A Building Shape Vectorization Hierarchy From VHR Remote Sensing Imagery Combined DCNNs-Based Edge Detection and PCA-Based Corner Extraction
Open Access
- 22 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 750-761
Abstract
The automatic vectorization of building shape from very high resolution (VHR) remote sensing imagery is fundamental in many fields such as urban management and geodatabase updating. Recently, deep convolutional neural networks (DCNNs) have been successfully used for building edge detection but the results are raster images rather than vectorized maps, and do not meet the requirements of many applications. Although there are some algorithms for converting raster images into vector maps, such vector maps often have too many vector points and irregular shapes. This study proposed a building shape vectorization hierarchy, which combined DCNNs-based building edge detection and a corner extraction algorithm based on principal component analysis (PCA) for rapidly extracting building corners from the building edges. Experiments on the Jiangbei New Area Buildings and Massachusetts Buildings datasets showed that compared with the state-of-the-art corner detectors, the building vector corners extracted using our proposed algorithm had fewer breakpoints and isolated points, and our building vector boundaries were more complete and regular. In addition, the building shapes extracted using our hierarchy were 7.94% higher than the non-maximum suppression (NMS) method in terms of relaxed overall accuracy (OA) on the Massachusetts dataset. Overall, our proposed hierarchy is effective for building shape vectorization.Keywords
Funding Information
- National Natural Science Foundation of China (41801327)
- Postgraduate Research and Practice Innovation Program of Jiangsu Province (KYCX20_2365)
- Jiangsu Province Land and Resources Science and Technology Plan Project (2021046)
- Key Laboratory of Land Satellite Remote Sensing Application
- Ministry of Natural Resources of the People's Republic of China (KLSMNR-K202206)
This publication has 30 references indexed in Scilit:
- Automatic Detection of Low-Rise Gable-Roof Building from Single Submeter SAR Images Based on Local Multilevel SegmentationRemote Sensing, 2017
- Holistically-Nested Edge Detection2015
- Vectorization of line drawing image based on junction analysisScience China Information Sciences, 2015
- Faster and Better: A Machine Learning Approach to Corner DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Data fusion of high-resolution satellite imagery and LiDAR data for automatic building extractionISPRS Journal of Photogrammetry and Remote Sensing, 2007
- Raster-to-vector conversion by line fitting based on contours and skeletons2002
- Robust image corner detection through curvature scale spaceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- SUSAN—A New Approach to Low Level Image ProcessingInternational Journal of Computer Vision, 1997
- A robust parallel thinning algorithm for binary imagesPattern Recognition, 1994
- A Combined Corner and Edge Detector1988