Imagine a smart camera inside an airplane cabin that can look at the overhead bins and instantly tell crew whether luggage is stored safely — even in dim lighting. That's what SmaCS built: an AI-powered camera trained on 3D models of an A320 cabin to recognize luggage placement issues automatically. Instead of cabin crew manually checking every bin before takeoff, the system does it in seconds. The same technology can also work in trains and buses for passenger safety checks.
Airlines lose millions annually to delayed departures, and one bottleneck is the manual cabin readiness check — crew walking the aisle verifying every overhead bin meets safety requirements. This process is slow, error-prone in dim cabin lighting, and scales poorly across growing fleets. The same problem exists in trains and buses where pre-departure safety checks rely entirely on human inspection.
A TRL5 camera-based AI prototype that automatically verifies cabin luggage compliance using machine learning trained on synthetic 3D models of an A320 aircraft cabin. The system runs on ultra-compact, aircraft-compliant hardware built from commercial off-the-shelf components, designed for easy integration into existing cabin monitoring systems.
If you are an airline or cabin systems integrator dealing with slow turnaround times because crew must manually verify every overhead bin before departure — this project developed a TRL5 AI camera prototype that automatically checks cabin luggage compliance in low-light conditions. Built on an A320 cabin model, it can cut pre-departure checks from minutes to seconds, directly impacting on-time performance.
If you are a train operator or bus fleet manager dealing with passenger safety compliance checks that slow down boarding — this project developed camera-based AI that recognizes luggage and objects in tight, low-contrast spaces. Originally designed for aircraft cabins, the technology transfers directly to rail and bus environments where similar verification is needed before departure.
If you are a computer vision company struggling with the cost and time of collecting real-world training data — this project developed a method to train machine learning algorithms using synthetic 3D models instead of thousands of real photos. This cuts dataset creation costs dramatically while achieving high recognition accuracy, applicable to any industry where physical objects need automated visual inspection.
The project received EUR 843,575 in EU funding across 2 partners to develop the TRL5 prototype. Commercial pricing is not disclosed in the project data. Contact the coordinator for licensing or integration cost estimates.
The prototype was designed with aircraft compliance in mind — ultra-light, ultra-compact hardware based on commercial off-the-shelf (COTS) components with adaptable interface connections. The objective mentions derived products generating 10M$/year in additional turnover, suggesting commercial fleet-scale deployment is planned.
The consortium consists of OTONOMY Aviation (France, industry) and VICOMTECH (Spain, research). IP is likely shared between these two partners. OTONOMY Aviation as coordinator would be the first contact point for licensing discussions.
The system was specifically designed for low-light, low-contrast cabin environments. The TRL5 prototype was built for integration into a Cabin Demonstrator, and training used a realistic synthetic A320 cabin model provided through Airbus Interiors Services.
The project closed in July 2022 with a TRL5 prototype ready for cabin demonstrator integration. Moving from TRL5 to commercial deployment (TRL8-9) typically requires additional certification and qualification steps, especially for aviation-grade equipment.
The hardware was designed to be aircraft-compliant from the start, using COTS components with adaptable CVMS interface connections. However, full certification status is not detailed in the available project data. Based on available project data, regulatory approval would be a next step beyond TRL5.
This is a lean, focused consortium of just 2 partners across France and Spain — OTONOMY Aviation (industry, coordinator) brings deep expertise in aeronautic camera systems and direct relationships with Airbus Interiors Services, while VICOMTECH (research) contributes proven machine learning and synthetic 3D training capabilities. With 50% industry ratio and 1 SME in the mix, the consortium is commercially oriented. The EUR 843,575 budget is modest, suggesting efficient development. The Airbus connection through OTONOMY is a strong signal for future commercialization pathways in the aviation supply chain.
OTONOMY Aviation (France) — aviation camera systems company with Airbus supply chain connections
Want to explore licensing this AI cabin inspection technology for your fleet or transport operation? SciTransfer can connect you directly with the development team.
