A Digitally Interfaced Analog Correlation Filter System for Object Tracking Applications
Abstract
This study reports a 24×57 correlation filter system for object tracking applications. While digital interfacing of the input and output data enabled a standard and flexible way of communication with pre- and post-processing digital blocks, the multiply-accumulate (MAC) operations were performed in the analog domain to save power and area. The proposed system utilizes non-volatile floating-gate memories to store filter coefficients. The chip was fabricated in a 0.13- μm CMOS process and occupies 3.23 mm 2 of silicon area. The system dissipates 388.4 μW of power at a throughput of 11.3 kVec/s, achieving an energy efficiency of 25.2 pJ/MAC. Finally, experimental results for a custom filter designed to detect vehicles are presented.
- Authors:
-
- Univ. of Tennessee, Knoxville, TN (United States)
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Univ. of Tennessee, Knoxville, TN (United States); Univ. of North Carolina, Charlotte, NC (United States)
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Tennessee, Knoxville, TN (United States)
- Sponsoring Org.:
- USDOE; Defense Advanced Research Projects Agency (DARPA) (United States)
- OSTI Identifier:
- 1464004
- Grant/Contract Number:
- AC05-00OR22725; HR0011-13-2-0016
- Resource Type:
- Journal Article: Accepted Manuscript
- Journal Name:
- IEEE Transactions on Circuits and Systems I: Regular Papers
- Additional Journal Information:
- Journal Volume: 65; Journal Issue: 9; Journal ID: ISSN 1549-8328
- Publisher:
- IEEE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; analog signal processing; analog computing; correlation filter; floating-gate memory; digital interface; object tracking
Citation Formats
Judy, Mohsen, Poore, Nicholas Conley, Liu, Peixing, Yang, Tan, Britton, Charles, Bolme, David S., Mikkilineni, Aravind K., and Holleman, Jeremy. A Digitally Interfaced Analog Correlation Filter System for Object Tracking Applications. United States: N. p., 2018.
Web. doi:10.1109/TCSI.2018.2819962.
Judy, Mohsen, Poore, Nicholas Conley, Liu, Peixing, Yang, Tan, Britton, Charles, Bolme, David S., Mikkilineni, Aravind K., & Holleman, Jeremy. A Digitally Interfaced Analog Correlation Filter System for Object Tracking Applications. United States. https://doi.org/10.1109/TCSI.2018.2819962
Judy, Mohsen, Poore, Nicholas Conley, Liu, Peixing, Yang, Tan, Britton, Charles, Bolme, David S., Mikkilineni, Aravind K., and Holleman, Jeremy. 2018.
"A Digitally Interfaced Analog Correlation Filter System for Object Tracking Applications". United States. https://doi.org/10.1109/TCSI.2018.2819962. https://www.osti.gov/servlets/purl/1464004.
@article{osti_1464004,
title = {A Digitally Interfaced Analog Correlation Filter System for Object Tracking Applications},
author = {Judy, Mohsen and Poore, Nicholas Conley and Liu, Peixing and Yang, Tan and Britton, Charles and Bolme, David S. and Mikkilineni, Aravind K. and Holleman, Jeremy},
abstractNote = {This study reports a 24×57 correlation filter system for object tracking applications. While digital interfacing of the input and output data enabled a standard and flexible way of communication with pre- and post-processing digital blocks, the multiply-accumulate (MAC) operations were performed in the analog domain to save power and area. The proposed system utilizes non-volatile floating-gate memories to store filter coefficients. The chip was fabricated in a 0.13- μm CMOS process and occupies 3.23 mm 2 of silicon area. The system dissipates 388.4 μW of power at a throughput of 11.3 kVec/s, achieving an energy efficiency of 25.2 pJ/MAC. Finally, experimental results for a custom filter designed to detect vehicles are presented.},
doi = {10.1109/TCSI.2018.2819962},
url = {https://www.osti.gov/biblio/1464004},
journal = {IEEE Transactions on Circuits and Systems I: Regular Papers},
issn = {1549-8328},
number = 9,
volume = 65,
place = {United States},
year = {Wed Apr 11 00:00:00 EDT 2018},
month = {Wed Apr 11 00:00:00 EDT 2018}
}
Web of Science