Experimental evaluation of neural, statistical and model-based approaches to FLIR ATR

Baoxin Li, Qinfen Zheng, Sandor Der, Rama Chellappa, Nasser M. Nasrabadi, Lipchen A. Chan, LinCheng C. Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations


This paper presents an empirical evaluation of a number of recently developed Automatic Target Recognition Algorithms for Forward-Looking InfraRed(FLIR) imagery using a large database of real second-generation FLIR images. The algorithms evaluated are based on convolution neural networks (CNN), principal component analysis (PCA), linear discriminant analysis (LDA), learning vector quantization (LVQ), and modular neural networks (MNN). Two model-based algorithms, using Hausdorff metric based matching and geometric hashing, are also evaluated. A hierarchical pose estimation system using CNN plus either PCA or LDA, developed by the authors, is also evaluated using the same data set.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsF.A. Sadjadi
Number of pages10
StatePublished - 1998
Externally publishedYes
EventAutomatic Target Recognition VIII - Orlando, FL, United States
Duration: Apr 13 1998Apr 17 1998


OtherAutomatic Target Recognition VIII
Country/TerritoryUnited States
CityOrlando, FL


  • Automatic target recognition
  • Performance evaluation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics


Dive into the research topics of 'Experimental evaluation of neural, statistical and model-based approaches to FLIR ATR'. Together they form a unique fingerprint.

Cite this