This study proposes an approaching method of identifying sea fog by using Geostationary Ocean Color Imager (GOCI) data through applying a Convolution Neural Network Transfer Learning (CNN-TL) model. In this study, VGG19 and ResNet50, pre-trained CNN models, are used for their high identification performance. The training and testing datasets were extracted from GOCI images for the area of coastal regions of the Korean Peninsula for six days in March 2015. With varying band combinations and changing whether Transfer Learning (TL) is applied, identification experiments were executed. TL enhanced the performance of the two models. Training data of CNN-TL showed up to 96.3% accuracy in matching, both with VGG19 and ResNet50, identically. Thus, it is revealed that CNN-TL is effective for the detection of sea fog from GOCI imagery.
Ship type classification of synthetic aperture radar imagery with convolution neural network (CNN) has been faced with insufficient labeled datasets, unoptimized and noised polarization images that can deteriorate a classification performance. Meanwhile, numerous labeled text information for ships, such as length and breadth, can be easily obtained from various sources and can be utilized in a classification with k-nearest neighbor (KNN). This study proposes a method to improve the efficiency of ship type classification from Sentinel-1 dual-polarization data with 10 m pixel spacing using both CNN and KNN models. In the first stage, Sentinel-1 intensity images centered on ship positions were used in a rectangular shape to apply an image processing procedure such as head-up, padding and image augmentation. The process increased the accuracy by 33.0% and 31.7% for VH (vertical transmit and horizontal receive) and VV (vertical transmit and vertical receive) polarization compared to the CNN-based classification with original ship images, respectively. In the second step, a combined method of CNN and KNN was compared with a CNN-alone case. The f1-score of CNN alone was up to 85.0%, whereas the combination method showed up to 94.3%, which was a 9.3% increase. In the future, more details on an optimization method will be investigated through field experiments of ship classification.
30 October 2018 in Journal of the Korean Society of Marine Environment & Safety
공공 연안 관측자료를 이용한 다양한 연안환경 연구가 수행됨에 따라 해당 자료의 활용성 제고를 위한 논의가 대두되고 있으며, 이를 위해서는 관측정점에 대한 정성적 평가보다 구체적인 관측정점에서 계측된 물리량에 대한 정량적 평가를 제시할 필요가 있다. 이 연구에서는 담수의 영향이 미치는 영역을 정량적으로 제시하기 위해 1997-2021년 해양환경측정망자료 내 연안 염분 관측자료를 분석했다. 염분의 평균 및 평균 경사보다는 해역의 염분 확산 특성을 고려한 표준편차의 공간변화가 담수 확산 범위 추정에 보다 적절한 것으로 파악되었으며, 관측자료로부터 통계적 담수 영향 범위는 염분 표준편차 경사를 적용해 Δσ/Δs ≥ 0.14(PSU/km)를 제안한다. 제안된 방법을 통해 추정된 담수 확산 영역은 우리나라 주요 하천 인근 해역으로 나타나는 반면, 현재 관측정점의 공간적 배치는 일부 해역에서 담수 영향 범위를 충분히 대표하지 못하는 것으로 판단된다. 미관측 영역에서 높은 분산 추정오차는 제한요소가 되므로, 향후 추가적인 정점 확장을 통해 해당 오차는 점진적으로 감소할 수 있다. 제안된 방법은 담수 확산을 비롯한 과학적인 연안 해역 획정에 기여할 것으로 판단된다.
31 December 2025 in Korean Journal of Remote Sensing