Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors developed a new, easier way to check how rundown houses are in cities using advanced computer models that look at pictures from different angles. These models can spot problems like broken roofs or walls and give scores on how damaged the houses might be. They tested their method against expert human checks and found that combining multiple models made the system more accurate. This approach could help cities keep track of housing conditions more cheaply and regularly compared to traditional surveys.
urban blightvision-language modelshousing condition assessmentroof integritywall damageensemble learningXGBooststructured promptsstreet view imageryprobabilistic estimates
Authors
Xiaohao Yang, Aohua Tian, Derek Van Berkel, Xu Qiang, Mark Lindquist
Abstract
Addressing urban blight has seen increased focus in the past 15 years. Assessing urban blight is essential for guiding urban planning, targeting rehabilitation, and safeguarding public health, yet traditional residential blight surveys are difficult to maintain at scale due to the labor-intensive cost and long-term cycle. This study introduced a scalable framework for estimating residential blight using open-source large vision-language models on multiple views. Structured prompts guided models to evaluate housing attributes, including roof integrity, wall damage, and broken or boarded openings, producing both binary assessments and probabilistic estimates of disrepair. To evaluate the performance of these visual assessments, we compared professional human annotations of these features across several models, including an ensemble stacking approach based on XGBoost and a weighted scoring system. Results showed that (i) multiple street views can contribute to the improvement of accuracy, (ii) large vision-language models have different strengths of inference, (iii) the ensemble learner outperforms individual base models, enhancing robustness across all residential conditions and blight assessment. The practical application of the method allows low-cost tracking and management of housing stock conditions, providing a regularly updatable complement to traditional blight surveys.