How to capture images and record short videos using kafka

Hi,

I would like to know how I can capture images and record short videos using kafka using the sample found in deepstream sample-app/deepstream-test4. but in our case we wish to implement this on @jkjung13’s MTCNN model for face detection.

thanks

Hi,

If your model can be inferenced with TensorRT.
You can deploy it with deepstream-test4 via updating the model-engine-file path.

If a customized parser is needed, please also update the parse-bbox-func-name and custom-lib-path parameter.
You can find several customized parser samples below:

/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_FasterRCNN/
/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_SSD/
/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo/

Thanks.