School of Geoscience and Info-Physics, Central South University, Changsha 410083, China.
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China.
Sensors (Basel). 2020 Sep 27;20(19):5538. doi: 10.3390/s20195538.
Detecting changes between the existing building basemaps and newly acquired high spatial resolution remotely sensed (HRS) images is a time-consuming task. This is mainly because of the data labeling and poor performance of hand-crafted features. In this paper, for efficient feature extraction, we propose a fully convolutional feature extractor that is reconstructed from the deep convolutional neural network (DCNN) and pre-trained on the Pascal VOC dataset. Our proposed method extract pixel-wise features, and choose salient features based on a random forest (RF) algorithm using the existing basemaps. A data cleaning method through cross-validation and label-uncertainty estimation is also proposed to select potential correct labels and use them for training an RF classifier to extract the building from new HRS images. The pixel-wise initial classification results are refined based on a superpixel-based graph cuts algorithm and compared to the existing building basemaps to obtain the change map. Experiments with two simulated and three real datasets confirm the effectiveness of our proposed method and indicate high accuracy and low false alarm rate.
检测现有建筑物底图与新获取的高空间分辨率遥感 (HRS) 图像之间的变化是一项耗时的任务。这主要是由于数据标注和手工制作特征的性能较差。在本文中，为了进行有效的特征提取，我们提出了一种完全卷积特征提取器，它是从深度卷积神经网络 (DCNN) 重建而来，并在 Pascal VOC 数据集上进行了预训练。我们提出的方法提取像素级特征，并使用现有的底图基于随机森林 (RF) 算法选择显著特征。还提出了一种通过交叉验证和标签不确定性估计的数据清理方法，以选择潜在的正确标签，并使用它们来训练 RF 分类器，以从新的 HRS 图像中提取建筑物。基于基于超像素的图割算法对像素级初始分类结果进行细化，并与现有建筑物底图进行比较，以获得变化图。使用两个模拟数据集和三个真实数据集的实验证实了我们方法的有效性，并表明具有较高的准确性和较低的误报率。
