User Guide for Single Depth Sensor Configuration

From iPiSoft Wiki

(Difference between revisions)

Revision as of 14:17, 29 November 2011

System Requirements

CPU: x86 compatible (Intel Pentium 4 or higher, AMD Athlon or higher), dual- or quad- core is preferable
Operating system: Windows 7 (x86 or x64), Windows Vista (x86 or x64), Windows XP SP3 (x86 or x64)
Video card: Direct3D 10-capable (Shader Model 4.0) gaming-class graphics card (GeForce GTS 250 or Radeon HD 4850 or better recommended)
Microsoft Kinect Sensor (“Depth Sensor”) with separate power adapter
- If you bought "XBox 360 + Kinect" bundle then you need to order power adapter

Software Installation

iPi Recorder

Note that even if you have used iPi Recorder before you will need to perform actions below anyway. Just letting iPi Recorder to be updated automatically will not work, because drivers for MS Kinect Sensor must be installed in addition.

Before installation:

unplug MS Kinect Sensor from computer
deinstall libusb-win32 driver if it was used before (see http://ipisoft.com/forum/viewtopic.php?f=11&t=4932 for details)

iPi Recorder is a tool for recording video from web cameras and depth sensors. Download the setup package of iPi Recorder latest version: http://ipisoft.com/downloads/iPiRecorderSetup.exe. Run it. In the following dialog window make sure that item “PrimeSensor Driver (psdrv3) Registration for MS Kinect Sensor” is selected:

Note that if you do not plan to use Sony PlayStation Eye cameras then you can deselect the appropriate item in the list.

Click “Install” button to start the installation process. You’ll be asked about installation of “PrimeSensor Driver (psdrv3) Registration for MS Kinect”:

Please read license agreement and accept it by checking the appropriate checkbox. Then press “Install” button. As soon as you get the Windows Security screen, please select “Install this driver software anyway”:

At this point the driver will complete its installation and should not give any other errors:

After that iPi Recorder itself will be installed:

After that, connect MS Kinect Sensor to your PC. Under Windows Vista and Windows 7 device initialization should be performed automatically and you’ll receive notification about it in the system tray area. Under Window XP you’ll be asked three times (for “Xbox NUI Motor”, “Xbox NUI Audio” and “Xbox NUI Camera”):

“Can Windows connect to Windows Update to search for software?”
“What do you want the wizard to do?”

In all three cases answer “No, not this time” and “Install the software automatically (Recommended)” respectively:

Run iPi Recorder and make sure that there is “MS Kinect Sensor” in “Camera Selector” dialog:

Select “MS Kinect Sensor (OpenNI)” and press “Ok” button. Make sure that you can see colored “depth video” from sensor, that actual frame rate is 30 fps, that frames drop is in range from 0 to 5 and that you can change motor position using appropriate slider:

Note that values of Tilt and Roll are updated with a time lag. During recording these values cannot be updated assuming that in this case sensor should be static.

iPi Studio

Note that if you have used iPi Studio before and have Internet connection on your computer then you only need to let iPi Studio to automatically update:

iPi Studio is a core software of iPi Desktop Motion Capture (iPi DMC) solution. It’s used to process pre-recorded video and export resulted animation into most popular formats. You can use 30 days free trial. To install iPi Studio please download and run setup program: http://ipisoft.com/downloads/iPiStudioSetup.exe. Then, follow instructions of the installation wizard.

As a result of installation, iPi Studio will be executed. You will be prompted to enter your license key or start 30-days free trial period:

For more info about license protection see License.

Recording Video from Depth Sensor

Finally, after all these preparations completed, you are ready for performance.

Environment

It is convenient to put MS Kinect Sensor on a chair or a table. The picture below will help you to understand possible capture area and required space:


Side view	Top view

Actor Clothing

Current version uses only depth information to track motions. So clothes requirements are:

no restrictions on clothes colors (just avoid shiny fabrics)
please use slim clothes to reduce noise in resulted animation

Recording Process

Please start iPi Recorder and choose “MS Kinect Sensor (OpenNI)” in Camera Selector dialog:

Using “Motor” slider, adjust direction of sensor so that you can see floor at the bottom and actor is fully visible (with hands up if needed):

Set output directory for recorded video:

Press “Start Video Recording” button to begin video recording.

Important! Initial two seconds of video should contain only background and static objects. Presence of actor or any moving objects in the initial two seconds of recorded video is unacceptable. It’s because initial seconds of video are used to calculate static background necessary to separate actor from other objects of 3D scene.

As soon as recorder starts and “clear” scene is recorded for a couple of seconds, go to the capture area and stand in a T-pose:

After that you can act desired motions.

To stop recording, press “Stop Video Recording” button.

Using Windows Explorer, go to destination folder and open the recorded file with name video_YYYY-MM-DD_hh-mm-ss.avi in Windows Media Player. You should see depth information as a blue image:

Now you are ready for processing this video using iPi Studio.

Processing Video from Depth Sensor

Run iPi Studio
Press Ctrl+O or push “Open” button on toolbar
Choose recorded avi file
In the “Select Video Layout” dialog select the following values:
- Depth video from MS Kinect Camera
- Numbers of cameras: 1
- Resolution: 640x480

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

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.

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.

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 arms/torso/legs morph using appropriate sliders from “Actor” tab.

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, check “Enable foot tracking” and “Enable shoulders tracking” checkboxes
To start tracking just push “Track Forward” button

Wait and watch...

Post-Processing

iPi Studio includes integrated animation clean-up and motion transfer. So you do not necessarily need expensive third-party software like Motion Builder. These tools are included in all editions (compare editions).

Clean-up

Animation export and motion transfer

Video Materials

Demo video

iPiSoft Motion Capture Workflow from Paul Stapelberg

"Car scene" by JeanDellac

Animation by NextGenReport

"First results" from Radiac

Frequently Asked Questions

Q: Is tracking realtime?

A: Not yet. You should capture video first and process the video offline after that. Speed of processing depends on your graphics card (this is a GPGPU application so a fast video card is recommended).

Q: Does iPi Mocap System support facial motion capture?

A: No, not yet.

Q: Can hands/fingers be tracked by iPi Mocap System?

A: No, not yet. Resolution of consumer-class cameras is not enough for that.

Q: What about head tracking?

A: Head tracking is not implemented as of yet but it is being developed.

Q: What output formats are supported by iPiStudio?

A: iPiStudio can export animations in many popular formats. For a full list please see Animation export and motion transfer.

Q: Is FBX format supported?

A: Yes.

Q: Can I retarget captured animation to my own character?

A: Yes. iPi Studio has built-in motion transfer. For more info please see Animation export and motion transfer.

Q: Can I use two or three Kinects with iPi Mocap System?

A: Not yet. Current version supports only one Kinect sensor.

Q: What drivers for Kinect are used in iPi Mocap System?

A: We use a lightweight solution based on the driver from PrimeSense (psdrv3.sys) to communicate with device via USB. Protocol implementation is our own.

Q: Is this driver compatible with OpenNI and Brekel plugin?

A: Yes. If you have already installed PrimeSense's OpenNI drivers for Kinect then there is no need to install drivers again thus you can deselect item “PrimeSensor Driver (psdrv3) Registration for MS Kinect Sensor” during iPi Recorder installation.

Q: Can I use OpenKinect drivers instead?

A: Yes, this is possible for compatibility but the performance will be sub-optimal. Install OpenKinect drivers and deselect item “PrimeSensor Driver (psdrv3) Registration for MS Kinect Sensor” during iPi Recorder installation. But note that OpenKinect driver is not stable and can cause a hang up of a slow computer.

Q: What does "iPi DMC" means?

A: "iPi DMC" is the abbreviation of "iPi Desktop Motion Capture". iPi Mocap System consists of:

iPiRecorder - a tool for recording video from web cameras and depth sensors;
iPiStudio - software application for processing pre-recorded video and exporting resulting animation.

Q: Is there a version for Mac?

A: To run this software on a Mac you need to install Windows on your Mac using Boot Camp or similar solution.

Q: How can I buy this software?

A: You can buy online.

@@ Line 173: / Line 173: @@
 * Wait and watch...
-== Next Steps ==
+== Post-Processing ==
-* [[Clean-up]]
+{{:Post-Processing}}
-* [[Animation export and motion transfer]]
 == Video Materials ==