DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Multi-frame moving object detection system

Abstract

A plurality of remote sensing images of a scene are received. A potential target object can be identified in one of the images, wherein the target object has a low signal-to-noise ratio (SNR). A candidate motion path of the target object can be generated based upon the images. A predicted position of the target object along the candidate motion path is determined for each of the remote sensing images. An image chip is extracted from each of the images, where each image chip is centered about the predicted position of the target object in its corresponding image. A sum image chip is generated based upon the image chips. An indication that the potential target object is an actual object in the images is output based upon a value of a center pixel of the sum image chip.

Inventors:
;
Issue Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1860126
Patent Number(s):
11188750
Application Number:
16/867,314
Assignee:
National Technology & Engineering Solutions of Sandia, LLC (Albuquerque, NM)
DOE Contract Number:  
NA0003525
Resource Type:
Patent
Resource Relation:
Patent File Date: 05/05/2020
Country of Publication:
United States
Language:
English

Citation Formats

Ma, Tian J., and Anderson, Robert J. Multi-frame moving object detection system. United States: N. p., 2021. Web.
Ma, Tian J., & Anderson, Robert J. Multi-frame moving object detection system. United States.
Ma, Tian J., and Anderson, Robert J. Tue . "Multi-frame moving object detection system". United States. https://www.osti.gov/servlets/purl/1860126.
@article{osti_1860126,
title = {Multi-frame moving object detection system},
author = {Ma, Tian J. and Anderson, Robert J.},
abstractNote = {A plurality of remote sensing images of a scene are received. A potential target object can be identified in one of the images, wherein the target object has a low signal-to-noise ratio (SNR). A candidate motion path of the target object can be generated based upon the images. A predicted position of the target object along the candidate motion path is determined for each of the remote sensing images. An image chip is extracted from each of the images, where each image chip is centered about the predicted position of the target object in its corresponding image. A sum image chip is generated based upon the image chips. An indication that the potential target object is an actual object in the images is output based upon a value of a center pixel of the sum image chip.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Nov 30 00:00:00 EST 2021},
month = {Tue Nov 30 00:00:00 EST 2021}
}

Works referenced in this record:

Noise Reduction in Radiation Image
patent-application, August 2017


Method and System for Generating Multidimensional Maps of a Scene Using a Plurality of Sensors of Various Types
patent-application, August 2018


Multitarget particle filter track before detect application
journal, January 2004


Refined PHD Filter for Multi-Target Tracking under Low Detection Probability
journal, June 2019


Detecting and tracking low-observable targets using IR
conference, October 1990


Peformance of dynamic programming techniques for Track-Before-Detect
journal, January 1996


A recursive moving-target-indication algorithm for optical image sequences
journal, May 1990

  • Reed, I. S.; Gagliardi, R. M.; Stotts, L. B.
  • IEEE Transactions on Aerospace and Electronic Systems, Vol. 26, Issue 3, p. 434-440
  • https://doi.org/10.1109/7.106120

Artefact Detection and Correction
patent-application, June 2017


A Novel Dynamic Programming Algorithm for Track-Before-Detect in Radar Systems
journal, May 2013


Video Surveillance System
patent-application, August 2011


Multiple hypothesis tracking for multiple target tracking
journal, January 2004