Hi,
We have upgraded to Deepstream 6 and run a more thorough experiment:
Source: RTSP feed from an NVR. 25 fps
Ffprobe output: Stream #0:0: Video: hevc (Main), yuvj420p(pc), 2688x1520 [SAR 1:1 DAR 168:95], 25 tbr, 90k tbn, 90k tbc
Our deepstream app is deployed in a container based on: nvcr.io/nvidia/deepstream-l4t:6.0-samples
Setup 1: Pedestrian Only Model with Fast Inference Speeds:
- Pipeline runs at 24fps
- No grey artifacts from smart record clips. All high quality. Sample screenshot attached
Setup 2: Multi-class model with slow inference speed:
- Pipeline runs at 3fps
- Grey artifacts observed on almost all cmart record clips. Sample screenshot attached.
We ran an additional experiment, where from the cli (on host device, outside the container) we recorded multiple clips from the RTSP stream with ffmpeg, for 3 cases:
- deepstream app with slow model
- deepstream app with fast model
- no deepstream app deployed
and in each case the video clips were all artifact free with no grey blocks.
