Bayesian Constrained Energy Minimization for Hyperspectral Target Detection
For better performance of hyperspectral target detectors, the prior target spectrum is expected to be accurate and consistent with the target spectrum in the hyperspectral image to be detected. The existing hyperspectral target detection algorithms usually assume that the prior target spectrum is hi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9514466/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554125850935296 |
|---|---|
| author | Jing Zhang Rui Zhao Zhenwei Shi Ning Zhang Xinzhong Zhu |
| author_facet | Jing Zhang Rui Zhao Zhenwei Shi Ning Zhang Xinzhong Zhu |
| author_sort | Jing Zhang |
| collection | DOAJ |
| description | For better performance of hyperspectral target detectors, the prior target spectrum is expected to be accurate and consistent with the target spectrum in the hyperspectral image to be detected. The existing hyperspectral target detection algorithms usually assume that the prior target spectrum is highly reliable. However, the label obtained is not always precise in practice, and pixels of the same object may have quite different spectra. Since it is hard to acquire a highly reliable prior target spectrum in some application scenarios, we propose a Bayesian constrained energy minimization (B-CEM) method for hyperspectral target detection. Instead of the point estimation of the target spectrum, we infer the posterior distribution of the true target spectrum based on the prior target spectrum. Specifically, considering the characteristics of hyperspectral image and target detection task, we adopt the Dirichlet distribution to approximate the true target spectrum. Experimental results on three datasets demonstrate the effectiveness of the proposed B-CEM when the known target spectrum is noisy or inconsistent with the true target spectrum. The necessity to approximate the true target spectrum is also proved. Generally, the distributional estimate achieves better performance than using the known target spectrum directly. |
| format | Article |
| id | doaj-art-d683639a99cd4b52b08508f7b97b5b47 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-d683639a99cd4b52b08508f7b97b5b472025-01-09T00:00:19ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352021-01-01148359837210.1109/JSTARS.2021.31049089514466Bayesian Constrained Energy Minimization for Hyperspectral Target DetectionJing Zhang0https://orcid.org/0000-0002-9145-6905Rui Zhao1https://orcid.org/0000-0003-4271-0206Zhenwei Shi2https://orcid.org/0000-0002-4772-3172Ning Zhang3Xinzhong Zhu4Image Processing Center, School of Astronautics, Beihang University, Beijing, ChinaImage Processing Center, School of Astronautics, Beihang University, Beijing, ChinaImage Processing Center, School of Astronautics, Beihang University, Beijing, ChinaShanghai Aerospace Electronic Technology Institute, Shanghai, ChinaShanghai Aerospace Electronic Technology Institute, Shanghai, ChinaFor better performance of hyperspectral target detectors, the prior target spectrum is expected to be accurate and consistent with the target spectrum in the hyperspectral image to be detected. The existing hyperspectral target detection algorithms usually assume that the prior target spectrum is highly reliable. However, the label obtained is not always precise in practice, and pixels of the same object may have quite different spectra. Since it is hard to acquire a highly reliable prior target spectrum in some application scenarios, we propose a Bayesian constrained energy minimization (B-CEM) method for hyperspectral target detection. Instead of the point estimation of the target spectrum, we infer the posterior distribution of the true target spectrum based on the prior target spectrum. Specifically, considering the characteristics of hyperspectral image and target detection task, we adopt the Dirichlet distribution to approximate the true target spectrum. Experimental results on three datasets demonstrate the effectiveness of the proposed B-CEM when the known target spectrum is noisy or inconsistent with the true target spectrum. The necessity to approximate the true target spectrum is also proved. Generally, the distributional estimate achieves better performance than using the known target spectrum directly.https://ieeexplore.ieee.org/document/9514466/Bayesiandistributional estimatehyperspectral target detection (HTD) |
| spellingShingle | Jing Zhang Rui Zhao Zhenwei Shi Ning Zhang Xinzhong Zhu Bayesian Constrained Energy Minimization for Hyperspectral Target Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Bayesian distributional estimate hyperspectral target detection (HTD) |
| title | Bayesian Constrained Energy Minimization for Hyperspectral Target Detection |
| title_full | Bayesian Constrained Energy Minimization for Hyperspectral Target Detection |
| title_fullStr | Bayesian Constrained Energy Minimization for Hyperspectral Target Detection |
| title_full_unstemmed | Bayesian Constrained Energy Minimization for Hyperspectral Target Detection |
| title_short | Bayesian Constrained Energy Minimization for Hyperspectral Target Detection |
| title_sort | bayesian constrained energy minimization for hyperspectral target detection |
| topic | Bayesian distributional estimate hyperspectral target detection (HTD) |
| url | https://ieeexplore.ieee.org/document/9514466/ |
| work_keys_str_mv | AT jingzhang bayesianconstrainedenergyminimizationforhyperspectraltargetdetection AT ruizhao bayesianconstrainedenergyminimizationforhyperspectraltargetdetection AT zhenweishi bayesianconstrainedenergyminimizationforhyperspectraltargetdetection AT ningzhang bayesianconstrainedenergyminimizationforhyperspectraltargetdetection AT xinzhongzhu bayesianconstrainedenergyminimizationforhyperspectraltargetdetection |