Persönlicher Status und Werkzeuge

Home Research MeMoMan: Markerless Tracking of Human Motions

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
research:memoman [2011/08/01 16:14]
tenorth
research:memoman [2011/08/01 16:20] (current)
tenorth
Line 23: Line 23:
 Here are several videos to showcase the performance and different aspects of our work: Here are several videos to showcase the performance and different aspects of our work:
  
 +A short presentation video for a kitchen sequence with manipulation activities:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​2NtmgGLEox4&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​2NtmgGLEox4&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Tracking two subjects in a joint action scenario in the kitchen:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​xei_76e8ViE&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​xei_76e8ViE&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Tracking results on the HumanEva2 benchmark:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​6bBdmSORiDo&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​6bBdmSORiDo&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Ergonomic case studies on a car mock-up sequence:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​aVJMhuinLuo&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​aVJMhuinLuo&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +A 6.5 minute long sequence tracked at once:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​QxLJhZ-Ycww&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​QxLJhZ-Ycww&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Showing the effect of implicit environment modeling on the tracking outcome:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​mdKw7nV2e_I&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​mdKw7nV2e_I&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Self-training of motion models on the HumanEva2 S4 sequence. The tracker learns to improve its prediction of repetitive motion patterns over time. Previously observed motion patterns are shown in greyscale:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​W2kgbGO7r2o&​amp;​hl=en_US&​amp;​fs=1&​amp;"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​W2kgbGO7r2o&​amp;​hl=en_US&​amp;​fs=1&​amp;"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Using learned motion models to improve the prediction for environment- and task-specific activities. Trained motion patterns are shown in greyscale. The learned motion models can also be used for activity recognition:​
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​K6LVISs7bZI&​amp;​hl=en_US&​amp;​fs=1&​amp;"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​K6LVISs7bZI&​amp;​hl=en_US&​amp;​fs=1&​amp;"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +A kitchen sequence with random pick and place actions:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​WiCyEKFMSYc&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​WiCyEKFMSYc&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Another kitchen sequence with random pick and place actions:
 +
 +<​html><​object height="​385"​ width="​480"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​61gnFnl5PTI&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​61gnFnl5PTI&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +Another kitchen sequence, different actor:
 +
 +<​html><​object height="​385"​ width="​520"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​e2pd_wuFPWE&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​480"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​e2pd_wuFPWE&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
 +
 +
 +21 DOF upper-body-only motions showing the accuracy of the model:
 +
 +<​html><​object height="​385"​ width="​520"><​param name="​movie"​ value="​http://​www.youtube-nocookie.com/​v/​db9zchzZ_cw&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ /><​param name="​allowFullScreen"​ value="​true"​ /><​param name="​allowscriptaccess"​ value="​always"​ /><​embed width="​640"​ height="​385"​ src="​http://​www.youtube-nocookie.com/​v/​db9zchzZ_cw&​amp;​hl=en_US&​amp;​fs=1&​amp;​rel=0"​ type="​application/​x-shockwave-flash"​ allowscriptaccess="​always"​ allowfullscreen="​true"></​embed></​object></​html>​
  
  
Last edited 01.08.2011 16:20 by tenorth