Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet
Change detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. T...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/19/3559 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850284404994211840 |
|---|---|
| author | Min Yang Jie Yang Hongxia Mao Chong Zheng |
| author_facet | Min Yang Jie Yang Hongxia Mao Chong Zheng |
| author_sort | Min Yang |
| collection | DOAJ |
| description | Change detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. To solve these problems, an image change detection approach that combines infrared polarization imaging with a fast principal component analysis network (Fast-PCANet) is proposed. Firstly, the acquired infrared polarization images are analyzed, and pixel image blocks are extracted and filtered to obtain the candidate change points. Then, the Fast-PCANet network framework is established, and the candidate pixel image blocks are sent to the network to detect the change pixel points. Finally, the false-detection points predicted by the Fast-PCANet are further corrected by region filling and filtering to obtain the final binary change map of the damage scene. Comparisons with typical PCANet-based change detection algorithms are made on a dataset of infrared-polarized images. The experimental results show that the proposed Fast-PCANet method improves the <i>PCC</i> and the <i>Kappa</i> coefficient of infrared polarization images over infrared intensity images by 6.77% and 13.67%, respectively. Meanwhile, the inference speed can be more than seven times faster. The results verify that the proposed approach is effective and efficient for the change detection task with infrared polarization imaging. The study can be applied to the damage assessment field and has great potential for object recognition, material classification, and polarization remote sensing. |
| format | Article |
| id | doaj-art-c162d34a780348b894167261ccc38be1 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-c162d34a780348b894167261ccc38be12025-08-20T01:47:34ZengMDPI AGRemote Sensing2072-42922024-09-011619355910.3390/rs16193559Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANetMin Yang0Jie Yang1Hongxia Mao2Chong Zheng3National Key Laboratory of Scattering and Radiation, Beijing 100854, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing 100091, ChinaNational Key Laboratory of Scattering and Radiation, Beijing 100854, ChinaNational Key Laboratory of Scattering and Radiation, Beijing 100854, ChinaChange detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. To solve these problems, an image change detection approach that combines infrared polarization imaging with a fast principal component analysis network (Fast-PCANet) is proposed. Firstly, the acquired infrared polarization images are analyzed, and pixel image blocks are extracted and filtered to obtain the candidate change points. Then, the Fast-PCANet network framework is established, and the candidate pixel image blocks are sent to the network to detect the change pixel points. Finally, the false-detection points predicted by the Fast-PCANet are further corrected by region filling and filtering to obtain the final binary change map of the damage scene. Comparisons with typical PCANet-based change detection algorithms are made on a dataset of infrared-polarized images. The experimental results show that the proposed Fast-PCANet method improves the <i>PCC</i> and the <i>Kappa</i> coefficient of infrared polarization images over infrared intensity images by 6.77% and 13.67%, respectively. Meanwhile, the inference speed can be more than seven times faster. The results verify that the proposed approach is effective and efficient for the change detection task with infrared polarization imaging. The study can be applied to the damage assessment field and has great potential for object recognition, material classification, and polarization remote sensing.https://www.mdpi.com/2072-4292/16/19/3559infrared polarization imagingFast-PCANetdamage scenechange detection |
| spellingShingle | Min Yang Jie Yang Hongxia Mao Chong Zheng Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet Remote Sensing infrared polarization imaging Fast-PCANet damage scene change detection |
| title | Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet |
| title_full | Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet |
| title_fullStr | Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet |
| title_full_unstemmed | Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet |
| title_short | Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet |
| title_sort | damage scene change detection based on infrared polarization imaging and fast pcanet |
| topic | infrared polarization imaging Fast-PCANet damage scene change detection |
| url | https://www.mdpi.com/2072-4292/16/19/3559 |
| work_keys_str_mv | AT minyang damagescenechangedetectionbasedoninfraredpolarizationimagingandfastpcanet AT jieyang damagescenechangedetectionbasedoninfraredpolarizationimagingandfastpcanet AT hongxiamao damagescenechangedetectionbasedoninfraredpolarizationimagingandfastpcanet AT chongzheng damagescenechangedetectionbasedoninfraredpolarizationimagingandfastpcanet |