Feature Augmentation Improves Anomalous Change Detection for Human Activity Identification in Synthetic Aperture Radar Imagery
This addresses the challenge of detecting human activities in SAR data for applications like monitoring outdoor events, but it is incremental as it builds on existing ACD methods.
The paper tackled the problem of poor anomalous change detection (ACD) performance in SAR imagery for human activity identification, showing that low dimensionality leads to worse results than simple image differencing, but augmenting features with local spatial information improves performance.
Anomalous change detection (ACD) methods separate common, uninteresting changes from rare, significant changes in co-registered images collected at different points in time. In this paper we evaluate methods to improve the performance of ACD in detecting human activity in SAR imagery using outdoor music festivals as a target. Our results show that the low dimensionality of SAR data leads to poor performance of ACD when compared to simpler methods such as image differencing, but augmenting the dimensionality of our input feature space by incorporating local spatial information leads to enhanced performance.