Pixel distortion in RTSP camera with Deepstream 6.0

Hi,

I am developing an app with Deepstream SDK 6.0 on a computer using a 3060 dGPU card.

Im testing with only one RTSP stream and the RTSP output but the image is very distorted sometimes.

The RTSP camera streaming is configured with a bitrate at its minimum with a 1920x1080 resolution set to 10 FPS.

This is what the streaming output of Deepstream app looks like:

This only happens in the Deepstream output stream.

The configuration I’m running on Docker with deepstream6.0-devel image:

[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
#gie-kitti-output-dir=streamscl

[ds-example]
enable=1
processing-width=1920
processing-height=1080
session-string=FUNCI
full-frame=0
#batch-size for batch supported optimized plugin
batch-size=1
unique-id=15
gpu-id=0
blur-objects=1
# Supported memory types for blur-objects are 1 and 3
nvbuf-memory-type=3


[source0]
enable=1
type=4
uri=rtsp://xxxxx
drop-frame-interval=0
gpu-id=0
rtsp-reconnect-interval-sec=600
rtsp-reconnect-attempts=-1
cudadec-memtype=0
num-sources=1
camera-fps-n=10
camera-fps-d=1


[streammux]
gpu-id=0
live-source=1
batch-size=1
batched-push-timeout=80000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0
## If set to TRUE, system timestamp will be attached as ntp timestamp
## If set to FALSE, ntp timestamp from rtspsrc, if available, will be attached
# attach-sys-ts-as-ntp=1


# PRIMARY DETECTOR
[primary-gie]
enable=1
gpu-id=0
model-engine-file=./models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine
batch-size=1
bbox-border-color0=0.6;0.6;1;1
bbox-border-color1=0.6;0.6;1;1
bbox-border-color2=0.8;0.8;0.9;1
bbox-border-color3=0.8;0.8;0.9;1
interval=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=./configs/Primary_Detector/config_infer_primary.txt


# SECONDARY DETECTOR: Faces, License Plates
[secondary-gie0]
enable=1
gpu-id=0
gie-unique-id=2
config-file=./configs/Secondary_FaceDetect/secondary_detector_config.txt
batch-size=1
operate-on-gie-id=1
operate-on-class-ids=0;1;2


[tracker]
enable=1
tracker-width=640
tracker-height=384
ll-lib-file=/opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_nvmultiobjecttracker.so
ll-config-file=./configs/Trackers/config_tracker_NvDCF_perf.yml
gpu-id=0
enable-batch-process=1
enable-past-frame=1
display-tracking-id=1
# NVIDIA only
compute-hw=1


[osd]
enable=1
gpu-id=0
border-width=2
text-size=8
text-color=1;1;1;1
text-bg-color=0;0;0;1
font=Serif
show-clock=1
clock-x-offset=5
clock-y-offset=20
clock-color=1;1;1;1
clock-text-size=12
clock-color=0;0;0;1
nvbuf-memory-type=0


[sink0]
enable=1
type=4
codec=1
enc-type=0
sync=0
# Resolutions: 540p = 1500 kpbs, 720p = 4000 kbps, 1080p = 8000 kbps 
bitrate=4000000
profile=0
rtsp-port=8554
udp-port=5400
udp-buffer-size=524288
#source-id=0


[sink1]
enable=1
type=6
msg-conv-config=./configs/msgconv_sample_config.txt
msg-conv-payload-type=1
msg-broker-proto-lib=/opt/nvidia/deepstream/deepstream/lib/libnvds_kafka_proto.so
# IP of my kafka server
msg-broker-conn-str=xxx.xxx.xxx.xxx;9092;test-topic
topic=test-topic


[tests]
file-loop=0

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.0 (docker image: nvcr.io/nvidia/deepstream:6.0-devel)
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.0.1-1 + CUDA 11.3
• NVIDIA GPU Driver Version (valid for GPU only) 470.129.06

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Hi @carloselilopezt , cause we don’t have your env and rtsp source.
Can you use the gst-launch-1.0 cli command to play your source?
You can refer below and learn something about gst-launch-1.0.

gst-launch-1.0 rtspsrc location=RTSP_URL ! rtph264depay ! queue ! h264parse ! nvv4l2decoder ! nvvideoconvert ! "video/x-raw(memory:NVMM),format=RGBA" ! nvegltransform ! nveglglessink sync=False

Then, you can get the stream from any plugin node (before decoder, after decoder, the original source…). Please help us to find where the pixel distortion begin. Thanks

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.