Pedro Proença
Assistant Professor at Faculdade de Ciências e Tecnologia da Universidade NOVA de Lisboa
Los Angeles, California, Portugal
Summary
👤
Senior🎓
Top SchoolPedro Proença is an assistant professor and seasoned computer vision and AI engineer with 11+ years building perception and state-estimation software for drones, rovers, snake robots and other robotic platforms. He spent four years at NASA JPL contributing to seven projects including a lunar flight mission and autonomy advances for the Mars Helicopter, developing mapping, visual-inertial odometry, stereo, detection/tracking and pose-estimation modules. His PhD researched RGB-D odometry under depth uncertainty, and he continues to publish and review at top robotics venues while mentoring junior engineers and interns. A long-time C++ and ROS practitioner, he also builds simulators in Unreal Engine and maintains the TACO open dataset for litter annotation, which has seen international practical use. Based in Los Angeles with roots in Portugal, he blends research rigor with hands-on systems integration across fielded robotic missions.
11 years of coding experience
7 years of employment as a software developer
Master of Science - MS Computer Science and Telecommunications Engineering, Master of Science - MS Computer Science and Telecommunications Engineering at Iscte - Instituto Universitário de LisboaBSc Erasmus Telecommunications Engineering Computer Science, BSc Erasmus Telecommunications Engineering Computer Science at Università degli Studi di FirenzeDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of SurreyBachelor's degree Aerospace Engineering, Bachelor's degree Aerospace Engineering at Instituto Superior Técnico
Github Skills (8)
mask-rcnn10
object-detection10
computer-vision10
machine-learning10
python10
image-processing9
datasets8
tensorflow7
Programming languages (2)
Github contributions (5)
pedropro/TACO
Jun 2019 - Jan 2023
🌮 Trash Annotations in Context Dataset Toolkit
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 183 commits, 1 PR in 3 years 8 months
Contributions summary:Pedro's commits primarily involve modifying the `detector/inspect_data.ipynb` file to integrate Mask-RCNN. These changes include the addition of Mask-RCNN, suggesting an effort to enhance object detection capabilities, and adjustments to handle potential issues, specifically related to image orientation. The user also updates the annotations and corrects bounding box coordinates, improving the dataset's utility for model training. Furthermore, the user corrects the configuration path for model training.
litterannotationsdeep-learningdatasetobject-detection
pedropro/OMG_Depth_Fusion
Nov 2017 - Aug 2019
Contributions:51 commits, 49 pushes, 1 branch in 1 year 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.