PROCESSOR-SDK-AM69A: Linux OS in SK - AM69 without setup or environment build in ubuntu.

Hi Ruban,

Unfortunately, the imshow function within OpenCV's library installed on the board cannot be used. 

You may use an alternative, GStreamer, to stream data in and out of the application. Please reference this thread: https://e2e.ti.com/support/processors-group/processors/f/processors-forum/1391318/am69a-alternative-of-imshow-function

Regards,

Takuma

Hi Takuma Fujiwara,

Thanks for the support and link. I the link provided they have provided detailed to use usb . Can I get more information on using CS0 connected imx219 camera to output to Gstreamer with this input I used for testing

  input0:
source: /dev/video-imx219-cam0
subdev-id: /dev/v4l-imx219-subdev0
width: 1920
height: 1080
format: rggb
framerate: 30

Can you modify this below with the above input 

import time
import cv2
fps = 30
frame_width = 640
frame_height = 480
cap = cv2.VideoCapture(0)

cap.set(cv2.CAP_PROP_FRAME_WIDTH, frame_width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, frame_height)
cap.set(cv2.CAP_PROP_FPS, fps)

gst_str = "appsrc name=source ! tiovxdlcolorconvert ! video/x-raw,format=NV12 ! kmssink driver-name=tidss sync=false"

out = cv2.VideoWriter(gst_str, 0, fps, (frame_width, frame_height), True)
while True:
    ret, frame = cap.read()
    out.write(frame)

out.release()
cap.release()

Thanks in advance.
Ruban

Hi Ruban,

We have examples in the SDK for how to use IMX219: https://software-dl.ti.com/jacinto7/esd/processor-sdk-linux-am69a/10_00_00/exports/edgeai-docs/common/edgeai_dataflows.html#object-detection

Please reference the input portion of the pipeline used here, and feel free to use gst-launch-1.0 tool to prototype your pipeline.

Regards,

Takuma

Hi Takuma Fujiwara,

Thanks for the information.

I am able to use gst-launch-1.0 tool and execute but in tat I change the shape of the output . My requirement is to reshape 4 camera to make in one frame such as bird eye view .I am able to create using opencv. So kindly help me to stream output using opencv for IMX219 camera

Thanks in advance.

Ruban

Hi Ruban,

Ruban A said:

So kindly help me to stream output using opencv for IMX219 camera

Do you need help with input or output?

I am aware of an input limitation with OpenCV where OpenCV only takes in BGR format (instead of more standard RGB or YUV). This can be worked around with GStreamer elements like videoconvert.

Or do you need help with output? I see that appsrc element is used in the shared code snippet, but is help needed here?

Regards,

Takuma

Hi Takuma Fujiwara,

Takuma Fujiwara said :

You need help with input or output?

Yes required both input and output.

Takuma Fujiwara said :

 do you need help with output? I see that appsrc element is used in the shared code snippet, but is help needed here?

Yes

Regards

Ruban

Hi Ruban,

Takuma is currently out of office on holiday, please expect a delay in response until next week.

Best,
Jared

Hi Ruban,

We have an old unoptimized data flow that uses GStreamer to stream data in to an app, then do some inferencing using deep learning runtimes, then some postprocessing using OpenCV, which is then outputted on to a screen. Refer to this pipeline here where gray box for post processing is OpenCV: https://software-dl.ti.com/jacinto7/esd/processor-sdk-linux-sk-tda4vm/10_00_00/exports/edgeai-docs/common/edgeai_dataflows.html#python-c-apps

The source code for this pipeline can be found here: https://github.com/TexasInstruments/edgeai-gst-apps/tree/main/apps_python

Regards,

Takuma