RCSANet: A Full Convolutional Network for Extracting Inland Aquaculture Ponds from High-Spatial-Resolution Images

Abstract

Numerous aquaculture ponds are intensively distributed around inland natural lakes and mixed with cropland, especially in areas with high population density in Asia. Information about the distribution of aquaculture ponds is essential for monitoring the impact of human activities on inland lakes. Accurate and efficient mapping of inland aquaculture ponds using high-spatial-resolution remote-sensing images is a challenging task because aquaculture ponds are mingled with other land cover types. Considering that aquaculture ponds have intertwining regular embankments and that these salient features are prominent at different scales, a Row-wise and Column-wise Self-Attention (RCSA) mechanism that adaptively exploits the identical directional dependency among pixels is proposed. Then a fully convolutional network (FCN) combined with the RCSA mechanism (RCSANet) is proposed for large-scale extraction of aquaculture ponds from high-spatial-resolution remote-sensing imagery. In addition, a fusion strategy is implemented using a water index and the RCSANet prediction to further improve extraction quality. Experiments on high-spatial-resolution images using pansharpened multispectral and 2 m panchromatic images show that the proposed methods gain at least 2–4% overall accuracy over other state-of-the-art methods regardless of regions and achieve an overall accuracy of 85% at Lake Hong region and 83% at Lake Liangzi region in aquaculture pond extraction.

The Impact of Multiple Pond Conditions on the Performance of Dike-Pond Extraction

“…Our research contributes a reference for those pond extraction studies that required high classification accuracy. Using high-resolution image data (e.g., Sentinel [30,53] and Worldview [33] satellites) or powerful classification methods (e.g., support vector machines [54] and deep learning [27,55]) are two major ways to capture high accuracy. To further improve the accuracy based on the data and method, the characteristics of the extracted objects can be incorporated into the method design and processing flow of the extraction.…”

HROF: a high-resolution remote sensing dataset for segmentation of offshore farms

“…At present, many researchers have studied the segmentation of aquaculture farms based on RSIs. The proposed methods can be broadly classified into four categories: visual interpretation-based methods [3][4], spectral indices-based methods [5][6], object-based image analysis (OBIA) [7] [8], and methods based on machine learning and deep learning (DL).…”

New deep learning method for efficient extraction of small water from remote sensing images

“…Wang et al applied a full convolutional network (FCN) to extract lake water bodies from Google remote sensing images [18]. Zeng et al proposed a FCN with the RCSA mechanism [19] for the large-scale extraction of aquaculture ponds from high spatial resolution remote sensing images. This study proposed a CNN-based framework to recognize global reservoirs from Landsat 8 images [20].…”