Oil Spill Drone: A Dataset of Drone-Captured, Segmented RGB Images for Oil Spill Detection in Port Environments (2402.18202v1)
Abstract: The high incidence of oil spills in port areas poses a serious threat to the environment, prompting the need for efficient detection mechanisms. Utilizing automated drones for this purpose can significantly improve the speed and accuracy of oil spill detection. Such advancements not only expedite cleanup operations, reducing environmental harm but also enhance polluter accountability, potentially deterring future incidents. Currently, there's a scarcity of datasets employing RGB images for oil spill detection in maritime settings. This paper presents a unique, annotated dataset aimed at addressing this gap, leveraging a neural network for analysis on both desktop and edge computing platforms. The dataset, captured via drone, comprises 1268 images categorized into oil, water, and other, with a convolutional neural network trained using an Unet model architecture achieving an F1 score of 0.71 for oil detection. This underscores the dataset's practicality for real-world applications, offering crucial resources for environmental conservation in port environments.
- Environmental effects of the deepwater horizon oil spill: A review. marine pollution bulletin environmental effects of the deepwater horizon oil spill environmental effects of the deepwater horizon oil spill: A review. \JournalTitleMarine Pollution Bulletin 110, 28–51, 10.1016/j.marpolbul.2016.06.027 (2016).
- Readman, J. W. et al. Recovery of the coastal marine environment in the Gulf following the 1991 war-related oil spills. \JournalTitleMarine Pollution Bulletin 32, 493–498, 10.1016/0025-326x(95)00227-e (1996).
- Itpof. Oil Tanker Spill Statistics 2019. Tech. Rep., International Tanker Owners Pollution Federation (2019).
- Artificial Neural Network Modeling for the Management of Oil Slick Transport in the Marine Environments. \JournalTitlePollution 6, 399–415, 10.22059/poll.2020.289549.684 (2020).
- Topouzelis, K. N. Oil spill detection by sar images: Dark formation detection, feature extraction and classification algorithms. \JournalTitleSensors 8, 6642–6659 (2008).
- Oil spill detection using marine sar images. \JournalTitleInternational Journal of Remote Sensing 21, 3561–3566 (2000).
- Hyperspectral image analysis for oil spill detection. In Summaries of NASA/JPL Airborne Earth Science Workshop, Pasadena, CA, 5–9 (2001).
- Khanna, S. et al. Comparing the potential of multispectral and hyperspectral data for monitoring oil spill impact. \JournalTitleSensors 18, 558 (2018).
- Koirala, B. et al. Study on the potential of oil spill monitoring in a port environment using optical reflectance. \JournalTitleRemote Sensing 15, 10.3390/rs15204950 (2023).
- Oil spill detection using machine learning and infrared images. \JournalTitleRemote sensing 12, 4090 (2020).
- Video processing from electro-optical sensors for object detection and tracking in a maritime environment: A survey. \JournalTitleIEEE Transactions on Intelligent Transportation Systems 18, 1993–2016, 10.1109/TITS.2016.2634580 (2017).
- Seaships: A large-scale precisely annotated dataset for ship detection. \JournalTitleIEEE Transactions on Multimedia 20, 2593–2604, 10.1109/TMM.2018.2865686 (2018).
- Character region awareness for text detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 9365–9374 (2019).
- Suvorov, R. et al. Resolution-robust large mask inpainting with fourier convolutions. \JournalTitlearXiv preprint arXiv:2109.07161 (2021).
- Annotated rgb of oil spills in a port environment. Zenodo https://doi.org/10.5281/zenodo.10555314 (2024).
- Semantic object classes in video: A high-definition ground truth database. \JournalTitlePattern Recognition Letters 30, 88–97 (2009).
- Lin, T.-Y. et al. Microsoft coco: Common objects in context (2015). 1405.0312.
- Deng, J. et al. ImageNet: A Large-Scale Hierarchical Image Database. In Cvpr09 (2009).
- U-net: Convolutional networks for biomedical image segmentation (2015). 1505.04597.
- Eff-unet: A novel architecture for semantic segmentation in unstructured environment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 358–359 (2020).
- Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, 6105–6114 (PMLR, 2019).