High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement
Misusing image tampering software makes it easier to manipulate satellite images, leading to a crisis of trust and security concerns in society. This study compares the inconsistencies between heterogeneous images to locate tampered areas and proposes a high-precision heterogeneous satellite image m...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/19/3719 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850284236165087232 |
|---|---|
| author | Ruijie Wu Wei Guo Yi Liu Chenhao Sun |
| author_facet | Ruijie Wu Wei Guo Yi Liu Chenhao Sun |
| author_sort | Ruijie Wu |
| collection | DOAJ |
| description | Misusing image tampering software makes it easier to manipulate satellite images, leading to a crisis of trust and security concerns in society. This study compares the inconsistencies between heterogeneous images to locate tampered areas and proposes a high-precision heterogeneous satellite image manipulation localization (HSIML) framework to distinguish tampered from real landcover changes, such as artificial constructions, and pseudo-changes, such as seasonal variations. The model operates at the patch level and comprises three modules: The heterogeneous image preprocessing module aligns heterogeneous images and filters noisy data. The feature point constraint module mitigates the effects of lighting and seasonal variations in the images by performing feature point matching, applying filtering rules to conduct an initial screening to identify candidate tampered patches. The semantic similarity measurement module designs a classification network to assess RS image feature saliency. It determines image consistency based on the similarity of semantic features and implements IML using predefined classification rules. Additionally, a dataset for IML is constructed based on satellite images. Extensive experiments compared with existing SOTA models demonstrate that our method achieved the highest F1 score in both localization accuracy and robustness tests and demonstrates the capability for handling large-scale areas. |
| format | Article |
| id | doaj-art-c6458ecbcc1d41ea8d82d125ef2f10b6 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-c6458ecbcc1d41ea8d82d125ef2f10b62025-08-20T01:47:37ZengMDPI AGRemote Sensing2072-42922024-10-011619371910.3390/rs16193719High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity MeasurementRuijie Wu0Wei Guo1Yi Liu2Chenhao Sun3State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaMisusing image tampering software makes it easier to manipulate satellite images, leading to a crisis of trust and security concerns in society. This study compares the inconsistencies between heterogeneous images to locate tampered areas and proposes a high-precision heterogeneous satellite image manipulation localization (HSIML) framework to distinguish tampered from real landcover changes, such as artificial constructions, and pseudo-changes, such as seasonal variations. The model operates at the patch level and comprises three modules: The heterogeneous image preprocessing module aligns heterogeneous images and filters noisy data. The feature point constraint module mitigates the effects of lighting and seasonal variations in the images by performing feature point matching, applying filtering rules to conduct an initial screening to identify candidate tampered patches. The semantic similarity measurement module designs a classification network to assess RS image feature saliency. It determines image consistency based on the similarity of semantic features and implements IML using predefined classification rules. Additionally, a dataset for IML is constructed based on satellite images. Extensive experiments compared with existing SOTA models demonstrate that our method achieved the highest F1 score in both localization accuracy and robustness tests and demonstrates the capability for handling large-scale areas.https://www.mdpi.com/2072-4292/16/19/3719image manipulation localizationchange detectionheterogeneous satellite imagesfeature point |
| spellingShingle | Ruijie Wu Wei Guo Yi Liu Chenhao Sun High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement Remote Sensing image manipulation localization change detection heterogeneous satellite images feature point |
| title | High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement |
| title_full | High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement |
| title_fullStr | High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement |
| title_full_unstemmed | High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement |
| title_short | High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement |
| title_sort | high precision heterogeneous satellite image manipulation localization feature point rules and semantic similarity measurement |
| topic | image manipulation localization change detection heterogeneous satellite images feature point |
| url | https://www.mdpi.com/2072-4292/16/19/3719 |
| work_keys_str_mv | AT ruijiewu highprecisionheterogeneoussatelliteimagemanipulationlocalizationfeaturepointrulesandsemanticsimilaritymeasurement AT weiguo highprecisionheterogeneoussatelliteimagemanipulationlocalizationfeaturepointrulesandsemanticsimilaritymeasurement AT yiliu highprecisionheterogeneoussatelliteimagemanipulationlocalizationfeaturepointrulesandsemanticsimilaritymeasurement AT chenhaosun highprecisionheterogeneoussatelliteimagemanipulationlocalizationfeaturepointrulesandsemanticsimilaritymeasurement |