Quality assessment of building extraction from remote sensing imagery

Avbelj, Janja; Müller, Rupert

doi:10.1109/igarss.2014.6947154

Cited by 4 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10). The root mean square error (RMSE) [36] was calculated separately between the vertices of the building outline (input data) and roof skeleton (extracted data) and the reference points for every building. The average RMSE was 0.73 m for the building outline and 0.92 m for the roof skeleton.…”

Section: Resultsmentioning

confidence: 99%

Automatic Reconstruction of Roof Models From Building Outlines and Aerial Image Data

Hron

Halounová

2019

Acta Polytech

View full text Add to dashboard Cite

The knowledge of roof shapes is essential for the creation of 3D building models. Many experts and researchers use 3D building models for specialized tasks, such as creating noise maps, estimating the solar potential of roof structures, and planning new wireless infrastructures. Our aim is to introduce a technique for automating the creation of topologically correct roof building models using outlines and aerial image data. In this study, we used building footprints and vertical aerial survey photographs. Aerial survey photographs enabled us to produce an orthophoto and a digital surface model of the analysed area. The developed technique made it possible to detect roof edges from the orthophoto and to categorize the edges using spatial relationships and height information derived from the digital surface model. This method allows buildings with complicated shapes to be decomposed into simple parts that can be processed separately. In our study, a roof type and model were determined for each building part and tested with multiple datasets with different levels of quality. Excellent results were achieved for simple and medium complex roofs. Results for very complex roofs were unsatisfactory. For such structures, we propose using multitemporal images because these can lead to significant improvements and a better roof edge detection. The method used in this study was shared with the Czech national mapping agency and could be used for the creation of new 3D modelling products in the near future.

show abstract

Section: Resultsmentioning

confidence: 99%

Automatic Reconstruction of Roof Models From Building Outlines and Aerial Image Data

Hron

Halounová

2019

Acta Polytech

View full text Add to dashboard Cite

show abstract

“…The corner‐distance RMSE was calculated according to the formula (Avbelj and Müller, ):

{RMSE}_{A, B} = n^{- 1 / 2} \sqrt{\sum_{i = 1}^{n} {()(, {truemin}_{b \in B}, false‖ {bolda}_{i} - b false‖)}^{2}}

where A and B are the compared polygons, b ∈ B is the closest vertex to the vertex a i ∈ A . The calculation was carried out in two ways in order to better estimate geometric discrepancies between the extracted and reference datasets.…”

Section: Methodsmentioning

confidence: 99%

“…Another possibility is to exclude distances exceeding a given threshold from the RMSE calculation which also decreases the objectivity of the outcomes. Moreover, RMSE calculation is not symmetric and delivers different results when the extracted vertexes are sought in the reference polygons and vice versa (Avbelj and Müller, ).…”

Section: Building Outline Evaluation: a Reviewmentioning

confidence: 99%

“…() propose a new metric called PoLiS (Polygon and Line Segments). It calculates the average of the distances between each corner of an extracted building outline ( A ) and the closest point (not necessary a corner) on a reference boundary (∂ B ) and vice versa according to the following formula (Avbelj and Müller, ):

p false(A, B false) = \frac{1}{2 n} \sum_{i = 1}^{n} {truemin}_{b \in \partial B} false‖ {bolda}_{i} - boldb false‖ + \frac{1}{2 m} \sum_{j = 1}^{m} {truemin}_{a \in \partial A} false‖ b_{j} - bolda false‖

where b ∈ ∂ B is the nearest point of the polygon B to the vertex a i ∈ A . Unlike the RMSE, the metric is clearly defined and it is easy to implement.…”

Section: Building Outline Evaluation: a Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Quality Measures for Building Outline Extraction

Potůčková

Hofman

2016

The Photogrammetric Record

View full text Add to dashboard Cite

To date, numerous automatic building detection methods using lidar data have been developed. However, in most cases the parameters used for the evaluation of the results are not specified, accuracy assessment results cannot be readily compared or no result evaluation is performed at all. In this study, accuracy assessment aspects have been analysed in order to find a generally applicable approach for the comparison of building outline extraction methods. An area‐based evaluation of accuracy has been selected as the most suitable due to its robustness, predictability and comparability between datasets. This assessment can be further supplemented with both object‐ and area‐based evaluations, procured solely with those buildings that were classified as true positives, in order to interpret the extraction results in more detail. In cases where a reference dataset of superior quality (such as low‐altitude aerial imagery) is available, an absolute accuracy evaluation is also relevant.

show abstract

“…The relevance of detecting IBs in Italy was stressed also by Cialdea and Quercio [24] with a case study concerning illegal settlements in the city of Campobasso (the capital of the Molise region, South of Italy) and its hinterland. So far, several methods have been proposed for automatic building detection from high-resolution remote sensing images ( [25][26][27][28][29]); few of them are specifically focused on IBs detection (e.g., [30][31][32][33][34]). Soon, most of them will be available on the marketplace as a plugin of GIS software.…”

Section: Relevance Of the Problemmentioning

confidence: 99%

Ranking of Illegal Buildings Close to Rivers: A Proposal, Its Implementation and Preliminary Validation

Felice

2019

IJGI

View full text Add to dashboard Cite

Illegal buildings (IBs) are a dramatic problem in developing countries due to the population explosion, but, at the same time, they represent an unsolved issue in several states usually called advanced (as, for instance, Italy). To protect the environment, and hence, people, land authorities must respond to the challenge of IBs by demolishing them. However, in countries where the phenomenon is extended, it is indispensable to provide those figures with an IT tool that returns to them an order of demolition. Through remote sensing methods, suspicious buildings can be identified with a good approximation, but they are all ex aequo. The research summarized in this paper formalizes a two-steps method to deal with a specific category of IBs, namely, those that are close to rivers. These buildings are of special interest to land authorities because people living or simply working inside them are exposed to the flood hazard that each year claims many victims all over the world. The first step of the method computes the census of the IBs located close to rivers, while the second step computes the ranking of these buildings. The ranking may be used as the IBs demolition order. In the paper, it is also proposed the structure of a Spatial DataBase (briefly, SDB) that is suitable to store the input data necessary to solve the problem, as well as the final ranking. Spatial SQL queries against the SDB implement the proposed two-steps method. A real case study was carried out to make a preliminary validation of the method.

show abstract

Quality assessment of building extraction from remote sensing imagery

Cited by 4 publications

References 9 publications

Automatic Reconstruction of Roof Models From Building Outlines and Aerial Image Data

Automatic Reconstruction of Roof Models From Building Outlines and Aerial Image Data

Comparison of Quality Measures for Building Outline Extraction

Ranking of Illegal Buildings Close to Rivers: A Proposal, Its Implementation and Preliminary Validation

Contact Info

Product

Resources

About