Fine-Grained Tidal Flat Waterbody Extraction Method (FYOLOv3) for High-Resolution Remote Sensing Images

Abstract

The tidal flat is long and narrow area along rivers and coasts with high sediment content, so there is little feature difference between the waterbody and the background, and the boundary of the waterbody is blurry. The existing waterbody extraction methods are mostly used for the extraction of large water bodies like rivers and lakes, whereas less attention has been paid to tidal flat waterbody extraction. Extracting tidal flat waterbody accurately from high-resolution remote sensing imagery is a great challenge. In order to solve the low accuracy problem of tidal flat waterbody extraction, we propose a fine-grained tidal flat waterbody extraction method, named FYOLOv3, which can extract tidal flat water with high accuracy. The FYOLOv3 mainly includes three parts: an improved object detection network based on YOLOv3 (Seattle, WA, USA), a fully convolutional network (FCN) without pooling layers, and a similarity algorithm for water extraction. The improved object detection network uses 13 convolutional layers instead of Darknet-53 as the model backbone network, which guarantees the water detection accuracy while reducing the time cost and alleviating the overfitting phenomenon; secondly, the FCN without pooling layers is proposed to obtain the accurate pixel value of the tidal flat waterbody by learning the semantic information; finally, a similarity algorithm for water extraction is proposed to distinguish the waterbody from non-water pixel by pixel to improve the extraction accuracy of tidal flat water bodies. Compared to the other convolutional neural network (CNN) models, the experiments show that our method has higher accuracy on the waterbody extraction of tidal flats from remote sensing images, and the IoU of our method is 2.43% higher than YOLOv3 and 3.7% higher than U-Net (Freiburg, Germany).

Assessment of Riverbank Erosion Hotspots along the Mekong River in Cambodia Using Remote Sensing and Hazard Exposure Mapping

“…Moreover, they can effectively detect water bodies at low computational costs. In recent years, many advanced techniques have been proposed for detecting water bodies using machine learning/deep learning [42][43][44][45][46][47][48]. These techniques were developed to improve the accuracy of water body detection, especially small water bodies in complex terrains, and to overcome the limitations of spectral resolution in high-resolution images (e.g., Ikonos and Quickbird).…”

“…According to Yang et al [49], convolutional neural network-based models are the most frequently used in water body detection. Machine learning methods were found to outperform the water index-based method in specific areas and terrains [42][43][44][45][46]. However, when water detection was performed in the same location at different image acquisition times using the same machine learning algorithm, accuracy was significantly reduced [50], requiring the model to be retrained, which was resource intensive.…”

Towards Synoptic Water Monitoring Systems: A Review of AI Methods for Automating Water Body Detection and Water Quality Monitoring Using Remote Sensing

“…However, their network cannot distinguish water bodies from farms and barren areas. In addition, the CNN-based model name FYOLOv3, proposed in [ 51 ], is able to detect tidal flats at different resolutions. However, it does depend on a manually selected similarity threshold that introduces some subjectivity.…”

“…Very few focus on tidal flat extraction, where sediment levels are high and the boundary of the water body itself is blurry. A CNN model called FYOLOv3 was proposed in [ 51 ], where the authors compared their model to NDWI, an SVM, a maximum likelihood classifier, U-Net, and YOLOv3. FYOLOv3 performed the best and is able to detect tidal flats at different resolutions; however, it depends on a manually-selected similarity threshold during the training process, which is a source of subjectivity.…”

Editorial for the Special Issue “Advances in Object and Activity Detection in Remote Sensing Imagery”

“…Advances in data collection and accessibility, such as unmanned aerial vehicle (UAV) technology, the availability of satellite imagery, and the increasing performance of deep learning models, have had significant impacts on solving various remote sensing problems and proposing new applications ranging from vegetation and wildlife monitoring to crowd monitoring. This Special Issue contains seven high-quality papers [1][2][3][4][5][6][7] approaching problems relating to object detection, semantic segmentation, and multi-modal data alignment. In terms of the methods utilized, it is not surprising that six of the seven papers on this issue involve the application of deep learning.…”