MarshallAI pilots groundbreaking automatic border control in cooperation with Finnish Customs

PRESS RELEASE The pilot tests new technology to automate freight traffic at border crossings. It takes place on the Finnish-Norwegian border in Kivilompolo and continues throughout the year. Smart technologies are used to digitalize the flow of information, identify transport data and speed up border crossing procedures. Cargo can be monitored in real time and … Read more

Mastering QA in High-Mix Manufacturing: Rapid Changeovers and >99% Accuracy at Taerosol

Contract manufacturing and frequent product changeovers used to mean a constant struggle with QA bottlenecks. Discover how Taerosol future-proofed their cosmetics line with a rapidly adaptable AI system that catches over 99% of complex label and packaging defects.

Eliminating Rogue Cans: High-Speed QA in Beverage Manufacturing

A global beverage manufacturer spent 15 years trying to reliably intercept “rogue cans” on their high-speed filling lines. Discover how MarshallAI deployed a zero-latency edge vision system to inspect 2,500 cans per minute, preventing mismatched products and costly mechanical jams with near-perfect precision.

Sub-Millimeter Quality Control at Scale: Securing Yield for Turvanasta

Legacy vision systems were throwing away perfectly good material. Discover how MarshallAI deployed an edge computing solution to eliminate false rejects and inspect hundreds of millions of sub-millimeter metal parts with absolute precision.

Actuating Physical Infrastructure: How MarshallAI Achieved 99.8% Reliability in Harsh Conditions

Discover how MarshallAI’s edge vision flawlessly tracks complex objects in extreme conditions, achieving a 99.8% pedestrian detection reliability rate while safely triggering physical infrastructure controllers in real-time.

Upgrading Legacy Infrastructure: Crowd Analytics & Security Without Cloud Dependency

Learn how we utilized Särkänniemi theme park’s existing camera infrastructure to process live video on a closed-loop local area network – enabling security and crowd flow analytics while maintaining privacy.

From Scratch to Deployment in 1 Hour and 40 Minutes: Winning the xTech Global AI Challenge

See how our platform won the U.S. Department of Defense sponsored xTech Challenge by building a custom, fully offline object-detection model in just 1 hour and 40 minutes using only 77 reference images.