NEW!  Version 3 of iPi Motion Capture is available. iPi Motion Capture 3 delivers new features for improved workflow including support of Kinect 2, improved arms tracking, simplified calibration and others. Read more >>

This documentation corresponds to version 2 of iPi Motion Capture. The latest documentation for version 3 can be found at https://docs.ipisoft.com/

Processing a video from a depth sensor

From iPiSoft Wiki
(Difference between revisions)
Jump to: navigation, search
m
 
(8 intermediate revisions by 2 users not shown)
Line 1: Line 1:
* Run iPi Studio
+
* Run [[iPi Mocap Studio]]
* Press <tt>Ctrl+O</tt> or push “Open” button on toolbar
+
* Press <tt>Ctrl+N</tt> or push '''New''' button on toolbar to create new project
* Choose recorded <tt>avi</tt> file
+
* Choose recorded [[.iPiVideo file extension|'''*.iPiVideo''']] file
* In the “Select Video Layout” dialog select the following values:
+
* After video opened, background will be calculated automatically and position of camera will be detected based on floor plane.
** <tt>Depth video from MS Kinect Camera</tt>
+
* Make sure, that floor is detected correctly:
** Number of cameras: <tt>1</tt>
+
*# Right mouse button down on 3d view port area
** Resolution: <tt>640x480</tt>
+
*# Move mouse, as a result 3d scene will be rotated
 +
*# Right mouse button up
 +
*# Visually control that 3d points from floor are located on ground plane which is marked by squared grid
  
[[Image:KSensor-process-step1.png|center]]
+
[[Image:KSensor-process-step2.png|center|400px]]
  
* After opwning the video iPiStudio will automatically calculate background and ground plane. Please do not interrupt this calculation.
+
::'''Note''' that you always can get back to the camera point of view by pressing <tt>'''1'''</tt> key  on keyboard or pushing “Camera 1” button on toolbar
* Make sure that ground plane is detected correctly:
+
*# Push right mouse button and drag to rotate 3d scene
+
*# Review 3D scene
+
*# Make sure that the virtual ground plane (marked by squared grid) matches the ground points as detected by depth sensor.
+
  
[[Image:KSensor-process-step2.png|center]]
+
* Save created project by pressing <tt>Ctrl+S</tt> or pushing button '''Save''' on toolbar
 +
* Position timeline slider to the frame where actor is in T-pose
 +
* Adjust actor height using appropriate slider on tab '''Actor'''
 +
* Select '''Move''' tool on toolbar.
 +
* Move actor model to left or right to match roughly actor silhouette on video. Note that actor model can look smaller due to its position along axis of view. Don’t pay attention to it on this step.
  
::'''Note''' that you can always get back to the camera point of view by pressing <tt>'''1'''</tt> key on your keyboard or pushing “Camera 1” toolbar button
+
[[Image:KSensor-process-step3.png|center|600px]]
  
* Save the project by pressing <tt>Ctrl+S</tt> or pushing the “Save” toolbar button.
+
* Switch to '''Tracking''' tab and push '''Refit pose''' button.
* Position timeline slider to the frame where actor is in T-pose.
+
* As a result model should be matched with actor image from video. If it does not happen then delete result using item '''Edit > Delete pose''' from main menu and repeat above actions.
* Adjust actor height using appropriate slider on “Actor” tab.
+
* Select the “Move” tool on toolbar.
+
* Move actor model to match actor silhouette on depth video. You do not need to be very accurate. Note that actor model can look smaller due to its position along axis of view.  
+
  
[[Image:KSensor-process-step3.png|center|484px|Click to enlarge]]
+
[[Image:KSensor-process-step4.png|center|600px]]
  
* Switch to “Tracking” tab and push “Refit pose” button.
+
* Using the slider right to the button '''Show Skin''' in toolbar, make sure that morph of model corresponds to the actor image. If no, than adjust chest/bust/waist/hips/belly morph using appropriate sliders from '''Actor''' tab.
* As a result model should be matched with actor image from video. If it does not happen then delete result using item “Edit” -> “Delete pose” from main menu and repeat above actions.
+
 
+
[[Image:KSensor-process-step4.png|center|483px|Click to enlarge]]
+
 
+
* Use sliders on “Actor” tab to morph arms/torso/legs of the model to better correspond to the actor body shape.  
+
  
 
[[Image:KSensor-process-step4a.png|center]]
 
[[Image:KSensor-process-step4a.png|center]]
  
* Set the beginning of Region-of-Interest (ROI) to the current frame with T-pose by pressing <tt>'''I'''</tt> key on keyboard or by double-clicking on the left edge of ROI bar under timeline.
+
* Set the beginning of '''Region-of-Interest''' (ROI) to the current frame with T-pose by pressing <tt>'''I'''</tt> key on keyboard or by double-clicking on the left edge of ROI bar under timeline.
* Switch to “Tracking” tab, check “Enable foot tracking” and “Enable shoulders tracking” checkboxes.
+
* Switch to '''Tracking''' tab, change tracking options ('''Head tracking''', '''Shoulders''' and '''Spine''') if required.
* Push “Track Forward” button to start tracking.
+
* To start tracking just push '''Track Forward''' button.
 
+
[[Image:KSensor-process-step5.png|center|483px|Click to enlarge]]
+
  
* Wait for iPiStudio to process the video.
+
[[Image:KSensor-process-step5.png|center|600px|Click to enlarge]]
  
You may find the following video tutorial useful:
+
* Wait and watch...
[http://vimeo.com/24073249 iPiStudio/Kinect video tutorial] by [http://www.paulstapelberg.com/ Paul Stapelberg]
+
<html><iframe src="http://player.vimeo.com/video/24073249?title=0&amp;byline=0&amp;portrait=0" width="480" height="270" frameborder="0"></iframe></html>
+

Latest revision as of 19:10, 19 February 2014

  • Run iPi Mocap Studio
  • Press Ctrl+N or push New button on toolbar to create new project
  • Choose recorded *.iPiVideo file
  • After video opened, background will be calculated automatically and position of camera will be detected based on floor plane.
  • Make sure, that floor is detected correctly:
    1. Right mouse button down on 3d view port area
    2. Move mouse, as a result 3d scene will be rotated
    3. Right mouse button up
    4. Visually control that 3d points from floor are located on ground plane which is marked by squared grid
KSensor-process-step2.png
Note that you always can get back to the camera point of view by pressing 1 key on keyboard or pushing “Camera 1” button on toolbar
  • Save created project by pressing Ctrl+S or pushing button Save on toolbar
  • Position timeline slider to the frame where actor is in T-pose
  • Adjust actor height using appropriate slider on tab Actor
  • Select Move tool on toolbar.
  • Move actor model to left or right to match roughly actor silhouette on video. Note that actor model can look smaller due to its position along axis of view. Don’t pay attention to it on this step.
KSensor-process-step3.png
  • Switch to Tracking tab and push Refit pose button.
  • As a result model should be matched with actor image from video. If it does not happen then delete result using item Edit > Delete pose from main menu and repeat above actions.
KSensor-process-step4.png
  • Using the slider right to the button Show Skin in toolbar, make sure that morph of model corresponds to the actor image. If no, than adjust chest/bust/waist/hips/belly morph using appropriate sliders from Actor tab.
KSensor-process-step4a.png
  • Set the beginning of Region-of-Interest (ROI) to the current frame with T-pose by pressing I key on keyboard or by double-clicking on the left edge of ROI bar under timeline.
  • Switch to Tracking tab, change tracking options (Head tracking, Shoulders and Spine) if required.
  • To start tracking just push Track Forward button.
Click to enlarge
  • Wait and watch...
Personal tools