Window Detection from UAS-Derived Photogrammetric Point Cloud Employing Density-Based Filtering and Perceptual Organization

Malihi, Shirin; Zoej, Mohammad Javad Valadan; Hahn, Michael; Mokhtarzade, Mehdi

doi:10.3390/rs10081320

Cited by 14 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a result indicates that the structures falsely recognized as windows openings are mostly very small. Our achieved values of 90% completeness and 95% correctness, compared against the same metrics reported in the literature (85% and 82% [15], or 92% and 96% [16]), prove the quality of the applied method.…”

Section: Contextual Classification Of Tir-attributed Point Cloudssupporting

confidence: 83%

“…In a general context, an object is considered to be a true positive if a certain minimum percentage of its area is covered by objects in the other data set. In our research, similarly to the window detection evaluation presented in [15,16], the detected object is considered to be true positive (TP) if at least 70% of its points are properly classified. If at least 50% of object points are classified incorrectly, the object is considered to be a false negative (FN).…”

Section: Contextual Classification Of Tir-attributed Point Cloudsmentioning

confidence: 99%

See 1 more Smart Citation

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

2020

View full text Add to dashboard Cite

Targeted energy management and control is becoming an increasing concern in the building sector. Automatic analyses of thermal data, which minimize the subjectivity of the assessment and allow for large-scale inspections, are therefore of high interest. In this study, we propose an approach for a supervised extraction of façade openings (windows and doors) from photogrammetric 3D point clouds attributed to RGB and thermal infrared (TIR) information. The novelty of the proposed approach is in the combination of thermal information with other available characteristics of data for a classification performed directly in 3D space. Images acquired in visible and thermal infrared spectra serve as input data for the camera pose estimation and the reconstruction of 3D scene geometry. To investigate the relevance of different information types to the classification performance, a Random Forest algorithm is applied to various sets of computed features. The best feature combination is then used as an input for a Conditional Random Field that enables us to incorporate contextual information and consider the interaction between the points. The evaluation executed on a per-point level shows that the fusion of all available information types together with context consideration allows us to extract objects with 90% completeness and 95% correctness. A respective assessment executed on a per-object level shows 97% completeness and 88% accuracy.

show abstract

Section: Contextual Classification Of Tir-attributed Point Cloudssupporting

confidence: 83%

Section: Contextual Classification Of Tir-attributed Point Cloudsmentioning

confidence: 99%

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

2020

View full text Add to dashboard Cite

show abstract

“…The ground truth (bounding boxes of the windows) is measured manually. Similar to the work (Malihi et al, 2018), if at least 70% of points in a segment are located inside a reference bounding box, this segment is considered to be a TP. While if more than 50% of points in a segment are not located inside a reference bounding box, this segment is counted as a FP.…”

Section: Discussionmentioning

confidence: 99%

Unsupervised Window Extraction From Photogrammetric Point Clouds With Thermal Attributes

Lin

Dong

Zhang

et al. 2019

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The automatic extraction of windows from photogrammetric data has achieved increasing attention in recent times. An unsupervised windows extraction approach from photogrammetric point clouds with thermal attributes is proposed in this study. First, point cloud segmentation is conducted by a popular workflow: Multiscale supervoxel generation is applied to the image-based 3D point cloud, followed by region growing and energy optimization using spatial positions and thermal attributes of the raw points. Afterwards, an object-based feature (window index) is extracted using the average thermal attribute and the size of the object. Next, thresholding is applied to extract initial window regions. Finally, several criterions are applied to further refine the extraction results. For practical validation, the approach is evaluated on an art nouveau building row façade located at Dresden, Germany.

show abstract

“…But one could also consider detecting facades based on sparse photogrammetric point clouds derived from oblique aerial images. However, in contrast to high resolution point clouds as discussed in (Malihi et al, 2018), such clouds can become noisy with wave-like artifacts (see Figure 1) and do not contain differentiated depth information. Also, windows might not appear as holes in photogrammetric clouds.…”

Section: Introductionmentioning

confidence: 95%

Facade Reconstruction for Textured Lod2 Citygml Models Based on Deep Learning and Mixed Integer Linear Programming

Hensel

Goebbels

Kada

2019

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The paper describes a workflow for generating LoD3 CityGML models (i.e. semantic building models with structured facades) based on textured LoD2 CityGML models by adding window and door objects. For each wall texture, bounding boxes of windows and doors are detected using “Faster R-CNN”, a deep neural network. We evaluate results for textures with different resolutions on the ICG Graz50 facade dataset. In general, detected bounding boxes match very well with the rectangular shape of most wall openings. Thus, no further classification of shapes is required. Windows are typically aligned to rows and columns, and only a few different types of windows exist for each facade. However, the neural network proposes rectangles of varying sizes, which are not always aligned perfectly. Thus, we use post-processing to obtain a more realistic appearance of facades. Window and door rectangles get aligned by solving a mixed integer linear optimization problem, which automatically leads to a clustering of these openings into few different classes of window and door types. Furthermore, an a-priori knowledge about the number of clusters is not required.

show abstract

Window Detection from UAS-Derived Photogrammetric Point Cloud Employing Density-Based Filtering and Perceptual Organization

Cited by 14 publications

References 41 publications

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

Unsupervised Window Extraction From Photogrammetric Point Clouds With Thermal Attributes

Facade Reconstruction for Textured Lod2 Citygml Models Based on Deep Learning and Mixed Integer Linear Programming

Contact Info

Product

Resources

About