Every system is designed for one specific problem. Computer vision, 3D reconstruction or AI automation, measured where you'll actually use it, not in a demo.
Industrial engineer (Universitat Jaume I, Castellón) and mechanical engineer specialising in mechatronics (INSA Lyon), with a master's in industrial engineering and another in robotics, graphics and computer vision, focused on vision and AI. I worked in programming and simulation in industry before moving into vision and automation. Now I'm going freelance, aiming to be the bridge between your company and new technologies, and to turn your ideas into something real. More about me.
Vision, 3D, AI and data. Cutting-edge technology, applied to what your business really needs.
Automated inspection, counting and tracking, tuned to your cameras and your data, working in your factory, your warehouse or wherever you need it.
Machines that understand a space the way you do, knowing what's in it, where everything is and how it all fits together. The next frontier of AI.
Your data already knows things you don't. A model learns them and uses them to classify, predict or decide. Sales, sensors or images: if there's data, there's something to learn.
A model that's too slow or too resource-hungry is no use. I optimise it and integrate it into your system so it responds instantly, on the hardware you already have.
A digital team that never sleeps. Agents that see tasks through from start to finish in your own tools, track down what's missing and decide the next step, always under your control.
Your business knows how to do its job, and paperwork shouldn't hold it back. I bring your data together in one place and automate the repetitive work, so your time goes on what really matters.
From sensor to screen, with no one in between. Sensors, gateways and a platform, all connected so your equipment tells you what's going on, as it happens.
A living replica of your network or facility that updates itself, alerts you the moment something fails and uses its history to see what's coming.
Problem, constraints, what I tried, what I ruled out and what I measured. No hype.
Objects in the map split, got mixed together or were duplicated after loop closure. Three fixes: up-to-date geometry, evidence-based assignment and voxel-based fusion.
A colonoscopy SLAM has to recognise the places it has already been through. Bag of Words was replaced by a deep-learning network ported to C++: it performs on par and proposes more consistent candidates.
Where was an old photo taken from? A Structure from Motion pipeline written from scratch reconstructs the place in 3D and locates the photo within it, less than a degree away from COLMAP.
From one figure every two months to every water meter, hour by hour. An IoT platform for villages and hotels: readings over LoRaWAN or M-Bus, from several manufacturers, in a single digital model with alerts as soon as something goes wrong.
You tell me about the problem, we look at it together and you come away from the call with a clear path to solving it.
Together we set the goals, deadlines and milestones, and what I'll need from you. You know from day one what you'll get and when.
I build the solution following the plan we agreed. I keep you posted and we adjust whatever needs adjusting.
The finished, documented solution, reviewed with you to make sure it does what we agreed. Your idea, made real.
Tell me about it on a quick call. I'll let you know if I can help.
