Urban land cover classification of oblique aerial imagery using object-based image analysis method

Jyun Ping Jhan, Ya Ching Hsu, Jiann-Yeou Rau

研究成果: Conference contribution

摘要

By means of airborne multiple camera imaging system, we can acquire vertical and oblique aerial images (VAI and OAI) at the same time. In addition to the reduction of data cost, the OAI can also strengthen the imaging geometry during aerial triangulation and be applied on automatic façade texture mapping. With the development of image matching technique, instead of airborne laser scanning (ALS), we can obtain surface point clouds by dense matching through both VAIs and OAIs. Comparing to the ALS data that were affected by the laser scanning angle, the photogrammetric points can provide much more information on the façade of buildings since the given information from the OAI. Therefore, the use of OAI in building verification and detection, 3D GIS, digital maps or other cyber-city related applications. In this study, we perform image classification using the original oblique aerial imagery and object-based image analysis (OBIA) method. We classify the OAI into six classes namely tree, grass, façade, roof, road and others. In OBIA, we utilize the multiresolution segmentation algorithm to separate the image into objects by merging pixels with similar color and shape homogeneity. Then, the objects are classified by different features such as color, shape, texture and object related features. In our study, we also use the "height map" and "gradient map" generated by back projecting the dense matched point clouds to the OAI to assist for urban object detection. The classification result shows that we can differentiate façade and roof from buildings successfully with the assistant of the height and gradient information. In the meanwhile, the classification result can further offer the semantic information from the OAI to 3D building models.

原文English
主出版物標題34th Asian Conference on Remote Sensing 2013, ACRS 2013
發行者Asian Association on Remote Sensing
頁面750-757
頁數8
1
ISBN(列印)9781629939100
出版狀態Published - 2013
事件34th Asian Conference on Remote Sensing 2013, ACRS 2013 - Bali, Indonesia
持續時間: 2013 十月 202013 十月 24

Other

Other34th Asian Conference on Remote Sensing 2013, ACRS 2013
國家Indonesia
城市Bali
期間13-10-2013-10-24

指紋

Image analysis
Antennas
Scanning
Roofs
Lasers
Textures
Color
Image matching
Image classification
Triangulation
Merging
Imaging systems
Geographic information systems
Pixels
Semantics
Cameras
Imaging techniques
Geometry
Costs
Object detection

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

引用此文

Jhan, J. P., Hsu, Y. C., & Rau, J-Y. (2013). Urban land cover classification of oblique aerial imagery using object-based image analysis method. 於 34th Asian Conference on Remote Sensing 2013, ACRS 2013 (卷 1, 頁 750-757). Asian Association on Remote Sensing.
Jhan, Jyun Ping ; Hsu, Ya Ching ; Rau, Jiann-Yeou. / Urban land cover classification of oblique aerial imagery using object-based image analysis method. 34th Asian Conference on Remote Sensing 2013, ACRS 2013. 卷 1 Asian Association on Remote Sensing, 2013. 頁 750-757
@inproceedings{0514c17407434622bd091d121b895f2f,
title = "Urban land cover classification of oblique aerial imagery using object-based image analysis method",
abstract = "By means of airborne multiple camera imaging system, we can acquire vertical and oblique aerial images (VAI and OAI) at the same time. In addition to the reduction of data cost, the OAI can also strengthen the imaging geometry during aerial triangulation and be applied on automatic fa{\cc}ade texture mapping. With the development of image matching technique, instead of airborne laser scanning (ALS), we can obtain surface point clouds by dense matching through both VAIs and OAIs. Comparing to the ALS data that were affected by the laser scanning angle, the photogrammetric points can provide much more information on the fa{\cc}ade of buildings since the given information from the OAI. Therefore, the use of OAI in building verification and detection, 3D GIS, digital maps or other cyber-city related applications. In this study, we perform image classification using the original oblique aerial imagery and object-based image analysis (OBIA) method. We classify the OAI into six classes namely tree, grass, fa{\cc}ade, roof, road and others. In OBIA, we utilize the multiresolution segmentation algorithm to separate the image into objects by merging pixels with similar color and shape homogeneity. Then, the objects are classified by different features such as color, shape, texture and object related features. In our study, we also use the {"}height map{"} and {"}gradient map{"} generated by back projecting the dense matched point clouds to the OAI to assist for urban object detection. The classification result shows that we can differentiate fa{\cc}ade and roof from buildings successfully with the assistant of the height and gradient information. In the meanwhile, the classification result can further offer the semantic information from the OAI to 3D building models.",
author = "Jhan, {Jyun Ping} and Hsu, {Ya Ching} and Jiann-Yeou Rau",
year = "2013",
language = "English",
isbn = "9781629939100",
volume = "1",
pages = "750--757",
booktitle = "34th Asian Conference on Remote Sensing 2013, ACRS 2013",
publisher = "Asian Association on Remote Sensing",

}

Jhan, JP, Hsu, YC & Rau, J-Y 2013, Urban land cover classification of oblique aerial imagery using object-based image analysis method. 於 34th Asian Conference on Remote Sensing 2013, ACRS 2013. 卷 1, Asian Association on Remote Sensing, 頁 750-757, 34th Asian Conference on Remote Sensing 2013, ACRS 2013, Bali, Indonesia, 13-10-20.

Urban land cover classification of oblique aerial imagery using object-based image analysis method. / Jhan, Jyun Ping; Hsu, Ya Ching; Rau, Jiann-Yeou.

34th Asian Conference on Remote Sensing 2013, ACRS 2013. 卷 1 Asian Association on Remote Sensing, 2013. p. 750-757.

研究成果: Conference contribution

TY - GEN

T1 - Urban land cover classification of oblique aerial imagery using object-based image analysis method

AU - Jhan, Jyun Ping

AU - Hsu, Ya Ching

AU - Rau, Jiann-Yeou

PY - 2013

Y1 - 2013

N2 - By means of airborne multiple camera imaging system, we can acquire vertical and oblique aerial images (VAI and OAI) at the same time. In addition to the reduction of data cost, the OAI can also strengthen the imaging geometry during aerial triangulation and be applied on automatic façade texture mapping. With the development of image matching technique, instead of airborne laser scanning (ALS), we can obtain surface point clouds by dense matching through both VAIs and OAIs. Comparing to the ALS data that were affected by the laser scanning angle, the photogrammetric points can provide much more information on the façade of buildings since the given information from the OAI. Therefore, the use of OAI in building verification and detection, 3D GIS, digital maps or other cyber-city related applications. In this study, we perform image classification using the original oblique aerial imagery and object-based image analysis (OBIA) method. We classify the OAI into six classes namely tree, grass, façade, roof, road and others. In OBIA, we utilize the multiresolution segmentation algorithm to separate the image into objects by merging pixels with similar color and shape homogeneity. Then, the objects are classified by different features such as color, shape, texture and object related features. In our study, we also use the "height map" and "gradient map" generated by back projecting the dense matched point clouds to the OAI to assist for urban object detection. The classification result shows that we can differentiate façade and roof from buildings successfully with the assistant of the height and gradient information. In the meanwhile, the classification result can further offer the semantic information from the OAI to 3D building models.

AB - By means of airborne multiple camera imaging system, we can acquire vertical and oblique aerial images (VAI and OAI) at the same time. In addition to the reduction of data cost, the OAI can also strengthen the imaging geometry during aerial triangulation and be applied on automatic façade texture mapping. With the development of image matching technique, instead of airborne laser scanning (ALS), we can obtain surface point clouds by dense matching through both VAIs and OAIs. Comparing to the ALS data that were affected by the laser scanning angle, the photogrammetric points can provide much more information on the façade of buildings since the given information from the OAI. Therefore, the use of OAI in building verification and detection, 3D GIS, digital maps or other cyber-city related applications. In this study, we perform image classification using the original oblique aerial imagery and object-based image analysis (OBIA) method. We classify the OAI into six classes namely tree, grass, façade, roof, road and others. In OBIA, we utilize the multiresolution segmentation algorithm to separate the image into objects by merging pixels with similar color and shape homogeneity. Then, the objects are classified by different features such as color, shape, texture and object related features. In our study, we also use the "height map" and "gradient map" generated by back projecting the dense matched point clouds to the OAI to assist for urban object detection. The classification result shows that we can differentiate façade and roof from buildings successfully with the assistant of the height and gradient information. In the meanwhile, the classification result can further offer the semantic information from the OAI to 3D building models.

UR - http://www.scopus.com/inward/record.url?scp=84903457855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903457855&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84903457855

SN - 9781629939100

VL - 1

SP - 750

EP - 757

BT - 34th Asian Conference on Remote Sensing 2013, ACRS 2013

PB - Asian Association on Remote Sensing

ER -

Jhan JP, Hsu YC, Rau J-Y. Urban land cover classification of oblique aerial imagery using object-based image analysis method. 於 34th Asian Conference on Remote Sensing 2013, ACRS 2013. 卷 1. Asian Association on Remote Sensing. 2013. p. 750-757