Active learning for object detection in high-resolution satellite images

TL;DR

This paper reviews active learning techniques for object detection in high-resolution satellite images, emphasizing their potential to reduce labeling effort in defense applications, demonstrated through aircraft detection case studies.

Contribution

It provides a comprehensive review of active learning methods tailored for high-resolution satellite imagery and illustrates their practical application in operational aircraft detection.

Findings

Active learning can significantly reduce labeling effort in satellite image analysis.

Effective active learning strategies improve detection performance with fewer labeled examples.

Application to aircraft detection demonstrates practical benefits in defense scenarios.

Abstract

In machine learning, the term active learning regroups techniques that aim at selecting the most useful data to label from a large pool of unlabelled examples. While supervised deep learning techniques have shown to be increasingly efficient on many applications, they require a huge number of labelled examples to reach operational performances. Therefore, the labelling effort linked to the creation of the datasets required is also increasing. When working on defense-related remote sensing applications, labelling can be challenging due to the large areas covered and often requires military experts who are rare and whose time is primarily dedicated to operational needs. Limiting the labelling effort is thus of utmost importance. This study aims at reviewing the most relevant active learning techniques to be used for object detection on very high resolution imagery and shows an example of the value of such techniques on a relevant operational use case: aircraft detection.