Concurrent Segmentation and Object Detection CNNs for Aircraft Detection and Identification in Satellite Images

TL;DR

This paper introduces a combined CNN approach using segmentation and detection models to improve aircraft identification in satellite images, significantly reducing false negatives.

Contribution

It presents a novel method integrating U-net and RetinaNet architectures for enhanced aircraft detection and identification in satellite imagery.

Findings

Combined model outperforms individual models

Significant reduction in false negative rate

Improved accuracy in small object detection

Abstract

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.