Share Email Print

Journal of Applied Remote Sensing • Open Access • new

Rapid broad area search and detection of Chinese surface-to-air missile sites using deep convolutional neural networks
Author(s): Richard A. Marcum; Curt H. Davis; Grant J. Scott; Tyler W. Nivin

Paper Abstract

We evaluated how deep convolutional neural networks (DCNN) could assist in the labor-intensive process of human visual searches for objects of interest in high-resolution imagery over large areas of the Earth’s surface. Various DCNN were trained and tested using fewer than 100 positive training examples (China only) from a worldwide surface-to-air-missile (SAM) site dataset. A ResNet-101 DCNN achieved a 98.2% average accuracy for the China SAM site data. The ResNet-101 DCNN was used to process ∼19.6  M image chips over a large study area in southeastern China. DCNN chip detections (∼9300) were postprocessed with a spatial clustering algorithm to produce a ranked list of ∼2100 candidate SAM site locations. The combination of DCNN processing and spatial clustering effectively reduced the search area by ∼660X (0.15% of the DCNN-processed land area). An efficient web interface was used to facilitate a rapid serial human review of the candidate SAM sites in the China study area. Four novice imagery analysts with no prior imagery analysis experience were able to complete a DCNN-assisted SAM site search in an average time of ∼42  min. This search was ∼81X faster than a traditional visual search over an equivalent land area of ∼88,640  km2 while achieving nearly identical statistical accuracy (∼90% F1).

Paper Details

Date Published: 6 October 2017
PDF: 31 pages
J. Appl. Rem. Sens. 11(4) 042614 doi: 10.1117/1.JRS.11.042614
Published in: Journal of Applied Remote Sensing Volume 11, Issue 4
Show Author Affiliations
Richard A. Marcum, Univ. of Missouri (United States)
Curt H. Davis, Univ. of Missouri (United States)
Grant J. Scott, Univ. of Missouri (United States)
Tyler W. Nivin, Univ. of Missouri (United States)

© SPIE. Terms of Use
Back to Top