 | Method2 | AP | AP50 | AP75 | APS | APM | APL | ARall-100 |
---|---|---|---|---|---|---|---|---|
51.0 | 78.4 | 55.3 | 6.1 | 23.0 | 58.8 | 60.8 | ||
√ | 53.5 | 79.0 | 57.3 | 7.1 | 25.2 | 61.4 | 62.3 | |
√ | √ | 54.9 | 78.8 | 59.5 | 7.4 | 26.1 | 63.0 | 68.3 |
Algorithm | Backbone | FLOPs (G) | Params (M) | mAP (%) |
---|---|---|---|---|
Faster R-CNN+FPN | Resnet18 | 148.00 | 28.15 | 51.0 |
Faster R-CNN+FPN | Resnet50 | 203.44 | 41.15 | 54.1 |
Faster R-CNN+PAFPN | Resnet18 | 174.02 | 31.69 | 52.8 |
Cascade R-CNN+FPN | Resnet18 | 150.02 | 55.94 | 54.9 |
Libra R-CNN+FPN | Resnet18 | 149.11 | 28.41 | 54.0 |
SR-CNN | Resnet18 | 148.03 | 28.15 | 54.9 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yu, M.; Han, S.; Wang, T.; Wang, H. An Approach to Accurate Ship Image Recognition in a Complex Maritime Transportation Environment. J. Mar. Sci. Eng. 2022, 10, 1903. https://doi.org/10.3390/jmse10121903
Yu M, Han S, Wang T, Wang H. An Approach to Accurate Ship Image Recognition in a Complex Maritime Transportation Environment. Journal of Marine Science and Engineering. 2022; 10(12):1903. https://doi.org/10.3390/jmse10121903
Chicago/Turabian StyleYu, Meng, Shaojie Han, Tengfei Wang, and Haiyan Wang. 2022. "An Approach to Accurate Ship Image Recognition in a Complex Maritime Transportation Environment" Journal of Marine Science and Engineering 10, no. 12: 1903. https://doi.org/10.3390/jmse10121903
APA StyleYu, M., Han, S., Wang, T., & Wang, H. (2022). An Approach to Accurate Ship Image Recognition in a Complex Maritime Transportation Environment. Journal of Marine Science and Engineering, 10(12), 1903. https://doi.org/10.3390/jmse10121903