Image-Based Real Estate Appraisal: Leveraging Mask R-CNN for Damage Detection and Severity Estimation

Authors

  • Kondragunta Rama Krishnaiah, Harish H

Keywords:

Real Estate Appraisal, Mask R-CNN, Image-Based Evaluation, Damage Detection, Deep Learning

Abstract

Real estate appraisal plays a vital role in property transactions, yet current methods often overlook the visual condition of a property, which can significantly impact its market value. This paper proposes a novel image-based real estate appraisal system that utilizes Mask R-CNN, a deep learning algorithm, to analyze and evaluate property images for damage detection and severity estimation. The system segments both interior and exterior images of properties, identifying key sections such as walls, floors, and components, and assesses the severity of any damage detected. By incorporating these image-based assessments, the system enhances traditional appraisal models, offering a more comprehensive and accurate property valuation. Experiments were conducted to validate the system's performance, showing promising results in detecting property damage and estimating its severity. This approach could be integrated into existing real estate platforms like Zillow and Realtor, providing more reliable appraisals and improving decision-making for buyers and sellers. Future work will focus on refining the model and adapting it to various real estate conditions globally.

Downloads

Download data is not yet available.

References

. Allen, G. (2017). Word Vector Size vs Vocabulary Size in word2vec. Retrieved from http://www.grega100k.com/wordvector/2016/03/17/words-vs-vocabularies.html

. Bagnoli, C., & Smith, H. (1998). The theory of fuzz logic and its application to real estate valuation. Journal of Real Estate Research, 16(2), 169-200.

. Dai, J., He, K., & Sun, J. (2016). Instance-aware semantic segmentation via multi-task network cascades. Paper presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

. Di, W., Sundaresan, N., Piramuthu, R., & Bhardwaj, A. (2014). Is a picture really worth a thousand words?:- on the role of images in e-commerce. Paper presented at the Proceedings of the 7th ACM international conference on Web search and data mining.

. Dong, C., Loy, C. C., He, K., & Tang, X. (2016). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307.

. Dwivedi, P. (2018). Ultimate Guide: Building a Mask R-CNN Model for Detecting Car Damage. Retrieved from https://www.analyticsvidhya.com/blog/2018/07/building-mask-r- cnn-model-detecting-damagecars-python/ Hardoon,

. D. R., Szedmak, S., & Shawe-Taylor, J. (2004). Canonical correlation analysis: An overview with application to learning methods. Neural computation, 16(12), 2639-2664.

. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. Paper presented at the Computer Vision (ICCV), 2017 IEEE International Conference on.

. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

. Kempa, O., Lasota, T., Telec, Z., & Trawiński, B. (2011). Investigation of bagging ensembles of genetic neural networks and fuzzy systems for real estate appraisal. Paper presented at the Asian Conference on Intelligent Information and Database Systems.

Downloads

Published

08.03.2024

How to Cite

Kondragunta Rama Krishnaiah. (2024). Image-Based Real Estate Appraisal: Leveraging Mask R-CNN for Damage Detection and Severity Estimation. International Journal of Intelligent Systems and Applications in Engineering, 12(21s), 4961 –. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/7541

Issue

Vol. 12 No. 21s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.