Pilot Project Südkreuz Berlin

Pilot Project Südkreuz Berlin
Excluded from graph
Deployment Status	Concluded
Deployment Start Date
Deployment End Date
Events	* uses Record type Property:Has event Start (1 August 2017, Documented, ?, No description) uses Record type Property:Has event End (31 December 2019, Documented, ?, No description)
City	Berlin
Country	Germany
Involved Entities
Keywords
Technology Deployed	BioSurveillance, Morpho Video Investigator (MVI), AnyVision Software, IBM Germany Gmbh, Funkwerk video systems Gmbh, G2K Group Gmbh, Hitachi
Information Certainty	Documented
Primary sources
Datasets Used	Images of Voluntary Participants, Staged behaviour by voluntary participants
Deployment Type	Surveillance
runs search software
managed by	German Federal Police (Bundespolizei), Deutsche Bahn AG
used by	German Federal Police (Bundespolizei)
Potentially used by
Information Certainty	100
Summary	0

Graph View ↗︎

Information Certainty: Documented

Deployment Purpose: Surveillance

Summary
0

• Details

Products and Institutions:

Product Deployed	AnyVision Software BioSurveillance Morpho Video Investigator (MVI) IBM Germany Gmbh Funkwerk video systems Gmbh G2K Group Gmbh Hitachi
Institutions ⠉	AnyVision Herta Security IDEMIA
Datasets	Images of Voluntary Participants Staged behaviour by voluntary participants
Search software

Status and Events:

Status	Concluded
Events	Start (1 August 2017, Documented, ?, No description) End (31 December 2019, Documented, ?, No description)
Start Date
End Date

Users:

Involved Entities
Managed by	German Federal Police (Bundespolizei) Deutsche Bahn AG
Used by	German Federal Police (Bundespolizei)

Location:

City	Berlin
Country ⠉	Germany

Loading map...

{"format":"leaflet","minzoom":false,"maxzoom":false,"limit":50,"offset":0,"link":"all","sort":[""],"order":[],"headers":"show","mainlabel":"","intro":"","outro":"","searchlabel":"... further results","default":"","import-annotation":false,"width":"auto","height":"350px","centre":false,"title":"","label":"","icon":"","lines":[],"polygons":[],"circles":[],"rectangles":[],"copycoords":false,"static":false,"zoom":5,"defzoom":14,"layers":["OpenStreetMap"],"image layers":[],"overlays":[],"resizable":false,"fullscreen":false,"scrollwheelzoom":false,"cluster":false,"clustermaxzoom":20,"clusterzoomonclick":true,"clustermaxradius":80,"clusterspiderfy":true,"geojson":"","clicktarget":"","showtitle":true,"hidenamespace":false,"template":"","userparam":"","activeicon":"","pagelabel":false,"ajaxcoordproperty":"","ajaxquery":"","locations":[{"text":"\u003Cb\u003E\u003Ca href=\"/wiki/index.php/Pilot_Project_S%C3%BCdkreuz_Berlin\" title=\"Pilot Project S\u00fcdkreuz Berlin\"\u003EPilot Project S\u00fcdkreuz Berlin\u003C/a\u003E\u003C/b\u003E","title":"Pilot Project S\u00fcdkreuz Berlin","link":"","lat":52.51704,"lon":13.38886,"icon":""}],"imageLayers":[]}

Description

The German federal police (BPOL), in cooperation with the Deutsche Bahn AG, the German railway company, conducted a project called “Sicherheitsbahnhof” at the Berlin railway station Südkreuz in 2017/18. The project consisted of two parts: part one was done from August 2017 until January 2018 with 312 voluntary participants. Part two was carried out from February until July 2018, including 201 participants (Bundespolizeipräsiudium Potsdam 2018).

For the first project, 77 video cameras and a video management system were installed at the train station Berlin Südkreuz. Three cameras were used for the biometric facial recognition during live monitoring. During the project, the systems BioSurveillance by the company Herta Security, delivered by Dell EMC AG, Morpho Video Investigator (MVI) by IDEMIA AG, and AnyVision by Anyvision were used and tested. To detect and identify faces, the systems worked based on neural networks using Template Matching Methods. For that purpose, images of the faces were recorded and converted into templates. Subsequently, the facial recognition software matched the unknown picture to a known model saved in the reference database. As soon as a certain threshold of similarity is reached, the image is considered a match. The reference database consisted of high-quality images of the participants. That means the photographs had to adhere to quality standards such as a neutral grey background, no shadow in the faces, enough lighting, low compression to avoid artefacts, high resolution, and a straightforward viewing direction.

For the first testing phase, the participants passed the designated area of the train station Berlin Südkreuz a total of 41.000 times. BioSurveillance had an average hit rate of 68,5%, MVI of 31,7%, and AnyVision 63,1%. A combined hit rate by the interconnection of the three systems resulted in an increased total hit rate of 84,9%. The interconnection also increased the rate of false positives. The matches were logged but not saved.

For the second testing phase, the reference database consisted of participant images from the video stream of the first testing phase. For each participant, 2-5 images were extracted from the video stream. The images recorded during the second testing phase generally were of worse quality than from the first phase. All systems used more than one picture as a reference to identify a person.

During the second phase, the interconnected systems had an average testing rate of 91,2%. BioSurveillance resulted in an average hit rate of 82,8%, MVI in 31,2%, and AnyVision in 76,2%. The performance increased as the systems had more images as a reference (Bundespolizeipräsiudium Potsdam 2018).

The Deutsche Bahn AG used the existing infrastructure at the railway station Berlin Südkreuz for an experiment on behavioural analysis starting in June 2019. The tests were done twice a week during the day. Volunteers played situations the system should recognize and identify. After scanning people's behaviour, the software would alert the police or the railway company (Henning 2019). The police assembled a list of behaviours that should be recognized by the system: people lying down or entering certain zones of the train station (such as construction areas), groups of people or streams of people, objects that were set down such as luggage, and the positions of persons and objects. Furthermore, the system would be counting the number of people in certain areas and allow the analysis of the video data by the police. The software used by the tests is provided by IBM Germany GmbH, the Hitachi Consortium (Hitachi, Conef, MIG), Funkwerk video systems GmbH and G2K Group GmbH (Bundespolizei 2019).

The projects were criticized to be unscientific in handling the data, the low number of participants and the use of pictures of high quality in the database. Moreover, the Chaos Computer Club criticized that the results would not justify using the technology on a bigger scale as it did not do very well as the hit rate was quite low (Chaos Computer Club 2018).

Bundespolizei. (07.06.2019). Test intelligenter Videoanalyse-Technik. Retrieved on 18 April 2021 from https://www.bundespolizei.de/Web/DE/04Aktuelles/01Meldungen/2019/06/190607_videoanalyse.html 1

Bundespolizeipräsidium Potsdam (18. September 2018). Teilprojekt 1. Abschlussbericht. Retrieved on 18 April 2021 from https://www.bundespolizei.de/Web/DE/04Aktuelles/01Meldungen/2018/10/181011_abschlussbericht_gesichtserkennung_down.pdf;jsessionid=B00C5E4B9341D9F8733EF8508A6D9C46.2_cid324?__blob=publicationFile&v=12

Chaos Computer Club (13.10.2018). Biometrische Videoüberwachung: Der Südkreuz-Versuch war kein Erfolg. Retrieved on 18 April 2021 from https://www.ccc.de/de/updates/2018/debakel-am-suedkreuz 3

Henning, Maximilian (19.06.2019). Überwachung am Südkreuz soll jetzt Situationen und Verhalten scannen. Netzpolitik.org. Retrieved on 18 April 2021 from https://netzpolitik.org/2019/ueberwachung-am-suedkreuz-soll-jetzt-situationen-und-verhalten-scannen/ 4

This page uses the following references:

• References#_SCITEe10576836b385ea7ab4d656193b981a0
• References#_SCITE56e0db1f483bd2d56171ef1f53fbeadc
• References#_SCITEaad11b216b851ae9b7b92b1a994c5dc7
• References#_SCITE532c18d4e6f568636a57376cf16dfbde