Automated damage assessment based on satellite imagery is crucial for initiating fast response actions. Several methods based on supervised learning approaches have been reported as effective for automated mapping of damages using remote sensing images. However, adopting these methods for practical use is still challenging, as they typically demand large amounts of training samples to build a supervised classifier, which are usually not readily available. With the advancement in technologies local and detailed damage assessment for individual buildings is being made available, for example through analysis of images captured by unmanned aerial vehicles, monitoring systems installed in buildings, and through crowdsourcing. Often such assessments are being done in parallel, with results becoming available progressively. In this paper, an online classification strategy is adopted where a classifier is built incrementally using the streaming damage labels from various sources as training samples, i.e. without retraining it from the scratch when new samples stream in. The Passive-Aggressive online classifier is used for the classification process. Apart from the classifier, the choice of image features plays a crucial role in the performance of the classification. The features extracted using recently reported deep learning approaches such as Convolutional Neural Networks (CNN), which learns features directly from images, have been reported to be more effective than conventional handcrafted features such as gray level co-occurrence matrix and Gabor wavelets. Thus in this study, the potential of CNN features is explored for online classification of satellite image to detect structural damage, and is compared against handcrafted features. The feature extraction and classification process is carried out at an object level, where the objects are obtained by over-segmentation of the satellite image. The proposed online framework for damage classification achieves a maximum overall accuracy of about 73%, which is comparable to that of batch classifier accuracy (74%) obtained for the same training and testing samples, however at a significantly lesser time and memory requirements. Moreover, the CNN features always significantly outperform handcrafted features.
|Conference||6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016|
|Period||14/09/16 → 16/09/16|