13 October 2014 Detection of people in military and security context imagery
Author Affiliations +
Abstract
A high level of manual visual surveillance of complex scenes is dependent solely on the awareness of human operators whereas an autonomous person detection solution could assist by drawing their attention to potential issues, in order to reduce cognitive burden and achieve more with less manpower. Our research addressed the challenge of the reliable identification of persons in a scene who may be partially obscured by structures or by handling weapons or tools. We tested the efficacy of a recently published computer vision approach based on the construction of cascaded, non-linear classifiers from part-based deformable models by assessing performance using imagery containing infantrymen in the open or when obscured, undertaking low level tactics or acting as civilians using tools. Results were compared with those obtained from published upright pedestrian imagery. The person detector yielded a precision of approximately 65% for a recall rate of 85% for military context imagery as opposed to a precision of 85% for the upright pedestrian image cases. These results compared favorably with those reported by the authors when applied to a range of other on-line imagery databases. Our conclusion is that the deformable part-based model method may be a potentially useful people detection tool in the challenging environment of military and security context imagery.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Thomas M. L. Shannon, Emmet H. Spier, Ben Wiltshire, "Detection of people in military and security context imagery", Proc. SPIE 9250, Electro-Optical Remote Sensing, Photonic Technologies, and Applications VIII; and Military Applications in Hyperspectral Imaging and High Spatial Resolution Sensing II, 92500K (13 October 2014); doi: 10.1117/12.2071902; https://doi.org/10.1117/12.2071902
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT

Image classification based on region of interest detection
Proceedings of SPIE (December 14 2015)
Matching 3D segmented objects using wire frame analysis
Proceedings of SPIE (August 06 1993)
Database representation for scene simulation
Proceedings of SPIE (April 13 1993)
Hand gesture recognition by analysis of codons
Proceedings of SPIE (September 10 2007)
Refinding objects using model-based knowledge
Proceedings of SPIE (October 05 2001)

Back to Top