Sergio Bampi
Professor at Federal University of Rio Grande do Sul
Rio Grande do Sul, Brazil
Summary
🤩
Rockstar🎓
Top SchoolSergio Bampi is a seasoned professor and microelectronics researcher with over four decades of academic leadership at Federal University of Rio Grande do Sul, specializing in CMOS VLSI, ultra-low power/voltage design and near-Vt digital circuits. He holds an M.Sc.E.E. and Ph.D. from Stanford in microelectronics and silicon processing, and has coordinated research groups and graduate supervision spanning integrated circuits, image/video algorithms-to-architecture, and CMOS RF front-ends. Beyond academia he contributes applied machine learning work — notably on an attention-based license-plate detection and recognition system integrating darknet and Keras components — reflecting a hands-on approach to bridging hardware-aware design and computer vision. His profile combines deep device-level expertise with system-level thinking for energy- and throughput-optimized video processing, making him equally at home advising PhD research or prototyping practical ML-enabled imaging solutions.
9 years of coding experience
Electronics Engineer, B.Sc. in Physics, Integrated Circuits and Solid State Devices, Electronics Engineer, B.Sc. in Physics, Integrated Circuits and Solid State Devices at Universidade Federal do Rio Grande do SulPh.D., Microelectronics, LDD FETs, MOS devices, Ph.D., Microelectronics, LDD FETs, MOS devices at Stanford University
English, Spanish, Italian
Github Skills (8)
computer-vision10
machine-learning10
darknet10
tensorflow10
python10
mask-rcnn9
faster-rcnn9
keras8
Programming languages (4)
Github contributions (5)
sergiomsilva/alpr-unconstrained
Aug 2018 - Apr 2019
License Plate Detection and Recognition in Unconstrained Scenarios
Role in this project:
ML Engineer
ML EngineerContributions:24 commits, 19 pushes, 1 branch in 8 months
Contributions summary:Sergio's contributions primarily focused on developing and refining a license plate detection and recognition system. They implemented and trained an attention-based network architecture within a darknet framework, as shown by the code additions in `attention.c`. The user also worked on training scripts for the detection network and integrated YOLO output filtering. Further updates included modifications to the annotation tool and the addition of a Keras-based model for vehicle detection.
pythonunconstrainedlicense-plateplaterecognition
VeriSilicon/TIM-VX
Nov 2024 - Nov 2024
VeriSilicon Tensor Interface Module
Contributions:1 comment in 1 day
deep-learningneural-networktensortensorflow
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.