An Optimized Edge-Focused Siamese Network for Monitoring New Illegal Buildings Using Satellite Images

Illegal construction is a common problem often encountered by cities with rapid development, which is hard to deal with for multiple reasons. Although these illegal buildings are primarily defined by laws and regulations, they still have physical characteristics in common that makes them identifiable. In this study, we propose an illegal building monitoring method based on satellite images and deep learning techniques, named illegal building monitoring network (IBMNet), to improve the data collection capacity for monitoring new illegal buildings. IBMNet is an end-to-end pixelwise segmentation network with two flows: the Segment Flow, which includes a Siamese encoder and an attention fusion module (AFM), and the Edge Flow, which uses Gated Convolutional Layers to extract edge information. We implement and evaluate our model in China, a country with fast development and struggling with illegal buildings. In addition to the conventional metrics, we propose a set of specialized metrics to evaluate the model’s ability to discriminate illegal buildings and legal buildings (
${\text {OA}}_{B}$
,
$\text {F1}_{B}$
, and
${\text {IoU}}_{B}$
). The model achieves great results on the illegal building monitoring dataset (IBMD) with an
$F1$
score of 0.7990 and
${\text {IoU}}_{B}$
of 0.7449, showing its great ability in detecting illegal buildings in various scenarios and distinguishing them from legal buildings. Compared to the existing methods based on urban database, IBMNet has a higher time resolution and a larger space coverage, making it more accessible in data and cost-effective for governments. The proposed method is also promising in other cities and countries with similar problems.