Xovis
Production Xovis 3D people counting sensors.

Xovis launches first AI-powered sensor

07.01.2018
Anina Jampen

Showcased as a world’s first at this year’s NRF in New York, Xovis proudly releases the first AI-powered sensor PC2S. 

Showcased as a world’s first at this year’s NRF in New York, Xovis proudly releases the first AI-powered sensor PC2S. The new Xovis Sensor with integrated AI marks the beginning of a new generation of 3D sensors and opens the door for serverless in-store-analytics. In combination with the Xovis SPIDER processing unit, true full-area monitoring and customer journey analytics inside a store become a reality.

«You will see devices featuring 3D technologies like TOF and Lidar, but the future will be in the hands of vision sensors featuring AI capabilities based on Deep Learning. The market demand to detect the exact behavior of shoppers in brick-and-mortar stores can only be targeted with the new generation of 3D Smart Sensors», Christian Studer, CPO of Xovis states.

«Based on the powerful Xilinx Zynq processing platform, we were able to integrate a Deep Net with a classification accuracy of over 99.5% on the edge device. Compared to the technologies available today, this process significantly enhances people detection.

This forms the base for many new features and applications to come. At the same time, we completely redeveloped the tracking algorithms as mathematically closed-form solutions, allowing to handle even the most challenging tracking situations such as occlusion and heavily cluttered situations. This leads to the required accuracy to realize full-path customer analytics» Markus Herrli, CTO of Xovis explains.

Full coverage for advanced in-store analytics

Together with the new Xovis platform "Spider" for the Multisensor full-coverage in-store analytics, those sensors will be the base for the next generation of Xovis in-store analytics. This innovation will be available to retail analytics solution providers and integrators worldwide.

“We believe in the AI revolution and in its power to take in-store analytics to the next level. With the AI-powered Xovis 3D Sensors, we want Retailers to perfect data accuracy and save labor costs. For example, trough large area Multisensor installations to track the full customer journey.” Christian Studer, CPO at Xovis explains.

The new Xovis PC2S sensor with integrated AI marks the beginning of a new generation of 3D sensors. Of course, also our latest sensor, the PC2R will be given AI capability. In combination with the Xovis SPIDER processing unit, the PC2S and PC2R sensors will apply AI algorithms that will spur for full-area monitoring and customer journey analytics.

Cyrill Gyger, VP Products at Xovis describes a bright future for AI-powered Xovis Sensors: “With reliable 3D sensors, it is relatively easy to determine an object of the shape and height of a person. In dense areas, accuracy nevertheless leaves room for improvement. That is where AI-powered 3D sensors excel in reducing false counts. Especially, the recognition of behavioral details is the key to taking cashier-free stores from the trial stage to becoming a global standard.” Together with reliable partners from all over the world, Xovis is setting new industry standards in building on the unmatched accuracy of the PC-series.

About Xovis

Swiss-based Xovis is the market leader in people flow monitoring. More than 60 international airports, as well as 140 system integrators in the retail and other industries, count on the combination of Xovis 3D sensors and software solutions to move people more smoothly through their facilities, optimize resource planning and ultimately increase customer satisfaction. Customers capitalize on Xovis’ unmatched accuracy, reliability and ease of use to measure a broad range of KPIs such as customer frequency, dwell times, waiting times and passenger throughput. The Xovis system also includes a sophisticated data privacy concept and does not depend on signal emitting devices. Founded in 2008, Xovis has evolved from a three-man start-up to a high-tech company with more than 80 employees.