Deepstream_app_sourse1_peoplenet.txt does not work smooth with Jetson nano

[KaoruMiya]

Hi,
I want to run deepstream_app_sourse1_peoplenet.txt with usb-camera in order to detect Human body .
so I change [source0] in deepstream_app_sourse1_peoplenet.txt and run it.
I look at the link page. Jetson nano’s fps is 11.

Here is link page
https://developer.nvidia.com/ja-jp/deepstream-sdk

but, my program works very slowly and The screen has often frozen.
Is it need more settings?
Thank you.

[Amycao]

1 Change sink type from nveglglessink to nvoverlaysink on Jetson.
2 If the GPU is the performance bottleneck, try increasing the interval at which the primary detector infers on input frames. You can do this by modifying the interval property of [primary-gie] group in the application configuration, or the interval property of the Gst-nvinfer configuration file.

[KaoruMiya]

I tried the two solutions you suggested and it worked smooth.
thanks a lot.

but after a short time, following message appears on terminal and fps slows down.

**PERF:  27.28 (29.71)	 

WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped. 

 Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): 

 /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink:sink_sub_bin_sink1: 

There may be a timestamping problem, or this computer is too slow. 

Could you tell me how can it works smooth?

[Amycao]

This message coming from gstreamer plugin. refer to this topic.
Gstreamer error - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums