Automatic Changes Detection between Outdated Building Maps and New VHR Images Based on Pre-Trained Fully Convolutional Feature Maps

Yunsheng Zhang,Haifeng Li,Siyang Chen,Ling Zhao,Yaochen Zhu,Jian Peng

doi:10.3390/s20195538

Yunsheng Zhang, Haifeng Li + Show 4 more

Open Access

https://doi.org/10.3390/s20195538

Copy DOI

Abstract

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.

Highlights

Developing countries have witnessed a rapid expansion of urban areas during the last decades.With the fast urbanization, updating buildings geo-database plays an important role in urban planning, as it provides valuable information regarding, e.g., land use/cover monitoring [1], evaluation of agricultural lands decline [2], disaster assessment [3], civil BIM updating [4]
The contribution of our work are the following: (1) We present a novel framework with the combination of pixel-wise and object-based analysis for image-map change detection based on data cleaning method; (2) fully convolutional network (FCN) pre-trained on the PASCAL VOC dataset for semantic segmentation is used to reconstruct the proposed fully convolutional feature extractors to extract dense features of high spatial resolution remotely sensed (HRS) images; and (3) outdated noise label is used to guide the feature selection for eliminating the redundancy of the features
The corresponding newly acquired HRS images are downloaded from Google Earth

Summary

Introduction

With the fast urbanization, updating buildings geo-database plays an important role in urban planning, as it provides valuable information regarding, e.g., land use/cover monitoring [1], evaluation of agricultural lands decline [2], disaster assessment [3], civil BIM updating [4]. Such information enables the government to adopt suitable and sustainable development strategies. Automatic building geo-database updating relies on identifying the areas, where changes occurred. Change identification is mainly a labor-intensive work, especially in urban environments, due to its complexity.

Methods

Results

Conclusion