Kevin W. Bowyer - Change Detection In Before/After Aerial Images

  • Jim Thomas, Ahsan Kareem and Kevin W. Bowyer,
    Automated post-storm damage classification of low-rise building roofing systems using high resolution aerial imagery,
    IEEE Transactions on Geoscience and Remote Sensing 52 (7), 3851-3861, July 2014.
    link to this paper in IEEE Xplore.
    Techniques concerning postdisaster assessment from remotely sensed images have been studied by different research communities in the past decade. Such an assessment benefits a range of stakeholders, e.g., government organizations, insurance industry, local communities, and individual homeowners. This work explores detailed damage assessment on an individual building basis by utilizing supervised classification. In contrast with previous research efforts in the field, this work attempts at predicting the type of damages such as missing tiles, collapsed rooftop, and presence of holes, gaps, or cavities. ...

  • Fast, Robust Feature-Based Matching for Automatic Image Registration in Disaster Response Applications,
    Jim Thomas, Ahsan Kareem and Kevin W. Bowyer,
    IEEE Interational Geoscience and Remote Sensing Symposium (IGARSS), July 2012.
    pdf of this paper.
    ... In this work, we propose a two-step approach to achieve fast and robust registration of before- / after-disaster aerial image pairs. This problem is difficult because there can be substantial change in the image content between the two images, and the time of day and lighting typically are different between the two images. ...

  • Color Balancing for Change Detection in Multitemporal Images,
    Jim Thomas, Kevin W. Bowyer and Ahsan Kareem,
    IEEE Workshop on Applications of Computer Vision, January 2012, Colorado Springs, CO.
    pdf of this paper.
    narrated ppt on this work.
    ... In this paper we address color balancing for the purpose of change detection. ... We evaluated the proposed method against other state-of-the-art ones using a database consisting of aerial image pairs. The test image pairs were taken at different times, under different lighting conditions, and with different scene geometries and camera positions. On this database, our proposed approach outperformed other state-of-the-art algorithms.

  • Towards a robust automated hurricane damage assessment from high-resolution images,
    James Thomas, Ahsan Kareem, and Kevin W. Bowyer,
    13th International Conference on Wind Engineering (ICWE 13), July 2011.
    pdf of this paper.
    In the event of a natural disaster such as hurricane or earthquake, estimating the extent of damage is necessary for implementing fast and effective recovery measures. Images of affected areas are easily obtained through satellite or aerial sensors. The key objects of interest in such images are buildings, as damage directly impacts lives. This work aims to build a system capable of fine-grained damage analysis by comparing before and after storm images. ...

  • Efficacy of Damage Detection Measures from Aerial Images,
    Jim Thomas, Ahsan Kareem and Kevin W. Bowyer,
    11-th Americas Conference on Wind Engineering, June 2009.
    pdf of this paper.
    Estimating the extent of damage caused by natural disasters is necessary for implementing effective recovery measures. Aerial images of affected areas are easily obtained through satellite or aerial sensors. A careful analysis of images from before and after an event facilitates rapid detection and assessment of damage. Significant previous research has been done on developing measures to quantify the damage. In this study we evaluate the efficacy of existing change measures used to estimate damage. Determining the efficacy of these damage measures in definitive characterization of damage states is necessary for accurate automated assessment of windstorm damage.