Home


About us


Our AI


Blog


Contact us

   Lummetry VAPOR+ is our advanced scene and video analysis solution based on custom Deep Vision technologies.

   Standing for Video Analysis Processing, confidentialization – obfuscation and entity Recognition, it is a solution that targets multiple areas, ranging from GDPR-oriented basic features up to advanced video analysis. The solution is a complex AI Deep Vision powered video analytics platform capable of being deployed in various scenarios.

Person detect
Person head detect
Person item detect

In short
It helps companies gather data automatically from their video feeds and then analyzes these data using Deep Learning modules in accordance with our clients’ needs. Its application ranges from security (e.g. real time burglary alert) to retail (e.g. planogram conformity) and healthcare (e.g. patient lying on the ground in clinic or homecare)

Key features

Person tracking system for real-time or offline video analysis

On-demand customized video analytics features, including configurable alerts for various purposes

Works either as a stand-alone online system (deployed on-prem or in-cloud) or as an API back-end

What inspired us to create VAPOR

   We believe that there is more information available to us through computer vision than we realize. It is observing with a purpose, and that is what we tried to achieve here.

   A flexible AI that can identify, as precise as a human would, several unique items and individuals while never containing or distributing any personal information. This characteristic makes it adaptable for retail stores of all sizes, businesses and in institutional buildings.

http://vapor.lummetry.ai/wp-content/uploads/2019/08/VAPOR_inspiration_video_1.mp4

   At this point in time it is capable of observing 80 different unique objects and can be upgraded to any specific client requirement. Our ambition is to take it even further, to the micro level, detecting faces by emotion and objects with a higher accuracy. 

0
+
Possible items detected
0
sec
Inference time per frame