Deepstream 9.0 nvdsosd cpu mode show black border when using multiple stream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) 3090RTX
• DeepStream Version 9.0
• JetPack Version (valid for Jetson only)
• TensorRT Version deepsteram 9.0 isntallation guide
• NVIDIA GPU Driver Version (valid for GPU only) 590
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

i try to use multiple stream in deepstream 9.0 (using deepstream python binding_ but when i change nvdsosd to cpu-mode i get a black border in video
Screenshot from 2026-06-29 11-35-43

3

Which sample are you testing? what is the complete media pipeline? The issue can’t be reproduced by the following gst-launch command-line. could you prvoide a simplifed gst-launch pipeline or simplifed code to reproduced the issue? Thanks!

gst-launch-1.0 filesrc location=/opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 ! qtdemux  ! h264parse ! nvv4l2decoder ! mux.sink_0 nvstreammux name=mux batch-size=1 width=1920 height=1080 ! nvinfer config-file-path=dstest1_pgie_config.yml ! nvmultistreamtiler  ! nvvideoconvert ! 'video/x-raw(memory:NVMM),format=RGBA' ! nvdsosd process-mode=0 !  nvvideoconvert ! 'video/x-raw(memory:NVMM),format=I420' ! nvv4l2h264enc bitrate=1000000 ! filesink location=test_cpu.264  filesrc location=/opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 ! qtdemux ! h264parse ! nvv4l2decoder !  mux.sink_1
4

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.

5

i foind out that when i use cnvmultistreamtiler this happends to me

6

Thanks for the update! could you provide the reproducing steps? Thanks!
As shown in the screenshot , the issue can’t be reproduced using the following cmd, which uses nvdsosd(cpu mode) and nvmultistreamtiler.

gst-launch-1.0 filesrc location=/opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 ! qtdemux  ! h264parse ! nvv4l2decoder ! mux.sink_0 nvstreammux name=mux batch-size=1 width=1920 height=1080 ! nvinfer config-file-path=dstest1_pgie_config.yml ! nvmultistreamtiler  ! nvvideoconvert ! 'video/x-raw(memory:NVMM),format=RGBA' ! nvdsosd process-mode=0 !  nvvideoconvert ! 'video/x-raw(memory:NVMM),format=I420' ! nvv4l2h264enc bitrate=1000000 ! filesink location=test_cpu.264  filesrc location=/opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 ! qtdemux ! h264parse ! nvv4l2decoder !  mux.sink_1

image
image680×365 81.3 KB

7

i fix this issue by changing nvbuf of all element to unified.
my pipeline was like this
8 nvurisrcbin → nvstreammxu → nvinfer → nvmultistreamtiler → nvdsosd → egeglesink

8

To reproduce this issue, which python sample are testing or referring to? you mean the issue will be fixed after adding the following codes for all nv plugins? the issue will remain without the following codes? Or could you provide a simplifed codes? Thank you!

        mem_type = int(pyds.NVBUF_MEM_CUDA_UNIFIED)
        plugin.set_property("nvbuf-memory-type", mem_type)