Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-8, 1185-1192, 2014
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-8/1185/2014/
doi:10.5194/isprsarchives-XL-8-1185-2014
© Author(s) 2014. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
28 Nov 2014
Shadow Analysis Technique for Extraction of Building Height using High Resolution Satellite Single Image and Accuracy Assessment
P. L. N. Raju1, H. Chaudhary2, and A. K. Jha1 1Remote Sensing and Geoinformatics Group, Indian Institute of Remote Sensing, ISRO, Dehradun, India
2G.D. Colony, Mayur Vihar Phase 3, New Delhi, 110096, India
Keywords: High Resolution Satellite Data, Automatic Extraction, Shadow Analysis Abstract. These High resolution satellite data with metadata information is used to extract the height of the building using shadow. Proposed approach divides into two phases 1) rooftop and shadow extraction and 2) height estimation. Firstly the rooftop and shadow region were extracted by manual/ automatic methods using Example – Based and Rule – Based approaches. After feature extraction next step is estimating height of the building by taking rooftop in association with shadow using Ratio Method and by using the relation between sun-satellite geometry. The performance analysis shows the total mean error of height is 0.67 m from ratio method, 1.51 m from Example – Based Approach and 0.96 m from Rule – Based Approach. Analysis concluded that Ratio Method i.e. manual method is best for height estimation but it is time consuming so the automatic Rule Based approach is best for height estimation in comparison to Example Based Approach because it require more knowledge and selection of more training samples as well as slows the processing rate of the method.
Conference paper (PDF, 900 KB)


Citation: Raju, P. L. N., Chaudhary, H., and Jha, A. K.: Shadow Analysis Technique for Extraction of Building Height using High Resolution Satellite Single Image and Accuracy Assessment, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-8, 1185-1192, doi:10.5194/isprsarchives-XL-8-1185-2014, 2014.

BibTeX EndNote Reference Manager XML