My platform is GPU and I am using DeepStream 6.1 with 8.2.5 TensorRT. Driver Version: 510.85.02
I used gstdsexample_optimized.cpp to save images of the detected objects, however when there is more than one detected object in the same frame plugin only save the one of them. Is there any way to save all cropped images as a batch form.
And how the solution can be extended to work with more than one stream.
Same problem here. Any solution yet?
which deepstream app are you testing? how to reproduce this issue?
Thanks for fast reply.
I used custom application with modified gstdsexample plugin.
I use similar approach in the link to save detected objects. But it can only save one object per frame.
how did you save the objects？ please refer to deepstream sample deepstream-image-meta-test, it can save objects to pictures.
Yes I can save the objects via the probe. But I tried to extract the functionality of saving images to another plugin to boost the performance.
did you still need support? from your link code, need to add object id in IMpath .
IMpath = IMpath + std::to_string(dsexample->frame_num) +“_new” + “.jpg”;
please refer to gstdsexample.cpp code below DSEXAMPLE_DEBUG.
There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.