Current projects:

Completed projects:

  • Nested Motion Descriptors:  Phase based motion descriptors for action recognition
  • Scene understanding on the DARPA Visual Media Reasoning program
  • Nested Shape Descriptors:  Exemplar based shape representations for fast global image correspondence
  • Visual deck pose estimation for Firescout Landing [perch][high-hover][low-hover]
  • VISYM: A Platform for Large Scale Visual Recognition [video]
  • Optical-GIF:  Visual time to contact estimation for guidance integrated fuzing on precision munition
  • VAMAV: Visual obstacle detection and avoidance for a micro air vehicle using expansion segmentation for time to collision estimates
  • VISTA:  Stereo based obstacle detection for small UAVs.
  • SAFESEE:  EO/IR/LIDAR sense and avoid for unmanned air vehicles
  • ImageNav: Image aided navigation for an unmanned air vehicle in GPS denied areas.
  • EVASE:  Pattern classification and tracking in head’s up display (HUD) video for aerial vehicles.
  • K-cut Image Segmentation: Perceptual organization using multiway graph cuts.
  • Constrained Fuzzy Clustering: Constrained fuzzy clustering for target detection in particle filters
  • Reconfigurable Vision Machine: Research staff at CMU Robotics Institute for modular architecture and software tools for high performance machine vision.
  • Micro Vision Engine: Consultant to CMU Robotics Institute on low noise analog NTSC layout for a vision computer suitable for a small unmanned vehicle.
  • TUGV: Research assistant on high speed cross country navigation using stereo vision for the Transitional Unmanned Ground Vehicle at CMU-RI
  • Virtualized Reality: CMU-RI research assistant on hardware and software based camera synchronization for multibaseline 3D reconstruction.
  • Automated Timber Inventory: Precise texture segmentation for tree diameter estimation.