Litcius/Paper detail

Capsule Feature Pyramid Network for Building Footprint Extraction From High-Resolution Aerial Imagery

Yongtao Yu, Yongfeng Ren, Haiyan Guan, Dilong Li, Changhui Yu, Shenghua Jin, Lanfang Wang

2020IEEE Geoscience and Remote Sensing Letters35 citationsDOI

Abstract

Building footprint extraction plays an important role in a wide range of applications. However, due to size and shape diversities, occlusions, and complex scenarios, it is still challenging to accurately extract building footprints from aerial images. This letter proposes a capsule feature pyramid network (CapFPN) for building footprint extraction from aerial images. Taking advantage of the properties of capsules and fusing different levels of capsule features, the CapFPN can extract high-resolution, intrinsic, and semantically strong features, which perform effectively in improving the pixel-wise building footprint extraction accuracy. With the use of signed distance maps as ground truths, the CapFPN can extract solid building regions free of tiny holes. Quantitative evaluations on an aerial image data set show that a precision, recall, intersection-over-union (IoU), and F-score of 0.928, 0.914, 0.853, and 0.921, respectively, are obtained. Comparative studies with six existing methods confirm the superior performance of the CapFPN in accurately extracting building footprints.

Topics & Concepts

FootprintArtificial intelligenceComputer sciencePyramid (geometry)Feature extractionAerial imageAerial imageryComputer visionPattern recognition (psychology)Intersection (aeronautics)PixelImage resolutionPrecision and recallFeature (linguistics)Remote sensingImage (mathematics)GeographyMathematicsCartographyPhilosophyGeometryArchaeologyLinguisticsAutomated Road and Building ExtractionRemote Sensing and LiDAR ApplicationsVideo Surveillance and Tracking Methods
Capsule Feature Pyramid Network for Building Footprint Extraction From High-Resolution Aerial Imagery | Litcius