Research project on the classification of radar images

In collaboration with the company IMST in Kamp-Lintfort, Prof. Hirsch is developing a radar module that can not only locate objects, but also classify them. The almost three-year project (2020-2022) is sponsored by the German government's Central Innovation Program for SMEs (ZIM).

The aim of this project is to develop a new radar module that can not only locate objects, but also classify them. One application is the monitoring of properties or buildings. The aim is to detect a dangerous situation, e.g. burglary or vandalism, at an early stage so that appropriate alarm or protective measures can be initiated. Object classification is an innovative and previously unavailable feature of the new product.

If the object is a moving person, the advantage of radar technology is that, unlike video recordings, the anonymity of the person is preserved and personal rights are not violated. Another advantage is that it is almost completely independent of light and weather conditions. Pattern recognition methods from the field of artificial intelligence (AI) will be used for classification, with specialization in the use of neural networks (NN). In order to determine a sufficient amount of annotated training data, a video recording will be made in parallel to the radar signal.

Back

Name	Purpose	Lifetime	Type	Provider
CookieConsent	Saves your consent to using cookies.	1 year	HTML	Website
fe_typo_user	Assigns your browser to a session on the server.	session	HTTP	Website

Name	Purpose	Lifetime	Type	Provider
_pk_id	Used to store a few details about the user such as the unique visitor ID.	13 months	HTML	Matomo
_pk_ref	Used to store the attribution information, the referrer initially used to visit the website.	6 months	HTML	Matomo
_pk_ses	Short lived cookie used to temporarily store data for the visit.	30 minutes	HTML	Matomo
_pk_cvar	Short lived cookie used to temporarily store data for the visit.	30 minutes	HTML	Matomo
_pk_hsr	Short lived cookie used to temporarily store data for the visit.	30 minutes	HTML	Matomo
_gcl_au	Used by Google AdSense to experiment with advertisement efficiency.	3 months	HTML	Google
AMP_TOKEN	Contains a token that can be used to retrieve a Client ID from AMP Client ID service. Other possible values indicate opt-out, request in progress or an error retrieving a Client ID from AMP Client ID service.	1 year	HTML	Google
_dc_gtm_--property-id--	Used by DoubleClick (Google Tag Manager) to help identify the visitors by either age, gender or interests.	2 years	HTML	Google
_fbp	Stores the unique visitor ID.	28 days	HTML	facebook
facebookPixel	If JavaScript is not enabled, this pixel initiates a connection to facebook.	none	Pixel	facebook

News