Gandhimathi (Mathi) Padmanaban

Ph.D., Industrial and Systems Engineering, University of Michigan-Dearborn

Applied Computer Vision and Machine Learning researcher. I build geometry-grounded perception that stays reliable when the camera, platform, or site changes, and that signals when it should not be trusted.

Seeking postdoctoral and research positions, 2026–27.  ·  Download CV

About Me

I am an applied computer vision and machine learning researcher. I completed my Ph.D. in Industrial and Systems Engineering at the University of Michigan-Dearborn, advised by Dr. Fred Feng (dissertation defended June 2026). My work builds perception systems that human-AI systems can rely on, and that keep working when the sensor, platform, or recording site changes. Each feature starts from how a vehicle's projection in the image encodes its geometry, the way its bounding box grows as it approaches and its bearing shifts as it passes, and I derive that quantitatively from the pinhole camera model so the feature carries a physical quantity rather than raw appearance. Geometric-consistency checks reject detections that violate the projection model, and a confidence threshold lets the classification stage abstain rather than commit to a label it cannot support.

I demonstrated this in road-safety measurement, estimating vehicle-bicyclist interactions from a single uncalibrated bicycle camera and showing that the same geometry-grounded formulation transfers to a different platform (the Waymo Open Dataset) when re-fit to a new supervision source. A second line of work models driver behavior from vehicle kinematics, the human side of any system that operates around people. I care about open, reproducible research, and I want to take the same approach, building the real structure of a problem into the model, into new domains where cheap sensors have to make reliable measurements. I am currently seeking postdoctoral and research positions.

Research Focus

I work on perception that has to hold up outside the conditions it was built in. In my dissertation that meant grounding measurements in the geometry of how a camera forms an image, and having the classifier withhold a prediction when its confidence was low. Both were useful, in one domain, and both rested on choices I set by hand: the validation rules, the abstention threshold, and the sensor labels needed to re-fit the model on a new platform.

What interests me now is making those choices less arbitrary. I want to know whether the physics of a scene can drive test-time adaptation to a new platform, in place of the sensor labels my own work relied on, and whether conformal prediction can put a real coverage guarantee behind an abstention threshold I currently set by hand. I am also interested in whether scene geometry can be used to check the spatial claims of large pretrained perception models, which are usually evaluated on clean imagery rather than in the conditions where they get deployed.

News

Jun 2026
Defended my Ph.D. dissertation, Adaptable Machine Learning and Computer Vision Frameworks for Road Safety: Applications to Driver Behavior and Driver-Bicyclist Interaction Research, at UM-Dearborn, advised by Dr. Fred Feng.
Jun 2026
Released an open-source two-stage pipeline for injury-risk vehicle body-type classification (RT-DETR plus a fine-tuned ViT), which holds 89% accuracy on held-out sites without retraining and abstains rather than guess when confidence is low.
Jan 2026
Presented at the Transportation Research Board (TRB) Annual Meeting, Washington, DC: geometry-informed overtaking detection from a single bicycle-mounted camera (poster), plus a co-authored talk.
Oct 2025
Received the Student Visionary Award at the International Forum on Research Excellence (IFoRE '25), Sigma Xi.
Apr 2025
Presented at the WCX SAE World Congress Experience, Detroit: naturalistic acceleration and deceleration profiles benchmarked against EPA fuel-economy test cycles.

Education

Ph.D. in Industrial and Systems Engineering
University of Michigan-Dearborn (dissertation defended June 2026; degree Aug 2026)
Advisor: Dr. Fred Feng
M.S. in Human Centered Design and Engineering
University of Michigan-Dearborn
2021
B.E. in Computer Science and Engineering
Anna University, India
2013

Research Interests

  • Methods: Geometry-informed computer vision • Physics-grounded measurement • Reliability-aware perception (out-of-distribution robustness, confidence-threshold abstention, conformal prediction) • Physics-driven test-time adaptation • Geometric checks on large pretrained perception models • Object detection and tracking • Behavioral modeling from kinematics
  • Domains (current and exploring): Infrastructure and platform-agnostic sensing • Trustworthy perception for human-AI systems • Remote sensing and environmental / climate machine learning • Vulnerable road user and transportation safety

Selected Awards

Student Visionary Award
International Forum on Research Excellence (IFoRE '25), Sigma Xi
2025
Upsilon Pi Epsilon (UPE) Scholarship
For academic performance and leadership in the computing community
2024
Global Finalist, NASA Space Apps Challenge
DigitwiML: digital twin of C. elegans in space
2023
Irma M. Wyman Scholar
Center for the Education of Women (CEW+), University of Michigan
$11,500 · 2020-2021

See full CV for the complete list of awards, publications, and service.

Recent Posts