Novel browser extension tool for image annotation : (Applications and use-cases in a novel CCTV-aware system)
Authors
Date
2022Access restrictions
The author has not given permission to make the work publicly available electronically. Therefore the material can be read only at the archival workstation at Jyväskylä University Library (https://kirjasto.jyu.fi/collections/archival-workstation).
Copyright
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Camera surveillance has become a worldwide phenomenon that affects the lives of almost every person. People are not aware of how much they are entering the surveillance zone and for some people the patronizing surveillance may raise concerns about individual freedom and privacy. This paper introduces a browser extension that allows users to annotate cameras to build a security / privacy type of navigation that avoids or follows cameras. Image annotation started with describing images with words that have evolved to annotate images in more detail, and today large datasets can be used for ML/CV model training. The purpose of the browser extension was to annotate images in a way that training of ML/CV models to recognize CCTV cameras from Google Street View images is possible. The browser extension was tested with the crowdsourcing effort where eight different people used the extension in different browsers and different operating systems, after which the people evaluated the extensions functionality and ease of use. The evaluation showed that the extension works as indented and it is an effective tool for annotating images. In addition, the extension succeeded in training ML/CV models to recognize CCTV cameras from Street View-level images.
...
Keywords
Metadata
Show full item recordCollections
- Pro gradu -tutkielmat [29141]
Related items
Showing items with similar title or keywords.
-
CCTVCV : Computer Vision model/dataset supporting CCTV forensics and privacy applications
Turtiainen, Hannu; Costin, Andrei; Hämäläinen, Timo; Lahtinen, Tuomo; Sintonen, Lauri (IEEE, 2022)The increased, widespread, unwarranted, and unaccountable use of Closed-Circuit TeleVision (CCTV) cameras globally has raised concerns about privacy risks for the last several decades. Recent technological advances implemented ... -
CCTV-FullyAware : toward end-to-end feasible privacy-enhancing and CCTV forensics applications
Turtiainen, Hannu; Costin, Andrei; Hämäläinen, Timo; Lahtinen, Tuomo; Sintonen, Lauri (IEEE, 2022)It is estimated that over 1 billion Closed-Circuit Television (CCTV) cameras are operational worldwide. The advertised main benefits of CCTV cameras have always been the same; physical security, safety, and crime deterrence. ... -
CCTV-Exposure: System for Measuring User’s Privacy Exposure to CCTV Cameras
Turtiainen, Hannu; Costin, Andrei; Hämäläinen, Timo (Springer International Publishing, 2022)In this work, we present CCTV-Exposure – the first CCTV-aware solution to evaluate potential privacy exposure to closed-circuit television (CCTV) cameras. The objective was to develop a toolset for quantifying human exposure ... -
Applications of Artificial Intelligence in the Economy, Including Applications in Stock Trading, Market Analysis, and Risk Management
Rahmani, Amir Masoud; Rezazadeh, Bahareh; Haghparast, Majid; Chang, Wei-Che; Ting, Shen Guan (Institute of Electrical and Electronics Engineers (IEEE), 2023)In an increasingly automated world, Artificial Intelligence (AI) promises to revolutionize how people work, consume, and develop their societies. Science and technology advancement has led humans to seek solutions to ... -
Practices and Infrastructures for Machine Learning Systems : An Interview Study in Finnish Organizations
Muiruri, Dennis; Lwakatare, Lucy Ellen; Nurminen, Jukka K.; Mikkonen, Tommi (Institute of Electrical and Electronics Engineers (IEEE), 2022)Using interviews, we investigated the practices and toolchains for machine learning (ML)-enabled systems from 16 organizations across various domains in Finland. We observed some well-established artificial intelligence ...