TY - JOUR
T1 - IMPROVING THE ACCURACY OF AN OIL SPILL DETECTION AND CLASSIFICATION MODEL WITH FAKE DATASETS
AU - Bui, N. A.
AU - Oh, Y. G.
AU - Lee, I. P.
N1 - Publisher Copyright:
© Author(s) 2023. CC BY 4.0 License.
PY - 2023/12/13
Y1 - 2023/12/13
N2 - Deep learning is a popular tool for object detection, including oil spill detection. However, acquiring sufficient data for training deep learning models can be challenging, particularly for offshore oil spill accidents. Data augmentation is an effective solution to this issue. This study proposes a data augmentation method using a conditional-GAN model, specifically Pix2Pix, to generate dummy datasets of oil spills. These datasets were used to train the DaNet model for oil detection and classification. Results show that using the dummy datasets improves the mIoU and f1-score to 2.56% and 1.69%, respectively, and enhances the accuracy of classifying of each oil in the model. This approach not only improves the accuracy of the deep learning model but also presents a direction for data enhancement in detection or segmentation tasks for formless objects, such as oil spills, cracks, water seepage, and mildew.
AB - Deep learning is a popular tool for object detection, including oil spill detection. However, acquiring sufficient data for training deep learning models can be challenging, particularly for offshore oil spill accidents. Data augmentation is an effective solution to this issue. This study proposes a data augmentation method using a conditional-GAN model, specifically Pix2Pix, to generate dummy datasets of oil spills. These datasets were used to train the DaNet model for oil detection and classification. Results show that using the dummy datasets improves the mIoU and f1-score to 2.56% and 1.69%, respectively, and enhances the accuracy of classifying of each oil in the model. This approach not only improves the accuracy of the deep learning model but also presents a direction for data enhancement in detection or segmentation tasks for formless objects, such as oil spills, cracks, water seepage, and mildew.
KW - Data augmentation
KW - Dual attention mechanism
KW - Generative adversarial networks-GANs
KW - Oil spill detection
KW - Pix2Pix
UR - http://www.scopus.com/inward/record.url?scp=85182985148&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-X-1-W1-2023-51-2023
DO - 10.5194/isprs-annals-X-1-W1-2023-51-2023
M3 - Conference article
AN - SCOPUS:85182985148
SN - 2194-9042
VL - 10
SP - 51
EP - 56
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
IS - 1-W1-2023
T2 - 5th Geospatial Week 2023, GSW 2023
Y2 - 2 September 2023 through 7 September 2023
ER -