G2-Update1
The Effect
Football player tracking with CG indicators
The Input
- Football game footage from side or goalpost view (We still need this!)
- User's indication of the players.
- Possible user corrections if tracking fails.
The Output
- Football game footage with CG indicators added based on feature tracking.
The Layers
- The raw football game footage
- CG indicators
The Pipeline
Progress
Research:
Coding:
- Wrote code that uses openCV to open an avi and iterate through the IplImage frames and playback in a openCV window.
- Explored tracking demos that use the CamShift and MeanShift algorithms.
- Started writing code that uses cvGoodFeaturesToTrack and cvCalcOpticalFlow.
- Optical flow for image sequences (since the field does not flow, this gives us additional information as to which areas contain players)
- Began development on effective tracking of multiple objects
Video:
We modified the openCV demo "camshiftdemo.c" to fit the video we had and to output images(modified code: FILE function cannot find the upload.). This is that output:
Work Distribution
Mike - Research and coding
Shovaen - Research and coding
Timeline
02/27 – Work on Final Project proposal
02/28 – Start research and learn to better use OpenCV
03/13 – Research finished, Continue implementation
03/15 – Finish MidTerm Report
03/27 – Project Update 1 (Tracking with OpenCV)
04/03 – Project Update 2 (Calibration and CG identifiers)
04/10 – Project Update 3 (Basic UI)
04/12 – FP_Preview Showing
04/17 – Project Update 4 (Touchups and improvements)
04/26 – FP_Final Showing
Links to this Page
- DVFX 2007 Groups last edited on 2 May 2007 at 12:51 am by coppola-win.cc.gatech.edu
- G2-Final Report last edited on 2 May 2007 at 5:18 am by coppola-win.cc.gatech.edu