Tradeoffs between quality of results and resource consumption in a recognition system

M. DeVore, R. Chamberlain, G. Engel, J. O'Sullivan, M. Franklin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The implementation of computational systems to perform challenging operations often involves balancing the performance specification, system throughput, and available system resources. For problems of automatic target recognition (ATR), these three quantities of interest are the probability of classification error, the rate at which regions of interest are processed, and the capabilities of the underlying hardware (which is a function of the available computational resources and available power). An understanding of the inter-relationships between these factors can be an aid in making informed choices while exploring competing design possibilities. Combining characterizations of ATR performance, which yield probability of classification error as a function of target model complexity, with analytical models of computational performance, which yield throughput as a function of target model complexity and available resources, we can form a set of parametric curves which relate the quality of the results to the resources consumed.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Application-Specific Systems, Architectures, and Processors, ASAP 2002
EditorsMichael Schulte, Shuvra Bhattacharyya, Neil Burgess, Robert Schreiber
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages391-402
Number of pages12
ISBN (Electronic)0769517129
DOIs
StatePublished - 2002
EventIEEE International Conference on Application-Specific Systems, Architectures, and Processors, ASAP 2002 - San Jose, United States
Duration: Jul 17 2002Jul 19 2002

Publication series

NameProceedings of the International Conference on Application-Specific Systems, Architectures and Processors
Volume2002-January
ISSN (Print)2160-0511
ISSN (Electronic)2160-052X

Conference

ConferenceIEEE International Conference on Application-Specific Systems, Architectures, and Processors, ASAP 2002
Country/TerritoryUnited States
CitySan Jose
Period07/17/0207/19/02

Keywords

  • Analytical models
  • Computer errors
  • Energy consumption
  • Error analysis
  • Hardware
  • Layout
  • Power system modeling
  • Synthetic aperture radar
  • Target recognition
  • Throughput

Fingerprint

Dive into the research topics of 'Tradeoffs between quality of results and resource consumption in a recognition system'. Together they form a unique fingerprint.

Cite this