How to store detection results as images from n stream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
#1

Hello ,

Presently I am able to save all the images which are given as input to the system using get_converted_mat() function. I am in need of only those images which have detected objects.

In gstdsexample.cpp file ,

gst_dsexample_transform_ip()
{
…
if (frame[i].num_obj_meta > 0 )
{
if (get_converted_mat (dsexample, surface, i, &rect_params,
scale_ratio, dsexample->video_info.width,
dsexample->video_info.height) != GST_FLOW_OK) {
goto error;
}

}
…
}

Using this if loop I am able to get only few , detected images . However not every detected images. Would be glad if you can give me some inputs on the same ?

#2

All detection inference result are saved in frame metadata, like object label, object bbox,source id, can you filter the detected images according to metadata?

#3

Using above code I have tried to retrieve all detected images. However it is not covering every detected images. However the detection results which are obtained in side kitti-output-directory is correct. So code is doing the perfect things , but I am unable to retrive all images from all 8 streams at the same time.

#4

Have you resolved this issue? if not can you share one sample code for further check?

#5

Hi,

Any luck with saving the image when an object is detected ? I would like to also do the same.

Thanks

Alan.

#6

Hi bhargav.ravat.

We haven’t heard back from you in a couple weeks, so marking this topic closed.
Please open a new forum issue when you are ready and we’ll pick it up there.

Hi Alan,

Please help to open a new topic for your issue.

#7