Classifying objects in LWIR imagery via CNNs

Iain Rodger, Barry Connor, Neil M. Robertson

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

12 Citations (Scopus)
2065 Downloads (Pure)

Abstract

The aim of the presented work is to demonstrate enhanced target recognition and improved false alarm rates for a mid to long range detection system, utilising a Long Wave Infrared (LWIR) sensor. By exploiting high quality thermal image data and recent techniques in machine learning, the system can provide automatic target recognition capabilities. A Convolutional Neural Network (CNN) is trained and the classifier achieves an overall accuracy of > 95% for 6 object classes related to land defence. While the highly accurate CNN struggles to recognise long range target classes, due to low signal quality, robust target discrimination is achieved for challenging candidates. The overall performance of the methodology presented is assessed using human ground truth information, generating classifier evaluation metrics for thermal image sequences.
Original languageEnglish
Title of host publicationProc. SPIE: Electro-Optical and Infrared Systems: Technology and Applications XIII
Pages99870-99884
Number of pages14
Volume9987
DOIs
Publication statusPublished - 21 Oct 2016

Bibliographical note

Winner of Best Student Paper prize

Fingerprint Dive into the research topics of 'Classifying objects in LWIR imagery via CNNs'. Together they form a unique fingerprint.

  • Cite this

    Rodger, I., Connor, B., & Robertson, N. M. (2016). Classifying objects in LWIR imagery via CNNs. In Proc. SPIE: Electro-Optical and Infrared Systems: Technology and Applications XIII (Vol. 9987, pp. 99870-99884) https://doi.org/10.1117/12.2241858