The applications of SWARM Analytics are already in use in Europe, North America and New Zealand.
Can existing surveillance cameras be upgraded?
Of course. However, if the camera is recording in real time, it is subject to GDPR and typically has to be deleted after 72 hours. The extracted statistical data, on the other hand, can be used.
How high is the sensitivity of the SWARM Perception Box?
For standardized applications, such as parking lots, the hit rate is almost 100 %. In other areas like public transport buses, it's somewhat more difficult because there are often partial overlaps of people. But even there, the SWARM algorithms achieve a precision of more than 95 %.
Are cameras that do not film still cameras?
In the legal and practical sense, not really. The camera still generates a digital image that the SWARM Analytics hardware immediately analyzes, but does not forward or save. Each image actually exists less than 50 milliseconds as a data object and is immediately deleted in the computer memory. It is similar to an eye, which also takes pictures, but does not save them either.
Is it only possible to gather entry and exit data or also the density of groups of people?
Entry and exit counts are very suitable for recognizing the total number of people in a specific area (e.g. open-air pool, market or stadium). If COVID related distance rules should be kept, the distribution of people is important. Therefore, the SWARM Analytics device also directly outputs the distribution of objects in an area. However, partial roofing or large sunshades can make it difficult to recognize the people-distribution.
Are the camera images stored?
No. Every image is immediately deleted from the SWARM Perception Box memory after the analysis. No image is saved at any time.
How long may the data be stored?
The generated data is no subject to any restrictions since it does not contain any personal data. If the data is linked to other data sources, the situation has to be clarified with the operator's data protection officer.
What biometric data is collected?
No biometric characteristics are collected, which means no individuals can be identified. In particular, the algorithms of SWARM Analytics do not use facial recognition.
Do I need a data protection approval or a data protection impact assessment?
No. There is no data collection permit or reporting system required. As long as the data is not linked to other data sources, there is no need for a data protection authorization or a data protection impact assessment necessary (see DSFA-AV). The image generated by the camera exists only about 50 milliseconds and is neither saved nor forwarded. The output of the software is textual data, which is then visualized in the dashboard of the user. Therefore, there is no personal data collected.
Is it possible to "hack" the system?
The system only sends, which means it is invisible to an active attack. It is also not possible to connect to the camera.
FAQs for Zones
Q: Is it important that the whole car or object passes “inside” the zone or is it enough if the center-point of the car does so?
A: The center-point of the vehicle (or another object) is tracked, therefore it is important that the center-point of the vehicle moves in the entry zone and leaves in the exit zone. Bear in mind that the camera view is a 2D representation of the 3D world, so the zones often have to be bigger than you expect. The center point of the car may be above road level.
Q: Is it okay if the cars stand still in a zone for a while, i.e. can I create a zone “in front” of the traffic light so that the cars are still in the “entry” zone?
A: It is okay if cars (or other objects) stand still for a while in a zone. When they move again, they will continue to be tracked. If possible, it is best to avoid having zones that cover parked cars. This can create performance problems as the cars are continuously tracked and if another similar car passes nearby, the cars can get confused with each other.
Q: Can zones overlap or be really close to each other?
A: Yes, zones can be very close to each other or overlap. However, an object (e.g. car) needs to be detected as entering and exiting two distinct zones (i.e. where there is no overlap) for their track to be recorded.