I am a Computer Vision Researcher and Engineer with over 5 years of hands-on experience delivering end-to-end AI powered imaging solutions across research and industry. My core expertise lies in deep learning-based computer vision, with a strong specialisation in multimodal imaging: combining hyperspectral cameras, 3D/depth sensors (ToF, structured light, stereo), and RGB cameras to solve complex real-world problems in industrial inspection, quality control, and spatial analysis.

I have designed and optimised pipelines for object detection, image segmentation, 3D human pose estimation, monocular depth estimation, and multi-object tracking, deploying them on both cloud platforms and edge devices such as Raspberry Pi and Jetson Nano. My background in 3D vision covers the full spectrum — from stereo camera calibration and depth map generation to point cloud processing, 3D bounding box fitting, and spatial filtering using libraries such as Open3D.

Beyond 3D, I bring deep knowledge of spectral and hyperspectral imaging, including acquisition, white/dark correction, and spectral segmentation techniques — applied to domains such as material analysis, colour science, and illumination optimisation. I hold an Erasmus Mundus Master's degree in Computational Colour and Spectral Imaging from a consortium of European universities (NTNU Norway, UJM France, UEF Finland), and I am a co-author of peer-reviewed publications in computer vision and imaging science.

Whether you need a custom object detection model, a 3D reconstruction pipeline, a hyperspectral data analysis workflow, or a real-time inference system integrated with a web interface, I can take your project from concept to working solution. I work remotely and am available for short-term consulting, project-based freelance contracts, and longer-term collaborations.