Abstract
Aerial images are widely used for building detection. However, the performance of building detection methods based on aerial images alone is typically poorer than that of building detection methods using both LiDAR and image data. To overcome these limitations, we present a framework for detecting and regularizing the boundary of individual buildings using a feature-level-fusion strategy based on features from dense image matching (DIM) point clouds, orthophoto and original aerial images. The proposed framework is divided into three stages. In the first stage, the features from the original aerial image and DIM points are fused to detect buildings and obtain the so-called blob of an individual building. Then, a feature-level fusion strategy is applied to match the straight-line segments from original aerial images so that the matched straight-line segment can be used in the later stage. Finally, a new footprint generation algorithm is proposed to generate the building footprint by combining the matched straight-line segments and the boundary of the blob of the individual building. The performance of our framework is evaluated on a vertical aerial image dataset (Vaihingen) and two oblique aerial image datasets (Potsdam and Lunen). The experimental results reveal 89% to 96% per-area completeness with accuracy above almost 93%. Relative to six existing methods, our proposed method not only is more robust but also can obtain a similar performance to the methods based on LiDAR and images.
Highlights
Buildings, as key urban objects, play an important role in city planning [1,2], disaster management [3,4,5], emergency response [6], and many other application fields [7]
Building detection consists of two steps: Dense Image Matching (DIM) point clouds filtering and object-oriented classification of original aerial images
This paper focuses on both building detection and footprint regularization using solely aerial images
Summary
As key urban objects, play an important role in city planning [1,2], disaster management [3,4,5], emergency response [6], and many other application fields [7]. Single-source-data-based methods, where the data include Airborne Laser Scanning (ALS) point clouds [9,10], ALS-based Digital Surface Model (DSM) grids [11,12], and images [13,14]. Many researchers have reported that multisource-data-based methods perform better than single-source-data-based methods [18,19,20]. With the fast development of multi-camera aerial platforms and dense matching techniques, reliable and accurate Dense Image Matching (DIM) point clouds can be generated from the overlapping aerial images [21] Under this condition, instead of using multisource remote sensing data, the approach of solely employing aerial images to extract buildings in complex urban scenes is feasible. We first discuss the related works in building detection paradigm only using aerial images and cover the relevant literature on boundary regularization in the following work
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
