In the project ImmBild, we develop automatic image analysis methods for the assessment of location quality of real estate objects from satellite images.

Real Estate Image Analysis (REIA) is a novel research initiative initiated by real estate experts and computer scientists from the Kufstein University of Applied Sciences and the St. Pölten University of Applied Sciences with the goal to improve the assessment of real estate by automated image analysis. The REIA initiative brings together two research disciplines that have so far hardly touched each other and bears a strong potential for novel and innovative real estate-related applications and services.

The theoretic foundation for real estate assessment is the hedonic pricing method which describes how the quantity and quality of object characteristics determine its price in a particular market. More formally, the hedonic price function takes the form: P_i = f(S_i, L_i, N_i), where P_i is the logarithm of the price or rent of house i, S_i represents structural housing characteristics, L_i location variables and N_i neighborhood characteristics. Traditional hedonic pricing is restricted to those characteristics which are available as quantifiable data, e.g. distances to schools, public transport, etc. REIA extends this model by additional - so far inaccessible - characteristics, which are derived by automated image analysis. To this end image data at different levels is leveraged. Structural housing characteristics (S_i) can be extracted from inside and outside views of buildings. Neighborhood (N_i) and location characteristics (L_i) in turn can be mined from 360° streetview and satellite images. The extracted characteristics represent a completely new set of parameters for real estate assessment and - beyond this - enable novel ways to index, search and retrieve real estate.

The project "ImmBild" (FFG COIN 856333) combines real estate industry specific knowledge and automated image analysis to find novel ways to determine rent and real estate prices. We leverage deep learning methodology to identify and classify different land covers, such as streets, water, trees and to detect different types of houses (e.g. residential and industrial buildings). From this information we derive location quality descriptors to extend hedonic price models.

Project partners


Despotovic, M., D. Koch, S. Leiber, M. Döller, M. Sakeena, and M. Zeppelzauer, "Prediction and Analysis of Heating Energy Demand and Year of Construction for Detached Houses by Computer Vision", Energy, Submitted.
Koch, D., M. Despotovic, S. Leiber, M. Sakeena, M. Döller, and M. Zeppelzauer, "Real Estate Image Analysis - A Literature Review", Real Estate Economics Journal, Submitted.
Zeppelzauer, M., M. Despotovic, M. Sakeena, D. Koch, and M. Döller, "Automatic Prediction of Building Age from Photographs", Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, New York, NY, USA, ACM, pp. 126–134, 2018.
Koch, D., M. Despotovic, M. Sakeena, M. Döller, and M. Zeppelzauer, "Visual Estimation of Building Condition with Patch-level ConvNets", Proceedings of the 2018 ACM Workshop on Multimedia for Real Estate Tech, New York, NY, USA, ACM, pp. 12–17, 2018.
Muhr, V., M. Despotovic, D. Koch, M. Döller, and M. Zeppelzauer, "Towards Automated Real Estate Assessment from Satellite Images with CNNs", In Proceedings of the 10th Forum Media Technology (FMT), Best Paper Award, vol. 2009, St. Pölten, Austria, CEUR Workshop Proceedings, pp. 14–23, 11/2017.