Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items
As part of establishing a management system to prevent the illegal transfer of nuclear items, automatic nuclear item detection technology is required during customs clearance. However, it is challenging to acquire X-ray images of major nuclear items (e.g., nuclear fuel and gas centrifuges) loaded in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7537 |
| _version_ | 1827727748166057984 |
|---|---|
| author | Haneol Jang Chansuh Lee Hansol Ko KyungTae Lim |
| author_facet | Haneol Jang Chansuh Lee Hansol Ko KyungTae Lim |
| author_sort | Haneol Jang |
| collection | DOAJ |
| description | As part of establishing a management system to prevent the illegal transfer of nuclear items, automatic nuclear item detection technology is required during customs clearance. However, it is challenging to acquire X-ray images of major nuclear items (e.g., nuclear fuel and gas centrifuges) loaded in cargo with which to train a cargo inspection model. In this work, we propose a new means of data augmentation to alleviate the lack of X-ray training data. The proposed augmentation method generates synthetic X-ray images for the training of semantic segmentation models combining the X-ray images of nuclear items and X-ray cargo background images. To evaluate the effectiveness of the proposed data augmentation technique, we trained representative semantic segmentation models and performed extensive experiments to assess its quantitative and qualitative performance capabilities. Our findings show that multiple item insertions to respond to actual X-ray cargo inspection situations and the resulting occlusion expressions significantly affect the performance of the segmentation models. We believe that this augmentation research will enhance automatic cargo inspections to prevent the illegal transfer of nuclear items at airports and ports. |
| first_indexed | 2024-03-10T23:12:22Z |
| format | Article |
| id | doaj.art-6f440e3abf7c446cac8a19ccee0719ae |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:12:22Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6f440e3abf7c446cac8a19ccee0719ae2023-11-19T08:51:13ZengMDPI AGSensors1424-82202023-08-012317753710.3390/s23177537Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear ItemsHaneol Jang0Chansuh Lee1Hansol Ko2KyungTae Lim3Department of Computer Engineering, Hanbat National University, Daejeon 34158, Republic of KoreaNuclear Export Control Division, Korea Institute of Nuclear Nonproliferation and Control (KINAC), Daejeon 34101, Republic of KoreaNuclear Export Control Division, Korea Institute of Nuclear Nonproliferation and Control (KINAC), Daejeon 34101, Republic of KoreaDepartment of Applied Artificial Intelligence, Seoul National University of Science and Technology, Seoul 01811, Republic of KoreaAs part of establishing a management system to prevent the illegal transfer of nuclear items, automatic nuclear item detection technology is required during customs clearance. However, it is challenging to acquire X-ray images of major nuclear items (e.g., nuclear fuel and gas centrifuges) loaded in cargo with which to train a cargo inspection model. In this work, we propose a new means of data augmentation to alleviate the lack of X-ray training data. The proposed augmentation method generates synthetic X-ray images for the training of semantic segmentation models combining the X-ray images of nuclear items and X-ray cargo background images. To evaluate the effectiveness of the proposed data augmentation technique, we trained representative semantic segmentation models and performed extensive experiments to assess its quantitative and qualitative performance capabilities. Our findings show that multiple item insertions to respond to actual X-ray cargo inspection situations and the resulting occlusion expressions significantly affect the performance of the segmentation models. We believe that this augmentation research will enhance automatic cargo inspections to prevent the illegal transfer of nuclear items at airports and ports.https://www.mdpi.com/1424-8220/23/17/7537data augmentationcargo inspectionsemantic segmentationnuclear itemsdeep neural networks |
| spellingShingle | Haneol Jang Chansuh Lee Hansol Ko KyungTae Lim Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items Sensors data augmentation cargo inspection semantic segmentation nuclear items deep neural networks |
| title | Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items |
| title_full | Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items |
| title_fullStr | Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items |
| title_full_unstemmed | Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items |
| title_short | Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items |
| title_sort | data augmentation of x ray images for automatic cargo inspection of nuclear items |
| topic | data augmentation cargo inspection semantic segmentation nuclear items deep neural networks |
| url | https://www.mdpi.com/1424-8220/23/17/7537 |
| work_keys_str_mv | AT haneoljang dataaugmentationofxrayimagesforautomaticcargoinspectionofnuclearitems AT chansuhlee dataaugmentationofxrayimagesforautomaticcargoinspectionofnuclearitems AT hansolko dataaugmentationofxrayimagesforautomaticcargoinspectionofnuclearitems AT kyungtaelim dataaugmentationofxrayimagesforautomaticcargoinspectionofnuclearitems |