Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery
Protecting privacy in street view imagery is a critical challenge in urban analytics, requiring comprehensive and scalable solutions beyond localized obfuscation techniques such as face or license plate blurring. To address this, we propose a novel framework that automatically detects and removes se...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iran University of Science and Technology
2025-08-01
|
| Series: | Iranian Journal of Electrical and Electronic Engineering |
| Subjects: | |
| Online Access: | http://ijeee.iust.ac.ir/article-1-3300-en.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849692647872004096 |
|---|---|
| author | Mahdi Khourishandiz Abdollah Amirkhani |
| author_facet | Mahdi Khourishandiz Abdollah Amirkhani |
| author_sort | Mahdi Khourishandiz |
| collection | DOAJ |
| description | Protecting privacy in street view imagery is a critical challenge in urban analytics, requiring comprehensive and scalable solutions beyond localized obfuscation techniques such as face or license plate blurring. To address this, we propose a novel framework that automatically detects and removes sensitive objects, such as pedestrians and vehicles, ensuring robust privacy preservation while maintaining the visual integrity of the images. Our approach integrates semantic segmentation with 2D priors and multimodal data from cameras and LiDAR to achieve precise object detection in complex urban scenes. Detected regions are seamlessly filled using a large-mask inpainting technique based on fast Fourier convolutions (FFC), enabling efficient generalization to high-resolution imagery. Evaluated on the SemanticKITTI dataset, our method achieves a mean Intersection over Union (mIoU) of 64.9%, surpassing state-of-the-art benchmarks. Despite its reliance on accurate sensor calibration and multimodal data availability, the proposed framework offers a scalable solution for privacy-sensitive applications such as urban mapping, and virtual tourism, delivering high-quality anonymized imagery with minimal artifacts. |
| format | Article |
| id | doaj-art-e0f87256c56041f2a0596f1f955f3ec4 |
| institution | DOAJ |
| issn | 1735-2827 2383-3890 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Iran University of Science and Technology |
| record_format | Article |
| series | Iranian Journal of Electrical and Electronic Engineering |
| spelling | doaj-art-e0f87256c56041f2a0596f1f955f3ec42025-08-20T03:20:39ZengIran University of Science and TechnologyIranian Journal of Electrical and Electronic Engineering1735-28272383-38902025-08-0121333003300Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View ImageryMahdi Khourishandiz0Abdollah Amirkhani1 School of Automotive Engineering, Iran University of Science and Technology (IUST), Tehran 16846-13114, Iran. School of Automotive Engineering, Iran University of Science and Technology (IUST), Tehran 16846-13114, Iran. Protecting privacy in street view imagery is a critical challenge in urban analytics, requiring comprehensive and scalable solutions beyond localized obfuscation techniques such as face or license plate blurring. To address this, we propose a novel framework that automatically detects and removes sensitive objects, such as pedestrians and vehicles, ensuring robust privacy preservation while maintaining the visual integrity of the images. Our approach integrates semantic segmentation with 2D priors and multimodal data from cameras and LiDAR to achieve precise object detection in complex urban scenes. Detected regions are seamlessly filled using a large-mask inpainting technique based on fast Fourier convolutions (FFC), enabling efficient generalization to high-resolution imagery. Evaluated on the SemanticKITTI dataset, our method achieves a mean Intersection over Union (mIoU) of 64.9%, surpassing state-of-the-art benchmarks. Despite its reliance on accurate sensor calibration and multimodal data availability, the proposed framework offers a scalable solution for privacy-sensitive applications such as urban mapping, and virtual tourism, delivering high-quality anonymized imagery with minimal artifacts.http://ijeee.iust.ac.ir/article-1-3300-en.pdfprivacy protectionstreet view imagerylarge mask inpaintingsemantic segmentationmulti-modalitylidar. |
| spellingShingle | Mahdi Khourishandiz Abdollah Amirkhani Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery Iranian Journal of Electrical and Electronic Engineering privacy protection street view imagery large mask inpainting semantic segmentation multi-modality lidar. |
| title | Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery |
| title_full | Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery |
| title_fullStr | Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery |
| title_full_unstemmed | Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery |
| title_short | Enhancing Privacy by Large Mask Inpainting and Fusion-Based Segmentation in Street View Imagery |
| title_sort | enhancing privacy by large mask inpainting and fusion based segmentation in street view imagery |
| topic | privacy protection street view imagery large mask inpainting semantic segmentation multi-modality lidar. |
| url | http://ijeee.iust.ac.ir/article-1-3300-en.pdf |
| work_keys_str_mv | AT mahdikhourishandiz enhancingprivacybylargemaskinpaintingandfusionbasedsegmentationinstreetviewimagery AT abdollahamirkhani enhancingprivacybylargemaskinpaintingandfusionbasedsegmentationinstreetviewimagery |