Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne Lidar Data

Nguyen, Thanh Huy; Daniel, Sylvie; Guériot, Didier; Sintes, Christophe; Caillec, J.-M. Le

doi:10.5194/isprs-archives-xlii-2-w16-181-2019

Cited by 9 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown by Table II, the building extraction from LiDAR data (both 2011 and 2017) has achieved 100% of precision and recall thanks to the contribution of 3-D information. Similar performance of extracting buildings from LiDAR data has been found consistently, as presented by [6] when conducting tests on the ISPRS Vaihingen benchmark dataset [65].…”

Section: Evaluation Of Building Candidate Extraction and Matching supporting

confidence: 75%

See 1 more Smart Citation

Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

Nguyen

Daniel²,

Guériot³

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Applications based on synergistic integration of optical imagery and LiDAR data are receiving a growing interest from the remote sensing community. However, a misaligned integration of these datasets fails to fully profit from the potential of both sensors. An optimum fusion of optical imagery and LiDAR data requires an accurate registration. This is a complex problem since a versatile solution is still missing, especially when data are collected at different times, from different platforms, under different acquisition configurations. This article presents a coarse-to-fine registration method of optical imagery with airborne LiDAR data acquired in such context. First, a coarse registration involves processes of extraction and matching of building candidates from the two datasets. Then, a mutual-information-based fine registration is carried out. It involves a superresolution approach applied to LiDAR data to generate images with the same resolution as the optical image, and a local approach of transformation model estimation. The proposed method succeeds at overcoming the challenges associated with this difficult context. For instance, considering the experimented airborne LiDAR (2011) and orthorectified aerial imagery (2016) datasets, their spatial shift is reduced by 48.15% after the proposed coarse registration. Moreover, the incompatibility of size and spatial resolution is well addressed by the superresolution. Finally, a high accuracy of dataset alignment is also achieved, highlighted by a 40-cm error based on a checkpoint assessment and a 64-cm error based on a check-pair-line assessment. These promising results enable further researches for a complete fusion methodology between these datasets in this challenging context.

show abstract

Section: Evaluation Of Building Candidate Extraction and Matching supporting

confidence: 75%

“…On the other hand, aerial and satellite photogrammetry supplies rich semantic and texture information, in the form of multispectral images. By integrating the two technologies, many applications have been enabled such as building extraction [3], [6], city digital twin construction [7], land use and land cover classification [8], and so on [9], [10].…”

mentioning

confidence: 99%

Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

Nguyen

Daniel²,

Guériot³

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…(8)) is the Normalized Combined Mutual Information (NCMI) [17], given by Eq. (10). NCMI-based registration method relies on the similarity between the optical image and both LiDAR images, i.e.…”

Section: B Fine Registrationmentioning

confidence: 99%

“…On the other hand, aerial and satellite photogrammetry supplies rich semantic and texture information, in the form of multispectral images [9]. By integrating the two technologies, many applications have been enabled such as building extraction [4], [10], city digital twin construction [11], land use and land cover classification [12] and so on.…”

mentioning

confidence: 99%

Robust Building-Based Registration of Airborne Lidar Data and Optical Imagery on Urban Scenes

Nguyen¹,

Daniel²,

Guériot³

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

Applications based on synergistic integration of optical imagery and LiDAR data are receiving a growing interest from the remote sensing community. However, a misaligned integration between these datasets may fail to fully profit from the potential of both sensors. In this regard, an optimum fusion of optical imagery and LiDAR data requires an accurate registration. This is a complex problem since a versatile solution is still missing, especially when considering the context where data are collected at different times, from different platforms, under different acquisition configurations. This paper presents a coarse-to-fine registration method of aerial or satellite optical imagery with airborne LiDAR data acquired in such context. Firstly, a coarse registration involves processes of extraction and matching of building candidates from LiDAR data and optical imagery. Then, a Mutual Information-based fine registration is carried out. It involves a super-resolution approach applied to LiDAR data to generate images with the same resolution as the optical image, and a local approach of transformation model estimation. The proposed method succeeds at overcoming the challenges associated with the aforementioned difficult context. For instance, considering the experimented airborne LiDAR (2011) and orthorectified aerial imagery (2016) datasets, their spatial shift is reduced by almost a half (i.e. 48.15%) after the proposed coarse registration. Moreover, the incompatibility of size and spatial resolution is well addressed by the mentioned super-resolution approach. Finally, a high accuracy of dataset alignment is also achieved, highlighted by a 40-cm error based on a check-point assessment and a 64-cm error based on a checkpair-line assessment. Promising results yielded by this registration enable further research for a complete versatile fusion methodology between airborne LiDAR and optical imagery data in this challenging context.

show abstract

“…In their work, several samples as varied as wood images, pear and potato images, stereogram of bent piece of paper and also a video sequence of human lip movements were investigated using active contours. Since then, active contours have been widely used in different areas such as the medical field [18][19][20][21] and urban planning [22][23][24] of which, studies in the medical field form the major chunk.…”

Section: Introductionmentioning

confidence: 99%

Nondestructive inspection of aerospace composite laminate using thermal image processing

2020

View full text Add to dashboard Cite

In this work, a novel image segmentation method in thermographic images using the computer vision algorithm, active contours, is presented. These studies were done on thermal images obtained from pulse thermography. Many aerospace components are made of composite laminates. De-bonds/de-laminations set in during the manufacturing or in-service stages of these materials. Identification of de-bonds in composite laminates is a difficult task and faces many challenges when it is done through the processing of thermographic images. The first challenge is to get an accurate seed point to be used in active contours. In this study, the seed points for active contours were obtained from the moving averages of the pixel values taken along the region of interest lines. It is shown that the active contours with the help of seed points identified through this method are able to distinguish the de-bonds. The experimental results, supported by segmentation metrics, suggest that the segmentation method used here outperforms some earlier results which were based on the combination of Gabor filters, watershed models and divide-and-conquer methods such as subdivision of images.

show abstract

Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne Lidar Data

Cited by 9 publications

References 28 publications

Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

Robust Building-Based Registration of Airborne Lidar Data and Optical Imagery on Urban Scenes

Nondestructive inspection of aerospace composite laminate using thermal image processing

Contact Info

Product

Resources

About