Skip to main navigation Skip to search Skip to main content

A weight SAE based hyperspectral image anomaly targets detection

  • Ning Ma
  • , Yu Peng
  • , Shaojun Wang*
  • , Wei Gao
  • *Corresponding author for this work
  • Harbin Institute of Technology

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

Abstract

Due to less limitation, hyperspectral image(HSI) anomaly detection(AD) is widely applied in agriculture, environment and military applications. However, the assumption requirement of special distribution in background makes traditional HSI AD acts poor when the assumption cannot fit in the real HSI. On the other hand, the model of local anomaly detection methods is susceptible to its neighbor anomaly pixels. In this work, we propose a weight sparse auto-encode (SAE) based anomaly targets detection method which combines the weight of neighbor pixel with distance discriminate algorithm. With the ability of high level feature learning in unsupervised way, a sparse code of HSI can be given by SAE for anomaly detection. This method can improve the accuracy of HSI anomaly detection by reducing the risk of anomaly contaminating through allocating different contribution to local pixels. Experimental results based on San Diego airport HSI dataset show that the performance can be ameliorated by the proposed method.

Original languageEnglish
Title of host publicationICEMI 2017 - Proceedings of IEEE 13th International Conference on Electronic Measurement and Instruments
EditorsWu Juan, Yin Jiali, Zhang Qi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages511-515
Number of pages5
ISBN (Electronic)9781509050345
DOIs
StatePublished - 2 Jul 2017
Event13th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2017 - Yangzhou, China
Duration: 20 Oct 201722 Oct 2017

Publication series

NameICEMI 2017 - Proceedings of IEEE 13th International Conference on Electronic Measurement and Instruments
Volume2018-January

Conference

Conference13th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2017
Country/TerritoryChina
CityYangzhou
Period20/10/1722/10/17

Keywords

  • Anomaly targets detection
  • Hyperspectral image
  • Sparse Auto-Encode

Fingerprint

Dive into the research topics of 'A weight SAE based hyperspectral image anomaly targets detection'. Together they form a unique fingerprint.

Cite this