Gaming
People counting, head detection and CCTV dataset QA for gaming and casino operators and the vendors who serve them.
Who it is for
Gaming and casino operators, and the analytics and AI vendors who build occupancy, queue and floor-monitoring models for them.
Typical problems
Casino floors are dense, unevenly lit and usually filmed from overhead or fisheye cameras. Models need reliable people counts and head positions across tables, machines and walkways, and the training data has to cope with crowding, overlaps and distortion at the edge of the lens.
What we can do
Head detection, crowd counting and dataset QA on fisheye and overhead video. We can create first-pass labels, or check and correct an existing dataset by fixing missing labels, false positives and overlapping boxes against a clear rulebook.
Proof
Our queue head detection work for a confidential US client includes casino venues, with more than 50,000 head boxes checked and corrected a month under dedicated QA and senior sign-off.
Delivery, security and quote
Every project runs through the same method: an agreed scope and taxonomy, calibration where the project calls for it, production by trained annotators and review before anything is handed back. Read more in How We Work and Tools and Delivery.
Data handling, including access, transfer, retention and deletion, is agreed with you in writing before work starts. See Security and Compliance for how we handle data.