A flow-based approach to vehicle detection and background mosaicking in airborne video. - Robotics Institute Carnegie Mellon University

A flow-based approach to vehicle detection and background mosaicking in airborne video.

Hulya Yalcin, Robert Collins, Michael Black, and Martial Hebert
Tech. Report, CMU-RI-TR-05-11, Robotics Institute, Carnegie Mellon University, March, 2005

Abstract

We address the detection of vehicles in a video stream obtained from a moving airborne platform. Our approach is based on robust optical flow algorithm applied on stabilized frames. Stabilization of the frames compensates for gross affine background motion prior to running robust optical flow to compute dense residual flow. Based on the flow and the previous background appearance model, the new frame is separated into background and foreground occlusion layers using an EM-based motion segmentation. The proposed framework shows that ground vehicles can be detected and segmented from airborne video sequences while building a mosaic of the background layer.

BibTeX

@techreport{Yalcin-2005-9134,
author = {Hulya Yalcin and Robert Collins and Michael Black and Martial Hebert},
title = {A flow-based approach to vehicle detection and background mosaicking in airborne video.},
year = {2005},
month = {March},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-05-11},
keywords = {background mosaicking, optical flow, motion estimation, vehicle detection},
}