Automatic Prediction of Building Age from Photographs

@article{Zeppelzauer2018AutomaticPO,
  title={Automatic Prediction of Building Age from Photographs},
  author={Matthias Zeppelzauer and Miroslav Despotovic and Muntaha Sakeena and David Koch and Mario D{\"o}ller},
  journal={Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval},
  year={2018}
}
We present a first method for the automated age estimation of buildings from unconstrained photographs. [...] Key Method We compile evaluation datasets from different sources and perform an detailed evaluation of our approach, its sensitivity to parameters, and the capabilities of the employed deep networks to learn characteristic visual age-related patterns. Results show that our approach is able to estimate building age at a surprisingly high level that even outperforms human evaluators and thereby sets a new…Expand
Combining Deep Learning and Variational Level Sets for Segmentation of Buildings
The larger context behind this work is the automated visual assessment of building characteristics (e.g. building age and condition) for the estimation of real estate prices from outdoor pictures. AExpand
Visual Estimation of Building Condition with Patch-level ConvNets
TLDR
This work develops a multi-scale patch-based pattern extraction approach and combines it with convolutional neural networks to estimate building condition from visual clues and shows that visually estimated building condition can serve as a proxy for condition estimates by appraisers. Expand
Intra-class Classification of Architectural Styles Using Visualization of CNN
TLDR
This paper proposes a new approach to accurately classify intra-class variance in the sense of their geographical locations: visualization of Convolutional Neural Network. Expand
Computer Analysis of Architecture Using Automatic Image Understanding
TLDR
This experiment provides a new paradigm for studying architecture, based on a quantitative approach that can enhance the traditional manual observation and analysis, and demonstrates that computer vision and pattern recognition algorithms can perform the complex cognitive task of analyzing images of buildings. Expand
Detecting individual abandoned houses from google street view: A hierarchical deep learning approach
TLDR
This study developed a new hierarchical deep learning method to leverage both global and local visual features of AH in the detection and demonstrated the feasibility of GSV imagery in AH detection and showed great potential to detect AH in a large spatial extent. Expand
Building Recognition in Static Images
TLDR
The method described is intended to be used to identify touristic landmarks in a set of vacation photos, while using few resources, and without the aid of consecrated, online solutions. Expand
4D Building Reconstruction with Machine Learning and Historical Maps
TLDR
This paper presents a methodology to derive 4D building models in the level of detail 1 (LoD1), inferring missing height information through machine learning techniques, and various evaluation metrics are presented for tackling the common issue of lack of ground-truth information within historical data. Expand
Analysis of the Uniqueness and Similarity of City Landscapes Based on Deep Style Learning
  • Ling Zhao, Li Luo, +4 authors Haifeng Li
  • ISPRS International Journal of Geo-Information
  • 2021
The city landscape is largely related to the design concept and aesthetics of planners. Influenced by globalization, planners and architects have borrowed from available designs, resulting in theExpand
Predicting residential electricity consumption using aerial and street view images
TLDR
An innovative approach to modeling building electricity consumption that relies exclusively on publicly available aerial and street view images is presented, which can predict electricity consumption about as well as conventional models, which are trained on commonly used features that are typically not publicly available at a large scale. Expand
Learning from urban form to predict building heights
TLDR
This work presents a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks, and finds that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. Expand
...
1
2
...

References

SHOWING 1-10 OF 32 REFERENCES
Towards Automated Real Estate Assessment from Satellite Images with CNNs
TLDR
This paper introduces a novel dataset generated from publicly available data sources with suitable ground-truth annotations for location assessment, adapts a state-of-the-art convolutional neural network and adapts it to predict different land covers and objects from satellite images and shows clear potential for the description of location quality. Expand
Rapid building detection using machine learning
TLDR
This work uses new candidate search and feature extraction techniques to reduce the problem to a machine learning (ML) classification task, and proposes a candidate alignment algorithm to boost classification performance to 80–90 % precision with a linear time algorithm and show it has negligible cost. Expand
LabelMe: A Database and Web-Based Tool for Image Annotation
TLDR
A web-based tool that allows easy image annotation and instant sharing of such annotations is developed and a large dataset that spans many object categories, often containing multiple instances over a wide variety of images is collected. Expand
What makes Paris look like Paris?
TLDR
It is shown that geographically representative image elements can be discovered automatically from Google Street View imagery in a discriminative manner and it is demonstrated that these elements are visually interpretable and perceptually geo-informative. Expand
Are buildings only instances?: exploration in architectural style categories
TLDR
This work explores the possibility that buildings can be categorized based on the architectural style, and performs experiments to evaluate how characteristic information obtained from low-level feature configurations can help in classification of buildings into architectural style categories. Expand
Unbiased look at dataset bias
TLDR
A comparison study using a set of popular datasets, evaluated based on a number of criteria including: relative data bias, cross-dataset generalization, effects of closed-world assumption, and sample value is presented. Expand
Building Recognition Using Local Oriented Features
  • Jing Li, N. Allinson
  • Engineering, Computer Science
  • IEEE Transactions on Industrial Informatics
  • 2013
TLDR
A new building recognition model based on local oriented features with an arbitrary orientation is presented and it is shown that the newly proposed SFBR model can obtain very satisfactory recognition accuracy despite its simplicity. Expand
Linking Past to Present: Discovering Style in Two Centuries of Architecture
TLDR
This work uses huge collections of street-level imagery to find visual patterns that correspond to semantic-level architectural elements distinctive to particular time periods, and uses this analysis both to date buildings, as well as to discover how functionally-similar architectural elements have changed over time due to evolving styles. Expand
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
Recognizing architecture styles by hierarchical sparse coding of blocklets
TLDR
This work decomposes a building image into a collection of blocks, each representing a basic architecture component such as a stone pillar, and introduces blocklets that capture the morphological characteristics of buildings to form architecture style recognition as matching between blocklets extracted from different buildings. Expand
...
1
2
3
4
...