Passionate by camera based algorithms development
Welcome on my profile!
My name is Maxvell, I'm a software engineer passionate about camera based algorithms development. On this website, I introduce my projects and my work experience. At the end, you will find a contact form, feel free to write to me and share any spotlight news or events. I am always enjoying getting in touch with other researchers and engineers.
Algorithms Development
Strong experience in designing complex algorithms.
«I have strong skills in coding mathematical algorithms handling real-time camera stream data. I am particularly good at working on projects with advanced analytical issues, involving various collaborators such as researchers or electronic engineers.»
Embedded Programming
Strong experience with firmware development for real-time processing on SoC platform.
«I have worked on the integration and optimisation of sophisticated algorithms on various platforms. I am currently working on embedded ARM processors interfaced with FPGA fabrics, integrating a multi-process low latency algorithm. I am able to work under tight development milestones and improve iteratively the embedded system reliability and performance.»
Platforms
Web Development
Contribution to integrating basic functionalities. (beginner level)
«By assisting my colleagues to integrate new front-end features or fixing urgent back-end matters during release deployments, I acquired a basic knowledge of website maintenance. I do not have advanced experience in website and server administration but I can punctually assist my collaborators for urgent needs.»
Front end
Abstract: A high-speed optical tracking with compression and CMOS windowing for tracking applications that require high-speed and low latency when delivering objects pose (orientation and position) data.
Marti, Gaëtan, Maurice Hälg, and Bernard Maxvell Arulraj. “High-speed optical tracking with compression and / or cmos windowing” International Patent Application No. PCT/IB20 18/050899.Abstract: A light field processing method for processing data corresponding to a light field, comprising: a plenoptic camera initial data representing a light field; converting said initial data into converted data in a camera independent format; processing the converted data so as to generate processed data representing a different light field.
Rime, Laurent, Bernard Maxvell Arulraj, and Keishi Nishida. “Light field processing method” International Patent Application No. PCT/EP20 13/074520.Abstract: This paper deals with using the MultiObjective Particle Swarm Optimisation (MOPSO) metaheuristic for optimally thresholding medical images. Two criteria are optimised: the interclass variance and the Shannon entropy. The process generates a Pareto front with various segmentations, leaving the final choice to the user.
Arulraj, Maxvell, Amir Nakib, Yann Cooren, and Patrick Siarry; 2014.“Multicriteria Image Thresholding Based on Multiobjective Particle Swarm Optimization”. Applied Mathematical Sciences 8(3), pp. 131-137.
My interests:
#Project Management
Working on applied research product development involving joint hardware / software design, project management and communication with multidisciplinary stakeholders.
#Embedded System
Building low-cost embedded camera hardware with processor-adapted real-time algorithms.
#Camera Lens Calibration
Developing manufacturing tools to calibrate camera lenses for reconstructing scenes with sub-millimetric accuracy.
#Event-Based Camera
Camera Developing bio-inspired vision algorithms adapted to asynchronous events stream.
#Machine Learning
Developing training tools, databases and simulators aiming at iteratively improving feature matching performances.
#Multi-Sensor Fusion
Designing time-critical agnostic algorithms processing inputs from different systems and sensors such as conventional cameras, depth sensors or IMUs.