Matthias M.

About Me

Matthias is a highly skilled software engineer with a special focus on Python, artificial intelligence, and machine learning. He has successfully designed and implemented a sophisticated computer vision solution for precise object and person detection, adeptly managing every aspect, including data collection, model training, and deployment on embedded hardware. With an outstanding track record of accomplishments, Matthias excels in swiftly developing prototypes and seamlessly integrating solutions into back-end systems or edge devices.

AI, ML & LLM

Backend

Database

DevOps

Docker Google Cloud Engine Google Cloud

Workflow

Other

Work history

Continental Automotive Regensburg
AI Software Engineer
2022 - Present (3 years)
Remote

Child presence detection inside vehicles with NIR camera: Lead role for all AI related activities, effort and feasibility estimation, planning of data recording and labelling campaigns, training and testing of ML models using TensorFlow and Keras. Application development in C++ for deployment on Qualcomm Snapdragon and QNX based automotive HPC system. Tests with synthetic data in addition to real images. Passenger abnormal body pose detection: Combined pose keypoint estimation with pose classification by feeding keypoints into tree based ML model

Weitblick.ai
Software Developer
2022 - Present (3 years)
Continental
AI Software Engineer
2018 - 2021 (3 years)
Remote

Detection of objects inside vehicles with NIR/RGB cameras: Collected and (auto)labeled images, trained model using TensorFlow Object Detection API, hyper parameter optimization. Application development in Python and C++ for deployment of AI models. Integrated object detection and pose estimation algorithms for a cabin sensing demonstrator running inside an autonomous shuttle bus. Model quantization with TensorRT for Nvidia Jetson Nano target device. Implemented wrapper for TensorFlow Object Detection API to simplify training on custom datasets, created Docker image for dependencies. Used by colleagues across departments for training models. Developed visual crop row detection node for agriculture robot using a stereo camera, Python, OpenCV and ROS.

Continental
Working Student
2013 - 2017 (4 years)

Showcase

3D Models Generation Solution
  • Led development of a Python back-end system that uses phone camera footage to create innovative 3D models.

  • Designed and implemented an image processing pipeline for accurate 3D point cloud and texture calculations.

  • Developed a state-of-the-art REST API using FastAPI technology for easy deployment on cloud platforms.

Vehicle In-cabin Computer Vision System
  • Contributed to the development of a computer vision system for automotive cabin sensing, with key functions like object detection, driver state recognition, and child presence detection.

  • Served as an AI software engineer, responsible for managing data collection and labeling, and model training.

  • Successfully integrated the computer vision system onto automotive hardware.

Computer Vision Solution for Agriculture Robot
  • Led the design and implementation of a computer vision pipeline to assist an autonomous robot's navigation in agricultural fields.

  • Developed advanced image processing techniques with OpenCV using real-time camera data.

  • Successfully integrated the solution into a ROS node.

Education

Education
Master's Degree in Computer Science
Regensburg University of Applied Sciences (OTH Regensburg)
2015 - 2018 (3 years)
Education
Bachelor's Degree in Computer Science
Regensburg University of Applied Sciences (OTH Regensburg)
2011 - 2015 (4 years)