With around a billion surveillance cameras capturing people’s daily activities, chances are you’ll be regularly recorded if you live in a densely populated area.
In London, for example, it is said that there is 500,000 CCTV cameras and it is estimated that the average person is recorded 300 times a day.
To help people understand when they are on camera and how ubiquitous cameras affect their privacy, computer scientists affiliated with the University of Jyvaskyla in Finland have released open-source software called exhibition-cctv “to quantify human exposure to CCTV cameras from a privacy perspective.”
The software, which is part of a larger initiative to empower people to make better decisions about their privacy, is described in a document titled “CCTV-Exposure: an open source system for measuring user privacy exposure to geolocation-mapped CCTV cameras”.
The paper, written by Hannu Turtiainen, Andrei Costin, and Timo Hamalainen, is an extended version of research presented at Business Modeling and Software Design: 12th International Symposium (BMSD 2022) in Fribourg, Switzerland. He describes the software as analogous to a Geiger counter for detecting harmful radiation.
“Compared to exposure to ‘harmful environments’ such as radiation exposure, the CCTV-Exposure system is intended to act as a ‘CCTV doser’ for the travel activities of privacy-conscious individuals,” explains the document.
The software, written in Python 3, requires two input files: a Global Positioning System (GPX) interchange file containing GPS coordinates of a person’s movements and an XML file of camera location coordinates.
This camera location data is not yet available, beyond a test file for the city of Jyvaskyla.
That said, the team is constantly working to gather a broader set of coordinates, using computer vision algorithms to identify surveillance cameras in Google Street View images. The researchers plan to provide an API that will provide this camera location data to CCTV-Exposure users, making the code easily useful. It is hoped that people will also be able to submit their own reports of camera locations for inclusion in the database.
Right now, without that camera data, this project is really one to watch, rather than starting right away. Unless, of course, you create your own camera location tables in the meantime and use them with the code, which you’re all free to do and share with others.
Once the software has the information it needs – your route and surrounding CCTV details – it calculates where the provided route was exposed to a security camera. Its output in JSON format includes:
- Identity: identity information for the processed file, track and segment
- Distance: total distance traveled in the segment, total exposure distance, average and average distance to the cameras (in GPX points)
- Time (if applicable): average speed, total segment time, exposure time
- Percentages: exposure per total distance, exposure time per total time (if applicable)
- Data per camera: time, distance and all available camera data (location, field of view, etc.)
- Number of unique cameras
There is also a Rust version of the code, but it requires timestamped GPX files due to analyzer limitations.
In a test of the software based on Jyvaskyla route data captured by researchers using Garmin devices, average exposure to CCTV was 12.5% based on distance and 15.1% in function of time.
Andrei Costin, assistant professor at the University of Jyvaskyla in Finland (JYU.FI) and co-founder/CEO of security company binare.io, said The register in a telephone interview that the CCTV newspaper is one of five models he and his colleagues have developed to promote CCTV awareness.
“It comes from the need to understand the extent of the invasion of privacy, to quantify it,” he said.
Costin said there’s been a lot of talk about the number of cameras in China, the UK capital and elsewhere, but that’s based on hearsay, marketing arguments and arcane methodologies that aren’t scientific approaches. solid.
This led Costin and his colleagues to develop a way to better define CCTV camera coverage. As mentioned above, their approach relies on computer vision and machine learning to identify and geolocate CCTV cameras captured in Google Street View images and to calculate where the cameras can see.
This data can be fed into CCTV-Exposure to make everything work, and it is hoped that this information will be provided through an online interface. There is no timeline for the availability of this, and the team asked people to contact them if they could help financially or technically to make this happen.
“We developed the system based on Google Street View because it is the largest source of Street View imagery,” Costin explained. “But our system also allows users to submit in real time, taking a snapshot from a CCTV camera while their location is active and sending it to our servers.”
This keeps the camera’s location data up to date.
Costin said the group working on this project – which incorporates work of other to research papers – is developing a web application to allow Internet users to submit camera location updates. Researchers have used the app internally although it is not yet ready for public use.
It’s important, Costin said, that people understand how ubiquitous this technology is and how ubiquitous it is likely to become.
“In the next two years – it’s not about ‘if’ but ‘when’ – this technology will be complemented by facial recognition,” he explained, adding that it could be used to introduce people in the street personalized advertisements.
“It’s a really scary reality,” Costin said, “so we’re trying to build privacy-enhancing tools, to at least empower ordinary users.”
Costin’s main concern, however, is to educate people, so they can make informed choices about privacy. That could mean choosing routes with fewer cameras, he said, or with more cameras, if personal safety is a concern.
“If you are going to a remote place in an unfamiliar area, you can try to follow the road with the most CCTV cameras in the hope that if something happens to you there will be evidence,” he said. he explains.
Costin added that there’s something like one camera for every eight people on the planet and he expects the number of cameras to get much bigger. “I think the growth rate of CCTV cameras is insane,” he said. ®