Building extraction by fusion of LIDAR data and aerial images

Mao, Jianhua; Liu, Xuefeng; Zeng, Qihong

doi:10.1109/urs.2009.5137631

Cited by 6 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fusion of LIDAR and aerial images has been discussed in several literatures for different purposes. For example, 3D modelling as in (Nakagawa & Shibasaki, 2003), Building extraction as (Mao, Liu, & Zeng, 2009) and (Zhou & Zhou, 2014). (Mao et al, 2009) integrated LIDAR with CCD images on the same board and used LIDAR return to filter vegetation, and then the remaining points were clustered to determine the buildings' roofs and walls.…”

Section: Related Work and Paper Contributionmentioning

confidence: 99%

“…For example, 3D modelling as in (Nakagawa & Shibasaki, 2003), Building extraction as (Mao, Liu, & Zeng, 2009) and (Zhou & Zhou, 2014). (Mao et al, 2009) integrated LIDAR with CCD images on the same board and used LIDAR return to filter vegetation, and then the remaining points were clustered to determine the buildings' roofs and walls. (Zhou & Zhou, 2014) utilized geometrical features and structures of houses to extract the building and create Digital Building Models (DBM).…”

Section: Related Work and Paper Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Synergy between aerial imagery and low density point cloud for automated image classification and point cloud densification

Badawy¹,

Moussa²,

El‐Sheimy³

2016

GEOBIA 2016: Solutions and Synergies

View full text Add to dashboard Cite

In this paper a synergy scheme between aerial imagery and sparse LIDAR point clouds is proposed for an automated aerial image classification. In this scheme, a point cloud and an image are chosen for a certain urban area. The point cloud is automatically classified into buildings, vegetation and roads using PCA and intensity variation. Afterwards, a projection of the point cloud into an image is obtained, such that it is registered with the aerial image. The aerial image classifier is trained with the LIDAR classification result to generate an automated classifier for aerial images. The classifier is tested with another image to demonstrate its accuracy. Another benefit of the synergy proposed is to densify the planar patches of the low density point cloud using the segmented aerial image to help modelling applications achieve more precise boundaries.

show abstract

Section: Related Work and Paper Contributionmentioning

confidence: 99%

Section: Related Work and Paper Contributionmentioning

confidence: 99%

Synergy between aerial imagery and low density point cloud for automated image classification and point cloud densification

Badawy¹,

Moussa²,

El‐Sheimy³

2016

GEOBIA 2016: Solutions and Synergies

View full text Add to dashboard Cite

show abstract

Section: Related Work and Paper Contributionmentioning

confidence: 99%

GEOBIA 2016: Solutions and synergies

Kerle¹,

Gerke²,

Lefèvre

2016

View full text Add to dashboard Cite

This study presents an algorithm for automatically mapping burnt areas using high-resolution images. It is applied to the Landsat 4, 5, 7 and 8 Land Surface Reflectance product; specifically, images acquired before and after (or during) the same fire season. It is also possible to extend the timeframe and use reference images acquired in the preceding year. This approach was adopted as cloudiness can make the acquisition of long time series impossible. A second advantage is that it avoids huge data transfers. The algorithm combines traditional, pixel-based image processing (calculation of spectral indexes and image differentiation) with object-based procedures (segmentation, reclassification, neighbourhood analysis) and consists of four steps. First, spectral indices (the Normalized Difference Vegetation Index and Normalised Burnt Ratio), and differences between image layers are calculated. The second is a multi-resolution segmentation, which uses the Normalised Burnt Ratio and near infrared layers. At this phase, masking of clouds, water and deserts takes place using atmospherically-corrected Landsat images. This is followed by the classification of 'core' burnt areas based on automatically-adjusted thresholds. The characteristics of the whole image (excluding clouds, deserts and water bodies) are analysed to develop functions that establish these thresholds. The fourth step consists of neighbourhood analysis. This focuses on objects that have not been classified as burnt areas, but whose spatial and spectral distances suggest that they may be part of them. The algorithm was tested in various areas (e.g. Spain, Greece, Siberia, California, Australia and Zambia). Comparisons with manual interpretation show that the fully-automated classification is very accurate (80-100%). The algorithm can be also applied to MODIS and Sentinel-2 data. It was developed within the framework of the Advanced Forest Fire Fighting (AF3) project, and the results have been used for damage and risk assessment.

show abstract

“…This reflects the extent of spectral distortion (Hartfield et al, 2011;Mao et al, 2009) caused by the low accuracy of the LiDAR intensity and undersampling. Since HSI fusion methodology replaces the intensity (I) band with a higher resolution panchromatic image, LiDAR intensity cannot be assumed to be suitable because the reflected intensity is not calibrated and the laser footprint size is much more smaller than the sampling (Mao et al, 2009). Hence, may not meet the required resolution for the fusion technique and therefore produces noisy classification result.…”

Section: Ajasmentioning

confidence: 99%

Imaging Spectroscopy and Light Detection and Ranging Data Fusion for Urban Features Extraction

Idrees

Shafri

Saeidi

2013

American Journal of Applied Sciences

View full text Add to dashboard Cite

This study presents our findings on the fusion of Imaging Spectroscopy (IS) and LiDAR data for urban feature extraction. We carried out necessary preprocessing of the hyperspectral image. Minimum Noise Fraction (MNF) transforms was used for ordering hyperspectral bands according to their noise. Thereafter, we employed Optimum Index Factor (OIF) to statistically select the three most appropriate bands combination from MNF result. The composite image was classified using unsupervised classification (k-mean algorithm) and the accuracy of the classification assessed. Digital Surface Model (DSM) and LiDAR intensity were generated from the LiDAR point cloud. The LiDAR intensity was filtered to remove the noise. Hue Saturation Intensity (HSI) fusion algorithm was used to fuse the imaging spectroscopy and DSM as well as imaging spectroscopy and filtered intensity. The fusion of imaging spectroscopy and DSM was found to be better than that of imaging spectroscopy and LiDAR intensity quantitatively. The three datasets (imaging spectrocopy, DSM and Lidar intensity fused data) were classified into four classes: building, pavement, trees and grass using unsupervised classification and the accuracy of the classification assessed. The result of the study shows that fusion of imaging spectroscopy and LiDAR data improved the visual identification of surface features. Also, the classification accuracy improved from an overall accuracy of 84.6% for the imaging spectroscopy data to 90.2% for the DSM fused data. Similarly, the Kappa Coefficient increased from 0.71 to 0.82. on the other hand, classification of the fused LiDAR intensity and imaging spectroscopy data perform poorly quantitatively with overall accuracy of 27.8% and kappa coefficient of 0.0988.

show abstract

Building extraction by fusion of LIDAR data and aerial images

Cited by 6 publications

References 11 publications

Synergy between aerial imagery and low density point cloud for automated image classification and point cloud densification

Synergy between aerial imagery and low density point cloud for automated image classification and point cloud densification

GEOBIA 2016: Solutions and synergies

Imaging Spectroscopy and Light Detection and Ranging Data Fusion for Urban Features Extraction

Contact Info

Product

Resources

About