Concurrent Segmentation and Object Detection CNNs for Aircraft Detection and Identification in Satellite Images
This work addresses the problem of low recall and precision in satellite image analysis for aircraft detection, which is incremental as it combines existing methods.
The paper tackled the challenge of detecting and identifying small aircraft in satellite images by combining a segmentation CNN (modified U-net) and a detection CNN (RetinaNet), resulting in significantly reduced false negative rates compared to using each model alone.
Detecting and identifying objects in satellite images is a very challenging task: objects of interest are often very small and features can be difficult to recognize even using very high resolution imagery. For most applications, this translates into a trade-off between recall and precision. We present here a dedicated method to detect and identify aircraft, combining two very different convolutional neural networks (CNNs): a segmentation model, based on a modified U-net architecture, and a detection model, based on the RetinaNet architecture. The results we present show that this combination outperforms significantly each unitary model, reducing drastically the false negative rate.