Multiscale feature fusion network for automatic port segmentation from remote sensing images
Multiscale feature fusion network for automatic port segmentation from remote sensing images
复制标题
DOI：
10.1117/1.jrs.16.044506
复制
发表时间：
2022-10
影响因子：
1.7
通讯作者：
Haoran Ju;Fukun Bi;M. Bian;Yinni Shi
中科院分区：
文献类型：
--
作者：
Haoran Ju;Fukun Bi;M. Bian;Yinni Shi
抽象的。近年来，遥感图像观测技术发展迅速。从遥感影像中提取海岸线已成为港口面积测量不可缺少的手段。港口遥感图像分割是海岸线提取和测量的重要方法。使用的遥感图像是全色遥感图像。由于遥感图像场景复杂，不同尺度下的特征信息差异较大，传统的分割方法无法进行有效的提取，难以准确分割遥感图像中的海岸线。提出了一种多尺度特征融合网络用于遥感图像港口自动分割。首先，为了减少传统卷积神经网络中的冗余参数和复杂操作问题，我们提出使用MobileNetv 2作为特征提取的基础网络来实现轻量级模型。然后针对遥感图像在不同尺度下的特征差异，提出了一种全网络的卷积方法--无向卷积，并结合联合收割机的多尺度特征融合方法对遥感图像进行特征提取，提高了特征提取能力。为了减少停靠在港口的船舶容易被误认为港区而造成误分割的问题，提出了一种消除港区的方法来减少干扰。最后，对大量Google港口遥感数据的综合评价表明，与现有方法相比，该方法具有轻量级、精度高的特点。
Abstract. In recent years, remote sensing image observation technology has developed rapidly. Extracting coastlines from remote sensing images has become an indispensable means of port area measurement. Port segmentation from remote sensing images is an important method of coastline extraction and measurement. The remote sensing images used are panchromatic remote sensing images. Due to complex remote sensing image scenes and the large difference in feature information at different scales, traditional segmentation methods cannot perform effective extraction, and it is difficult to accurately segment the coastline in remote sensing images. We propose a multiscale feature fusion network for automatic port segmentation from remote sensing images. First, to reduce the redundant parameters and complex operation problems in traditional convolutional neural networks, we propose using MobileNetv2 as the base network for feature extraction to achieve a lightweight model. Then aiming at the feature differences of remote sensing images at different scales, we present atrous convolution as a convolution method for the entire network and combine a multiscale feature fusion method to extract the features of remote sensing images and improve the feature extraction ability. To reduce the problem of ships calling at the port being easily mistaken for port area and causing false segmentation, we propose a method of eliminating the ship area to reduce the interference. Finally, the comprehensive evaluation of a large number of Google port remote sensing data shows that compared with existing methods, the proposed method has the characteristics of being lightweight and having high precision.