How to save the complete frame with bounding boxes in deepstream-image-meta-test

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) dGPU
• DeepStream Version 5
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only) 440.57

Can you suggest how to save the complete frame with bounding boxes instead of cropped objects. I am able to run deepstream-image-meta-test and generate the cropped images.

pls refer https://docs.nvidia.com/metropolis/deepstream/dev-guide/DeepStream_Development_Guide/baggage/group__ee__object__encoder.html

Can you please help with some code to save the complete frame instead of cropped objects?

@bcao @DaneLLL Any help in this regards is appreciated.

Hi,
Please check

There is osd_sink_pad_buffer_probe() in the sample. You can apply the same to source pad of nvdsosd.

Thanks. I will try and revert back.

Hi,
Another possible solution is to link nvdsosd ! tee like this pipeline:

$ gst-launch-1.0 uridecodebin uri=file:///home/nvidia/1080.mp4 ! mx.sink_0 nvstreammux width=1920 height=1080 batch-size=1 name=mx ! nvinfer config-file-path=/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_primary_nano.txt unique-id=7 ! nvvideoconvert ! nvdsosd ! tee name=t t. ! queue ! nvoverlaysink t. ! queue ! nvvideoconvert ! video/x-raw,format=RGBA ! videoconvert ! video/x-raw,format=BGR ! jpegenc ! multifilesink location=/tmp/dump_%03d.jpg

FYR.