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

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.

8 pages, 14 figures, 3 tables

References in corpus (3)

• Deep Residual Learning for Image Recognition
• The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs
• Detecting People in Cubist Art

Cited by in corpus (15)

• SpaceNet: A Remote Sensing Dataset and Challenge Series
• SpaceNet MVOI: a Multi-View Overhead Imagery Dataset
• Oriented Bounding Boxes for Small and Freely Rotated Objects
• A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations
• Satellite Imagery Multiscale Rapid Detection with Windowed Networks
• Bounding Box-Free Instance Segmentation Using Semi-Supervised Learning for Generating a City-Scale Vehicle Dataset
• SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations
• A Comparison of Deep Learning Object Detection Models for Satellite Imagery
• Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors
• Deep Active Learning for Remote Sensing Object Detection
• RarePlanes: Synthetic Data Takes Flight
• The SpaceNet Multi-Temporal Urban Development Challenge
• Guiding the Creation of Deep Learning-based Object Detectors
• Object Detection based on OcSaFPN in Aerial Images with Noise
• Airplane Type Identification Based on Mask RCNN and Drone Images