Jetson, Kinect V2(libfreenect2)

Now I trying that run libfreenect2 on Jetson TK1
and, there are some issues.

If you know, please some adbises.


1.I tried to adjust CPU clock and GPU clock
# cat /sys/kernel/cluster/active
G

# cat /sys/kernel/debug/clock/gbus/rate   
852000000 

2.And I use a mini PCI-Express USB3.0 19pin (Renesas nPD720200)
Power is on mora 4Pin on Jetson.

 After some tried, I used external power supply, but the same issue is happening 

3.Result of lsusb
$ lsusb
Bus 004 Device 001: ID 1d6b:0003 Linux Foundation 3.0 root hub
Bus 003 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 005 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 002 Device 003: ID 045e:02c4 Microsoft Corp.
Bus 002 Device 002: ID 045e:02d9 Microsoft Corp.
Bus 002 Device 001: ID 1d6b:0003 Linux Foundation 3.0 root hub
Bus 001 Device 002: ID 045e:02d9 Microsoft Corp.
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub

  1. I have installed them as described below.
    https://gist.github.com/jetsonhacks/1bd2830cc1a5790a6ac2#file-installlibfreenect2-sh


The following message is displayed when I start the Protonect.

It don’t show wondow depth, rgb, registred, …
but, I can’t see the message about depth.

I tried std::cout message the top of law of the “while loop” of the “main”
but, no message showed.
so dead lock at the “listener.waitForNewFrame(frames)”


$ sudo ./bin/Protonect
[sudo] password for ubuntu:
modprobe: FATAL: Module nvidia not found.
[CudaDepthPacketProcessorKernel::initDevice] device 0: GK20A @ 852MHz Memory 1892MB
[CudaDepthPacketProcessorKernel::initDevice] selected device 0
[Freenect2Impl] enumerating devices…
[Freenect2Impl] 8 usb devices connected
[Freenect2Impl] found valid Kinect v2 @2:3 with serial 017234451747
[Freenect2Impl] found 1 devices
[Freenect2DeviceImpl] opening…
[Freenect2DeviceImpl] opened
[Freenect2DeviceImpl] starting…
[Freenect2DeviceImpl] ReadData0x14 response
92 bytes of raw data
0x0000: 00 00 15 00 00 00 00 00 01 00 00 00 43 c1 1f 41 …C…A
0x0010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 …
0x0020: 0a 21 33 55 20 00 17 ba 00 08 00 00 10 00 00 00 .!3U …
0x0030: 00 01 00 00 00 10 00 00 00 00 80 00 01 00 00 00 …�…
0x0040: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 …
0x0050: 00 00 00 00 00 00 00 00 07 00 00 00 …

==== CuDepthPakePro CommandResponse ==== 1302882
[Freenect2DeviceImpl] ReadStatus0x090000 response
4 bytes of raw data
0x0000: 00 22 00 00 ."…

[Freenect2DeviceImpl] ReadStatus0x090000 response
4 bytes of raw data
0x0000: 00 22 00 00 ."…

[Freenect2DeviceImpl] enabling usb transfer submission…
[Freenect2DeviceImpl] submitting usb transfers…
[Freenect2DeviceImpl] started
device serial: 017234451747
device firmware: 2.3.3913.0.7
[TegraJpegRgbPacketProcessor] avg. time: 15.8725ms → ~63.0022Hz
[RgbPacketStreamParser::handleNewData] skipping rgb packet!
[RgbPacketStreamParser::handleNewData] skipping rgb packet!
[TegraJpegRgbPacketProcessor] avg. time: 15.9096ms → ~62.8553Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1333ms → ~66.0795Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1105ms → ~66.1793Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1506ms → ~66.0038Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1426ms → ~66.039Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1493ms → ~66.0098Hz
[TegraJpegRgbPacketProcessor] avg. time: 14.9997ms → ~66.6679Hz
[TegraJpegRgbPacketProcessor] avg. time: 14.4716ms → ~69.101Hz
[TegraJpegRgbPacketProcessor] avg. time: 14.429ms → ~69.3047Hz
[RgbPacketStreamParser::handleNewData] skipping rgb packet!
[TegraJpegRgbPacketProcessor] avg. time: 14.908ms → ~67.0779Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.0251ms → ~66.5553Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1235ms → ~66.1221Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1282ms → ~66.1015Hz
[TegraJpegRgbPacketProcessor] avg. time: 15.1414ms → ~66.0441Hz

Strange that it’s looking for the “nvidia” module, that gets loaded on x86 but I don’t believe it’s used on ARM. You might not have the correct version of libfreenect2, or perhaps there’s an incorrect dependency somewhere.

This article seems to be related to the link you posted, but might have some more info: Jetson TK1 with Microsoft Kinect using OpenKinect - JetsonHacks