Optimization of structure elements for morphological hit-or-miss transform for building extraction from VHR airborne imagery in natural hazard areas

Parape, Chandana Dinesh; Premachandra, Chinthaka; Tamura, Masayuki

doi:10.1007/s13042-014-0326-1

Cited by 8 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Very-high-resolution optical imagery can visualize earthquake damage, and it has been used by many researchers [ 9 , 12 , 26 , 27 ]. Major techniques used for retrieving the earthquake-induced building damage information are object based classification [ 28 , 29 , 30 ], template matching and pattern recognition [ 31 ], and supervised classification [ 32 , 33 , 34 ]. Airborne imagery is another source of building damage information [ 35 , 36 , 37 , 38 , 39 , 40 ].…”

Section: Introductionmentioning

confidence: 99%

Earthquake Damage Visualization (EDV) Technique for the Rapid Detection of Earthquake-Induced Damages Using SAR Data

Sharma

Tateishi

Hara

et al. 2017

Sensors

View full text Add to dashboard Cite

The damage of buildings and manmade structures, where most of human activities occur, is the major cause of casualties of from earthquakes. In this paper, an improved technique, Earthquake Damage Visualization (EDV) is presented for the rapid detection of earthquake damage using the Synthetic Aperture Radar (SAR) data. The EDV is based on the pre-seismic and co-seismic coherence change method. The normalized difference between the pre-seismic and co-seismic coherences, and vice versa, are used to calculate the forward (from pre-seismic to co-seismic) and backward (from co-seismic to pre-seismic) change parameters, respectively. The backward change parameter is added to visualize the retrospective changes caused by factors other than the earthquake. The third change-free parameter uses the average values of the pre-seismic and co-seismic coherence maps. These three change parameters were ultimately merged into the EDV as an RGB (Red, Green, and Blue) composite imagery. The EDV could visualize the earthquake damage efficiently using Horizontal transmit and Horizontal receive (HH), and Horizontal transmit and Vertical receive (HV) polarizations data from the Advanced Land Observing Satellite-2 (ALOS-2). Its performance was evaluated in the Kathmandu Valley, which was hit severely by the 2015 Nepal Earthquake. The cross-validation results showed that the EDV is more sensitive to the damaged buildings than the existing method. The EDV could be used for building damage detection in other earthquakes as well.

show abstract

Section: Introductionmentioning

confidence: 99%

Earthquake Damage Visualization (EDV) Technique for the Rapid Detection of Earthquake-Induced Damages Using SAR Data

Sharma

Tateishi

Hara

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…Further study should be made as regards the morphological processing of windows, doors, and platforms to obtain higher accuracy and more detailed information. Structural elements and morphological processing times affect the results of facades extraction both in accuracy and details [37,38].…”

Section: Discussionmentioning

confidence: 99%

Extraction and Simplification of Building Façade Pieces from Mobile Laser Scanner Point Clouds for 3D Street View Services

et al. 2016

IJGI

View full text Add to dashboard Cite

Extraction and analysis of building façades are key processes in the three-dimensional (3D) building reconstruction and realistic geometrical modeling of the urban environment, which includes many applications, such as smart city management, autonomous navigation through the urban environment, fly-through rendering, 3D street view, virtual tourism, urban mission planning, etc. This paper proposes a building facade pieces extraction and simplification algorithm based on morphological filtering with point clouds obtained by a mobile laser scanner (MLS). First, this study presents a point cloud projection algorithm with high-accuracy orientation parameters from the position and orientation system (POS) of MLS that can convert large volumes of point cloud data to a raster image. Second, this study proposes a feature extraction approach based on morphological filtering with point cloud projection that can obtain building facade features in an image space. Third, this study designs an inverse transformation of point cloud projection to convert building facade features from an image space to a 3D space. A building facade feature with restricted facade plane detection algorithm is implemented to reconstruct façade pieces for street view service. The results of building facade extraction experiments with large volumes of point cloud from MLS show that the proposed approach is suitable for various types of building facade extraction. The geometric accuracy of building façades is 0.66 m in x direction, 0.64 in y direction and 0.55 m in the vertical direction, which is the same level as the space resolution (0.5 m) of the point cloud.

show abstract

“…The third one only adopts deep features from the DOM image, and the fourth one uses deep features from the nDSM image and DOM image (proposed). In Table 5, these four strategies are represented using strategy (1) to (4), respectively. Figure 13 shows the results of four strategies, and Table 5 gives the corresponding accuracy assessments.…”

Section: Feature Selectionmentioning

confidence: 99%

“…Extraction results of four strategies in three data sets. (a-d): results based on strategy (1) to (4) in Area1 with DLG_M respectively; (e-h): results based on strategy (1) to (4) in Area2 with DLG2008 respectively; and (i-l): results based on strategy (1) to (4) in Area2 with DLG2014 respectively. Figure 13 and Table 5 indicate that hand-crafted features are ineffective.…”

Section: Feature Dimension Reductionmentioning

confidence: 99%

“…However, this kind of relationship cannot sufficiently represent all kinds of remote sensed images. Since vegetation is hard to distinguish from buildings, some methods were designed to filter vegetation area and then apply some morphological operations [3][4][5]. According to some studies [3,4], the application of a normalized difference vegetation index (NDVI) is helpful for filtering of vegetation areas and obtaining better extraction results.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Extracting Building Areas from Photogrammetric DSM and DOM by Automatically Selecting Training Samples from Historical DLG Data

Chen

Zhang

Nie

et al. 2020

IJGI

View full text Add to dashboard Cite

This paper presents an automatic building extraction method which utilizes a photogrammetric digital surface model (DSM) and digital orthophoto map (DOM) with the help of historical digital line graphic (DLG) data. To reduce the need for manual labeling, the initial labels were automatically obtained from historical DLGs. Nonetheless, a proportion of these labels are incorrect due to changes (e.g., new constructions, demolished buildings). To select clean samples, an iterative method using random forest (RF) classifier was proposed in order to remove some possible incorrect labels. To get effective features, deep features extracted from normalized DSM (nDSM) and DOM using the pre-trained fully convolutional networks (FCN) were combined. To control the computation cost and alleviate the burden of redundancy, the principal component analysis (PCA) algorithm was applied to reduce the feature dimensions. Three data sets in two areas were employed with evaluation in two aspects. In these data sets, three DLGs with 15%, 65%, and 25% of noise were applied. The results demonstrate the proposed method could effectively select clean samples, and maintain acceptable quality of extracted results in both pixel-based and object-based evaluations.

show abstract

Optimization of structure elements for morphological hit-or-miss transform for building extraction from VHR airborne imagery in natural hazard areas

Cited by 8 publications

References 24 publications

Earthquake Damage Visualization (EDV) Technique for the Rapid Detection of Earthquake-Induced Damages Using SAR Data

Earthquake Damage Visualization (EDV) Technique for the Rapid Detection of Earthquake-Induced Damages Using SAR Data

Extraction and Simplification of Building Façade Pieces from Mobile Laser Scanner Point Clouds for 3D Street View Services

Extracting Building Areas from Photogrammetric DSM and DOM by Automatically Selecting Training Samples from Historical DLG Data

Contact Info

Product

Resources

About