A MACH Filter-Based Reconstruction-Free Target Detector and Tracker for Compressive Sensing Cameras

A MACH Filter-Based Reconstruction-Free Target Detector and Tracker for Compressive Sensing Cameras

Henry Braun (University of Minnesota, USA), Sameeksha Katoch (Arizona State University, USA), Pavan Turaga (Arizona State University, USA), Andreas Spanias (Arizona State University, USA) and Cihan Tepedelenlioglu (Arizona State University, USA)
Copyright: © 2020 |Pages: 21
DOI: 10.4018/IJSST.2020070101
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Compressive sensing cameras hold the promise of cost-effective hardware, lower data rates, and improved video quality, particularly outside the visible spectrum. However, these improvements involve significant computational cost, as sensor output must be reconstructed in order to form an image viewable by a human. This paper describes a prototype automated detection and tracking system using a compressive sensing camera that does not rely on computationally costly image reconstructions. It operates on raw sensor data for an approximately ten-fold improvement in computation time over a comparable reconstruct-then-track algorithm. The detector is successful at a sensing rate of 0.3, comparable to that required for high-quality image reconstructions. If initialized with the location of a target, the tracker holds the target at a sensing rate of 0.005, below the boundary where reconstruction breaks down. These results show not only that direct tracking from compressive cameras is possible, but also give support to the pursuit of direct inference from compressive sensors of all types.
Article Preview
Top

Problem Statement And Background

The authors create a visual tracking system which operates on data from a CS camera with minimal computational requirements, at a reasonably high level of compression (5x compression or 0.2 sensing rate). Current CS image reconstruction methods are too slow to operate in real time hence, attention is focused on bypassing the reconstruction step. This section gives an overview of the compressive sensing problem, followed by a description of prior work in video tracking.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 9: 2 Issues (2022): Forthcoming, Available for Pre-Order
Volume 8: 2 Issues (2021): 1 Released, 1 Forthcoming
Volume 7: 2 Issues (2020)
Volume 6: 2 Issues (2019)
View Complete Journal Contents Listing