Abstract
Due to the increasing ship trafficking, illegal fishing, cargo crimes, drug crimes, identifying people in the sea, shipwrecked etc., it is essential to detect ships to monitor and control maritime crime. Researchers have been working constantly and facing challenges to automatically detect ships, mainly in remote sensing, which has shown a great impact in providing safety, detecting illegal trade, pollution, and oil slick monitoring. In this paper, 192,555 satellite images of ships have been used to train the deep learning models such as customized CNN, ResNet152V2, InceptionResNetV2, MobileNetV2, NasNetLarge, DenseNet201, and EfficientNetB7. The dataset has been first pre-processed to remove any noisy signals before being graphically represented using exploratory data analysis to study the pixel intensities of data. Later, feature extraction techniques such as image masking, image augmentation, and contour features are applied to create bounding boxes corresponding to the detected ship’s localizing coordinates. The models are further evaluated using the ship detected and ship not detected classes. It has been discovered that customized CNN achieved the highest precision by 96.16 as well as 95.64 and F1 score value by 99.89 and 95.99 in terms of both the classes, respectively. In contrast, DenseNet201 had the highest recall 95.46, and 93.45, for the ship, detected and not detected classes, respectively).
Similar content being viewed by others
Data availability
Not applicable.
References
Nie X, Duan M, Ding H, Hu B, Wong EK (2020) Attention mask R-CNN for ship detection and segmentation from remote sensing images. IEEE Access 8:9325–9334
Greidanus H, Alvarez M, Santamaria C, Thoorens FX, Kourti N, Argentieri P (2017) The SUMO ship detector algorithm for satellite radar images. Remote Sens 9(3):246
Wu F, Zhou Z, Wang B, Ma J (2018) Inshore ship detection based on convolutional neural network in optical satellite images. IEEE J Sel Top Appl Earth Obs Remote Sens 11(11):4005–4015
Clarizia MP, Braca P, Ruf CS, Willett P (2015) Target detection using GPS signals of opportunity. In: 2015 18th International Conference on Information Fusion (Fusion). IEEE, pp 1429–1436
Patel K, Bhatt C, Mazzeo PL (2022) Deep learning-based automatic detection of ships: an experimental study using Satellite images. J Imaging 8(7):182
Fan W, Zhou F, Bai X, Tao M, Tian T (2019) Ship detection using deep convolutional neural networks for PolSAR images. Remote Sens 11:2862. https://doi.org/10.3390/rs11232862
Wang N, Li B, Xu Q, Wang Y (2018) Automatic ship detection in optical remote sensing images based on anomaly detection and SPP-PCANet. Remote Sens 11(1):47
Yang X, Sun H, Fu K, Yang J, Sun X, Yan M, Guo Z (2018) Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sens 10(1):132
Zhou Y, Lv J, Wang Y, Liu C, Zhong S, Tan G, Sun J (2022) LEDet: localization estimation detector with data augmentation for ship detection based on unmanned surface vehicle. Int J Intell Robot Appl 6:216–230. https://doi.org/10.1007/s41315-022-00238-y
Liu Y, Zhang MH, Xu P, Guo ZW (2017) SAR ship detection using sea-land segmentation-based convolutional neural network. In: 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP). IEEE, pp 1–4
Niu H, Reeves E, Gerstoft P (2017) Source localization in an ocean waveguide using supervised machine learning. J Acoust Soc Am 142(3):1176–1188
Niu H, Ozanich E, Gerstoft P (2017) Ship localization in Santa Barbara Channel using machine learning classifiers. J Acoust Soc Am 142(5):EL455–EL460
Wang D, Zhang L, Bao C, Ma S, Wang Y (2019) Passive ship localization in a shallow water using pre-trained deep learning networks. Universitätsbibliothek der RWTH Aachen, pp 1956–1962
Stofa MM, Zulkifley MA, Zaki SZM (2020), July A deep learning approach to ship detection using satellite imagery. In: IOP Conference Series: Earth and Environmental Science, vol 540, no 1. IOP Publishing, p 012049
Hashi AO, Hussein IH, Rodriguez OER, Abdirahman AA, Elmi MA (2022) Ship detection approach using machine learning algorithms. In: Saeed F, Mohammed F, Ghaleb F (eds) Advances on Intelligent Informatics and Computing. IRICT 2021. vol 127. Springer, Cham. https://doi.org/10.1007/978-3-030-98741-1_2
Lou X, Liu Y, Xiong Z, Wang H (2022) Generative knowledge transfer for ship detection in SAR images. Comput Electr Eng 101:108041
Sharma R, Sharma H, Meena T, Khandnor P, Bansal P, Sharma P (2022) Performance Evaluation of Deep Learning Models for Ship Detection. In: International Conference on Computer Vision and Image Processing. Springer, Cham, pp 273–287
Mehran A, Tehsin S, Hamza M (2023) An effective deep learning model for ship detection from satellite images. Spat Inform Res 31(1):61–72
Hashi AO, Hussein IH, Rodriguez OER, Abdirahman AA, Elmi MA (2022) Ship detection approach using machine learning algorithms. In: International Conference of Reliable Information and Communication Technology. Springer, Cham, pp 16–25
Bo LI, Xiaoyang XIE, Xingxing WEI, Wenting TANG (2021) Ship detection and classification from optical remote sensing images: a survey. Chin J Aeronaut 34(3):145–163
Karki S, Kulkarni S (2021) Ship detection and segmentation using UNET. In: 2021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT). IEEE, pp 1–7
Kathiravan M, Reddy NA, Prakash V, Kumar BS, Malarvel M, Sambath M (2022) Ship detection from satellite images using deep learning. 7th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India 1044–1050. https://doi.org/10.1109/ICCES54183.2022.9835766
Zhang R, Yao J, Zhang K, Feng C, Zhang J (2016) S-CNN-Based ship detection from high-resolution remote sensing images. Int Arch Photogramm Remote Sens Spat Inf Sci XLI-B7, 423–430. https://doi.org/10.5194/isprs-archives-XLI-B7-423-2016
Wang HL, Zhu M, Lin CB, Chen DB (2017) Ship detection in optical remote sensing image based on visual saliency and AdaBoost classifier. Optoelectron Lett 13(2):151–155
Smith B, Chester S, Coady Y (2020), December Ship detection in satellite optical imagery. In: 2020 3rd Artificial Intelligence and Cloud Computing Conference, pp 11–18
Dolapci B, Özcan C (2021) Automatic ship detection and classification using machine learning from remote sensing images on Apache Spark. J Intell Syst: Theory Appl 4(2):94–102
Štepec D, Martinčič T, Skočaj D (2019) Automated system for ship detection from medium resolution satellite optical imagery. In: Oceans 2019 MTS/IEEE Seattle. IEEE, pp 1–10
Xie X, Li B, Wei X (2020) Ship detection in multispectral satellite images under complex environment. Remote Sens 12(5):792
Kumar Y, Kaur K, Singh G (2020) Machine learning aspects and its applications towards different research areas. In: 2020 International conference on computation, automation and knowledge management (ICCAKM). IEEE, pp 150–156
Gurucharan M (2020) Basic cnn architecture: explaining 5 layers of convolutional neural network. https://www.upgrad.com/blog/basic-cnn-architecture. Accessed 13 Nov 2021
Vidhanaarachchi SP, Akalanka PKGC, Gunasekara RPTI, Rajapaksha HMUD, Aratchige NS, Lunugalage D, Wijekoon JL (2021) Deep learning-based surveillance system for coconut disease and pest infestation identification. In: TENCON 2021–2021 IEEE Region 10 Conference (TENCON). IEEE, pp 405–410
Pires C, Bernardino A, Damas BD (2020) Ship segmentation in areal images for maritime surveillance. 26th Portuguese Conference on Pattern Recognition. Évora 2020
Tsang SH (2019) Review: Mobilenetv2—light weight model (image classification). Towards Data Science, Svibanj
Tsang SH (2020) Review:Nasnet-neural architecture search network (image classification) 82–93. https://doi.org/10.48550/arXiv.1712.00559
Bui DT, Tran TD, Nguyen TT, Tran QL, Nguyen DV (2018) Aerial image semantic segmentation using neural search network architecture. In: International Conference on Multi-disciplinary Trends in Artificial Intelligence. Springer, Cham, pp 113–124
Sun H, Xu Y, Kuang G, Chen J (2021) Adversarial robustness evaluation of deep convolutional neural network based SAR ATR algorithm. In: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, pp 5263–5266
Agarwal V (2020) Complete architectural details of all efficient net models. International Conference on Machine Learning 2020. https://doi.org/10.48550/arXiv.2104.00298
Parmar R (2018) Common loss functions in machine learning. https://towardsdatascience.com/common-loss-functions-in-machine-learning-46af0ffc4d23(visited on Nov. 2, 2020)(cit. on p.13)
Tharwat A (2020) Classification assessment methods. Appl Comput Inform 17(1):168–192. https://doi.org/10.1016/j.aci.2018.08.003
Koul A, Koul A (2020) Semantic segmentation and contextual information based image scene interpretation: a review. In: 2020 3rd International Conference on Information and Computer Technologies (ICICT). IEEE, pp 148–153
LT Z (2021) Essential things you need to know about F1-Score. https://towardsdatascience.com/essential-things-you-need-to-know-about-f1-score-dbd973bf1a3. Accessed 23 Dec 2021
Author information
Authors and Affiliations
Contributions
The first author has drafted the article, whereas the second author has drawn the figures and result tables. The third author has performed the training and validation for Ship Localization and Detection using deep learning.
Corresponding author
Ethics declarations
Ethical approval
All techniques performed on human subjects in studies conformed to the ethical norms of the institutional and/or national research committee as well as the 1964 Helsinki Declaration and its later revisions or other comparable ethical standards.
Consent to publish
All authors involved in the study gave their informed consent.
Competing interests
The authors declare no competing interests.
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chadha, J., Jain, A. & Kumar, Y. Satellite imagery-based Airbus ship localization and detection using deep learning-based approaches. Peer-to-Peer Netw. Appl. 16, 1481–1498 (2023). https://doi.org/10.1007/s12083-023-01493-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12083-023-01493-x