|
Project Information
Links
|
OverviewThe Automated Visual Event Detection and Classification (AVEDac) software is designed to automated the detection of organisms in underwater video. The software was designed in collaboration between the Monterey Bay Aquarium Research Institute (MBARI), California Institute of Technology (Caltech), Pasadena, CA, and the University of Southern California. Video frames are processed with a neuromorphic selective attention algorithm. The candidate objects of interest are tracked across video frames using linear Kalman filters or Nearest Neighbor approaches. If objects can be tracked successfully over several frames, they are labeled as potentially "interesting" and marked in the video frames. The plan is that the system will enhance the productivity of human video annotators and/or cue a subsequent object classification module by marking candidate objects. This work was made possible with the generous support of the David and Lucile Packard Foundation. This project originated at the 2002 Workshop for Neuromorphic Engineering in Telluride, CO RequirementsThis code is freely available, however to build the classifier you will need a copy of Matlab, the Matlab compiler and Matlab Image Processing Toolkit. It is primarily built for Linux, however certain components such as the GUI for analyzing detected events and running the classifier will run on a Mac If you would like a copy of this software to test and do no have the required Matlab components, please contact Danelle at dcline@mbari.org and she will be happy to give you a compiled version of this code on a virtual machine for experimenting with in the VMWare Player http://www.vmware.com/products/player/. You should be able to experiment with this on any platform supported by VMWare Player, like Windows, Linux, or a Mac. For users
|
|
|
