Fast building detection using new feature sets derived from a very high-resolution image, digital elevation and surface model

ABSTRACT

Detecting building rooftops with very high-resolution (VHR) images is an important issue in many fields, including disaster management, urban planning, and climate change research. Buildings with varying geometrical features are challenging to detect accurately from VHR image due to complicated image scenes containing spectrally similar objects, illumination, occlusions, viewing angles, and shadows. This study aims to detect building rooftops with high accuracy using a new framework that includes VHR image, visible band difference vegetation index, digital surface and elevation models, the terrain ruggedness and the topographic position index. Five distinct feature sets were generated in order of importance by exposing the ten related stacking features to a feature selection procedure using the maximum relevance minimum redundancy method. Then, Auto-Encoder, k-NN, decision tree, RUSBoost, and random forest machine learning algorithms were utilized for binary classification. Random forest yielded the highest accuracy (97.2% F-score, 98.72% accuracy) when all features (F₁₀) were used, while decision tree was the least successful (59.16% F-score, 83.56% accuracy) for RGB feature set (F_RGB). It was revealed that classification of F₁₀ with random forest increased F-score by about 23% compared to classification with F_RGB. Additionally, McNemar’s tests showed no statistically significant difference between random forest vs k-NN and decision tree vs RUSBoost.

KEYWORDS:

• Building detection
• very high-resolution image
• machine learning
• deep learning

Acknowledgements

Thanks to Republic of Türkiye Ministry of National Defense General Directorate of Maps.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Author contributions

MAG was responsible for the study’s design, research, and writing.

Data availability statement

The required references and the accompanying author can provide the datasets.