Hello All,
We are trying to test Video Driver(YUV16-1920*1080-30fps-CSI 2Lane) using Fpga CSI to Jetson Tx2 core board in Jetpack 4.2(L4T 32.3.1) for our customize carrier board !!
we compile Driver,and v4l2 video node is OK ,we are using for caputre frame this gstreamer pipeline in Tx2 Customized board::
gst-launch-1.0 v4l2src device="/dev/video0" ! "video/x-raw,width=1920,height=1080, format=(string)UYVY" ! nvvidconv ! 'video/x-raw(memory:NVMM),format=NV12,width=1920,height=1080,framerate=30/1' ! omxh264enc control-rate=1 bitrate=14000000 ! 'video/x-h264, stream-format=(string)byte-stream' ! rtph264pay ! udpsink host=IP_HOST port=5000 sync=false
but in EVM TX2,For caputre frame with OV5693-bayer10,1920*1080-30fps ,we use this gst pipeline::
gst-launch-1.0 nvarguscamerasrc ! 'video/x-raw(memory:NVMM), width=(int)1920, height=(int)1080, format=(string)NV12, framerate=(fraction)30/1' ! omxh264enc control-rate=1 bitrate=14000000 ! 'video/x-h264, stream-format=(string)byte-stream' ! h264parse ! rtph264pay mtu=1400 ! udpsink host=10.42.0.158 port=5000 sync=false
We calculated End to End time latency in EVM TX2 ov5693 gstreamer pipeline,is about 150 ms!!
and in Customized board TX2 ,YUV,gstreamer pipeline,Latency about 200 millisecond!!
The only difference between the two is,
Capture in ‘video / x-raw’ mode and convert to ‘memory:NVMM’ mode !!
Question1:
Do you think doing this will create a time delay frame?
Question2:
Do you have any suggestions for eliminating this delay ??
Thank you for your help!!