You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery

TL;DR

This paper introduces YOLT, a fast multi-scale object detection pipeline for satellite imagery that effectively detects small objects across large images with high accuracy, even at reduced resolutions.

Contribution

The paper presents a novel, rapid detection pipeline capable of handling large satellite images and small objects with minimal training data, outperforming traditional methods in speed and accuracy.

Findings

Achieves >0.5 km2/s processing rate on satellite images.

F1 score exceeds 0.8 for vehicle localization.

Objects as small as 5 pixels can be reliably detected.

Abstract

Detection of small objects in large swaths of imagery is one of the primary problems in satellite imagery analytics. While object detection in ground-based imagery has benefited from research into new deep learning approaches, transitioning such technology to overhead imagery is nontrivial. Among the challenges is the sheer number of pixels and geographic extent per image: a single DigitalGlobe satellite image encompasses >64 km2 and over 250 million pixels. Another challenge is that objects of interest are minuscule (often only ~10 pixels in extent), which complicates traditional computer vision techniques. To address these issues, we propose a pipeline (You Only Look Twice, or YOLT) that evaluates satellite images of arbitrary size at a rate of >0.5 km2/s. The proposed approach can rapidly detect objects of vastly different scales with relatively little training data over multiple sensors. We evaluate large test images at native resolution, and yield scores of F1 > 0.8 for vehicle localization. We further explore resolution and object size requirements by systematically testing the pipeline at decreasing resolution, and conclude that objects only ~5 pixels in size can still be localized with high confidence. Code is available at https://github.com/CosmiQ/yolt.