Building Corner Detection in Aerial Images with Fully Convolutional Networks
In aerial images, corner points can be detected to describe the structural information of buildings for city modeling, geo-localization, and so on. For this specific vision task, the existing generic corner detectors perform poorly, as they are incapable of distinguishing corner points on buildings...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/8/1915 |
| _version_ | 1828350040946507776 |
|---|---|
| author | Weigang Song Baojiang Zhong Xun Sun |
| author_facet | Weigang Song Baojiang Zhong Xun Sun |
| author_sort | Weigang Song |
| collection | DOAJ |
| description | In aerial images, corner points can be detected to describe the structural information of buildings for city modeling, geo-localization, and so on. For this specific vision task, the existing generic corner detectors perform poorly, as they are incapable of distinguishing corner points on buildings from those on other objects such as trees and shadows. Recently, fully convolutional networks (FCNs) have been developed for semantic image segmentation that are able to recognize a designated kind of object through a training process with a manually labeled dataset. Motivated by this achievement, an FCN-based approach is proposed in the present work to detect building corners in aerial images. First, a DeepLab model comprised of improved FCNs and fully-connected conditional random fields (CRFs) is trained end-to-end for building region segmentation. The segmentation is then further improved by using a morphological opening operation to increase its accuracy. Corner points are finally detected on the contour curves of building regions by using a scale-space detector. Experimental results show that the proposed building corner detection approach achieves an F-measure of 0.83 in the test image set and outperforms a number of state-of-the-art corner detectors by a large margin. |
| first_indexed | 2024-04-14T01:19:36Z |
| format | Article |
| id | doaj.art-579227dfc8414e97a82d4cb27ee1e001 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T01:19:36Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-579227dfc8414e97a82d4cb27ee1e0012022-12-22T02:20:42ZengMDPI AGSensors1424-82202019-04-01198191510.3390/s19081915s19081915Building Corner Detection in Aerial Images with Fully Convolutional NetworksWeigang Song0Baojiang Zhong1Xun Sun2School of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaIn aerial images, corner points can be detected to describe the structural information of buildings for city modeling, geo-localization, and so on. For this specific vision task, the existing generic corner detectors perform poorly, as they are incapable of distinguishing corner points on buildings from those on other objects such as trees and shadows. Recently, fully convolutional networks (FCNs) have been developed for semantic image segmentation that are able to recognize a designated kind of object through a training process with a manually labeled dataset. Motivated by this achievement, an FCN-based approach is proposed in the present work to detect building corners in aerial images. First, a DeepLab model comprised of improved FCNs and fully-connected conditional random fields (CRFs) is trained end-to-end for building region segmentation. The segmentation is then further improved by using a morphological opening operation to increase its accuracy. Corner points are finally detected on the contour curves of building regions by using a scale-space detector. Experimental results show that the proposed building corner detection approach achieves an F-measure of 0.83 in the test image set and outperforms a number of state-of-the-art corner detectors by a large margin.https://www.mdpi.com/1424-8220/19/8/1915buildingcorner detectionconvolutional networkssemantic segmentationaerial imageconditional random fields |
| spellingShingle | Weigang Song Baojiang Zhong Xun Sun Building Corner Detection in Aerial Images with Fully Convolutional Networks Sensors building corner detection convolutional networks semantic segmentation aerial image conditional random fields |
| title | Building Corner Detection in Aerial Images with Fully Convolutional Networks |
| title_full | Building Corner Detection in Aerial Images with Fully Convolutional Networks |
| title_fullStr | Building Corner Detection in Aerial Images with Fully Convolutional Networks |
| title_full_unstemmed | Building Corner Detection in Aerial Images with Fully Convolutional Networks |
| title_short | Building Corner Detection in Aerial Images with Fully Convolutional Networks |
| title_sort | building corner detection in aerial images with fully convolutional networks |
| topic | building corner detection convolutional networks semantic segmentation aerial image conditional random fields |
| url | https://www.mdpi.com/1424-8220/19/8/1915 |
| work_keys_str_mv | AT weigangsong buildingcornerdetectioninaerialimageswithfullyconvolutionalnetworks AT baojiangzhong buildingcornerdetectioninaerialimageswithfullyconvolutionalnetworks AT xunsun buildingcornerdetectioninaerialimageswithfullyconvolutionalnetworks |