How to Capture an image from a video played by a camera played using Deepstream-app?

How to Capture an image of person(covered by bounding box) detected using a pretrained model from a video that is being streamed by a USB camera played using Deepstream-app? I want to save this image frame only

I am capturing using the following command

deepstream-app -c /opt/nvidia/deepstream/deepstream-5.1/samples/configs/deepstream-app/source1_usb_dec_infer_resnet_int8.txt

Configuration:
NVIDIA Jetson Nano (Developer Kit Version)
L4T 32.5.1 [ JetPack 4.5.1 ]
Ubuntu 18.04.5 LTS
Kernel Version: 4.9.201-tegra
CUDA 10.2.89
CUDA Architecture: 5.3
OpenCV version: 4.1.1
OpenCV Cuda: NO
CUDNN: 8.0.0.180
TensorRT: 7.1.3.0

No, there is no such function in deepstream-app.

There is an object saving as image sample in deepstream-image-meta-test.

Please refer to the source code.