Looking for computer vision work. Multi-view stereo, camera calibration, SfM, scene reconstruction, 3D object triangulation, 3D multi-object tracking. Object detection, tracking, video processing. I mostly work in Python and C++, but the stack is not super important to me. I have 14 years of experience as a software engineer. Self-directed, and I do not require a lot of management. I go the extra mile producing technical notes, reports, visualizations, etc. to help communicate my results. References available upon request. Willing to travel.
RECENT PROJECTS
Damage detection/grading for collectable items
- 2D damage detection using smartphone camera from multiple views
- Map 2D multi-view into global 3D space for unique damage instance collation with novel camera calibration technique using differentiable rendering
- AWS pipeline to orchestrate all the ML/GPU crunching to support a mobile app
Real-time soccer markerless motion capture
- Camera calibration (20+ cameras) using COLMAP
- Calibration refinement and camera drift maintenance
- 3D object triangulation from multi-view 2D object detections
- 3D human pose reconstruction from 2D pose estimations
- 3D multi-object tracking
- Real-time pipeline (60 Hz)
Video auto-cropping to convert long-form landscape orientation videos in to vertical, short videos
- Prioritize between competing subjects in video
- Create smooth panning crop-out region for each subject
- Naturally transition focus between different subjects
CONTACT
email work at zacstewart dot com