익명화 내재 원본 디지털 이미지를 출력하는 프라이버시 카메라
Privacy Camera: Outputting Original Digital Images without Privacy Leaks
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
비디오 센서 기술은 CCTV, 디지털카메라, 자동차와 같은 여러 분야에서 사용되며, 우리의 일상생활과 밀접한 관계를 맺고 있다. 이와 같이 비디오 센서를 통해 촬영된 이미지 및 비디오에는 프라이버시 유출 가능성이 존재하며, 기존에는 이를 해결하기 위해 원본 이미지가 생성된 후에 프라이버시 보호를 위한 후처리 작업을 하였다. 따라서, 본 논문에서는 원본 이미지가 출력되기 전에 프라이버시 침해 요소를 제거하여 익명화가 내재된 이미지 및 비디오를 출력하는 프라이버시 카메라 개념을 제안한다. 프라이버시 카메라를 통해 다양한 상황에서도 프라이버시 침해 요소가 효과적으로 제거됨을 보여준다. 또한, 프라이버시 카메라로부터 출력된 이미지에 대한 객체 탐지 및 사람 자세 추정 실험을 통해, 객체 익명화 내재 원본 데이터의 활용 가능성을 검증한다.
Abstract
Video sensor technology is used in various fields such as CCTV, digital cameras, and automobiles, and it is closely related to our daily lives. Images and videos captured through such video sensors carry the potential risk of privacy leakage, and traditionally, post-processing for privacy protection was performed after the original image was generated. Therefore, in this paper, we propose the concept of a privacy camera that outputs images and videos with anonymization applied by removing privacy-invasive elements before the original image is outputted. We demonstrate that the privacy camera effectively removes privacy elements even in various situations. Furthermore, through object detection and human pose estimation experiments on the images output by the privacy camera, the potential for utilizing anonymized original data is verified.
참고문헌 (30)
- "Status of the CMOS Image Sensor Industry 2024" (2024)[URL]
- Z. Zou, "Object Detection in 20 Years : A Survey", Proceedings of the IEEE, 111(3), pp.257~276 (2023)
- Ce Zheng, "Deep Learning-based Human Pose Estimation: A Survey", ACM Comput. Surv, 56(1) (2023)
- R. Kumar, "A survey on intelligent human action recognition techniques", Multimedia Tools and Applications, 83(17), pp.52653~52709 (2024)
- Gil-Jae Lee, "Trends in the Use of Artificial Intelligence in Medical Image Analysis", Journal of the Korean Society of Radiology, 16(4), pp.453~462 (2022)
- Xin Li, "Role of Artificial Intelligence in Medical Image Analysis : A Review of Current Trends and Future Directions", Journal of Medical and Biological Engineering, 44(2), pp.231~243 (2024)
- S. Zou, "Traffic Flow Video Image Recognition and Analysis Based on Multi-Target Tracking Algorithm and Deep Learning", IEEE Transactions on Intelligent Transportation Systems, 24(8), pp.8762~8775 (2023)
- "Number of Reports and Consultations on Infringement of Personal Information" (2024)[URL]
- Jeremiah, Sekione Reward, "CCTV Footage De-identification for Privacy Protection: A Comprehensive Survey", Journal of Internet Technology, 25(3), pp.379~386 (2024)
- Kim, Do-Eun, "Development of Intelligent CCTV System Using CNN Technology", The Journal of the Institute of Internet, Broadcasting and Communication, 23(4), pp.99~105 (2023)
- K. N. K. Kumar, "Motion activated security camera using raspberry Pi", 2017International Conference on Communication and Signal Processing (ICCSP), pp.1598~1601 (2017)
- Huu-Quoc Nguyen, "Low cost real-time system monitoring using Raspberry Pi", 2015Seventh International Conference on Ubiquitous and Future Networks, pp.857~859 (2015)
- You Only Look Once: Unified, Real-Time Object Detection, "Joseph Redmon", ~ (2016)
- Zhe Cao, "OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields", IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)
- T. Suzuki, "Challenges of image-sensor development", 2010IEEE International Solid-State Circuits Conference - (ISSCC), pp.27~30 (2010)
- A. Luštica, "CCD and CMOS image sensors in new HD cameras", Proceedings ELMAR-2011, pp.133~136 (2011)
- S. Mehta, "CCD or CMOS Image sensor for photography", 2015 International Conference on Communications and Signal Processing(ICCSP), pp.0291~0294 (2015)
- M. El-Desouki, "CMOS Image Sensors for High Speed Applications", Sensors, 9(1) (2009)
- S.S.A. Zaidi, "A Survey of Modern Deep Learning based Object Detection Models", Digital Signal Processing, 126, pp.103514~ (2022)
- Carranza-García M., "On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data", Remote Sensing, 13(1) (2021)
- YOLOv4:Optimal Speed and Accuracy of Object Detection, "Alexey Bochkovskiy", ~ (2020)
- S. Dubey, "A comprehensive survey on human pose estimation approaches", Multimedia Systems, 19(1), pp.167~195 (2023)
- Kaiming He, "Mask R-CNN", 2017 IEEE International Conference on Computer Vision (ICCV), pp.2980~2988 (2017)
- X. Cao, "Content and Privacy Protection in JPEG Images by Reversible Visual Transformation", Applied Sciences, 10(19) (2020)
- L. Rakhmawati, "Image Privacy Protection Techniques: A Survey", TENCON 2018- 2018 IEEE Region 10 Conference, pp.0076~0080 (2018)
- S. Murthy, "A Comparative Study of Data Anonymization Techniques", 2019 IEEE 5th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS), pp.306~309 (2019)
- "Camera - Raspberry Pi Documentation" (2024)[URL]
- A. Ghosh, "IOT based Portable Image Dehazing Machine", 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN), pp.31~35 (2021)
- Li, Xin, "Image Demosaicing: A Systematic Survey", Visual Communications and Image Processing 2008, 6822 (2008)
- T.-Y. Lin, "Microsoft COCO:Common Objects in Context", Computer Vision – ECCV 2014, pp.740~755 (2014)