Satellite Imagery Multiscale Rapid Detection with Windowed Networks
Adam Van Etten

TL;DR
This paper introduces SIMRDWN, a fast, scalable pipeline for detecting small objects in large satellite images using multiple detection frameworks, achieving high accuracy and speed.
Contribution
The paper presents a unified, multiscale detection pipeline for satellite imagery that integrates various models and enables rapid, high-resolution object detection over large areas.
Findings
YOLT achieves highest mAP and fastest inference speed.
Using two detectors at different scales improves detection accuracy.
The pipeline processes images at native resolution at > 0.2 km²/sec.
Abstract
Detecting small objects over large areas remains a significant challenge in satellite imagery analytics. Among the challenges is the sheer number of pixels and geographical extent per image: a single DigitalGlobe satellite image encompasses over 64 km2 and over 250 million pixels. Another challenge is that objects of interest are often minuscule (~pixels in extent even for the highest resolution imagery), which complicates traditional computer vision techniques. To address these issues, we propose a pipeline (SIMRDWN) that evaluates satellite images of arbitrarily large size at native resolution at a rate of > 0.2 km2/s. Building upon the tensorflow object detection API paper, this pipeline offers a unified approach to multiple object detection frameworks that can run inference on images of arbitrary size. The SIMRDWN pipeline includes a modified version of YOLO (known as YOLT), along…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsRegion Proposal Network · RoIPool · Softmax · Faster R-CNN · Convolution · Non Maximum Suppression · 1x1 Convolution · Position-Sensitive RoI Pooling · SSD · Region-based Fully Convolutional Network
