What distance metric is used in ReID module used in the multObjectTracker in deepstream?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (GPU)
• DeepStream Version 7.0
• TensorRT Version 8.6.1
• NVIDIA GPU Driver Version (535)
• Issue Type( questions, new requirements, bugs)

I was using this in the config_tracker_NvDCF_accuracy.yml:

ReID:
  reidType: 2    # The type of reid among { DUMMY=0, NvDEEPSORT=1, Reid based reassoc=2, both NvDEEPSORT and reid based reassoc=3}

  # [Reid Network Info]
  batchSize: 100    # Batch size of reid network
  workspaceSize: 1000    # Workspace size to be used by reid engine, in MB
  reidFeatureSize: 256    # Size of reid feature
  reidHistorySize: 100    # Max number of reid features kept for one object
  inferDims: [3, 256, 128]    # Reid network input dimension CHW or HWC based on inputOrder
  networkMode: 1    # Reid network inference precision mode among {fp32=0, fp16=1, int8=2 }

  # [Input Preprocessing]
  inputOrder: 0    # Reid network input order among { NCHW=0, NHWC=1 }. Batch will be converted to the specified order before reid input.
  colorFormat: 0    # Reid network input color format among {RGB=0, BGR=1 }. Batch will be converted to the specified color before reid input.
  offsets: [123.6750, 116.2800, 103.5300]    # Array of values to be subtracted from each input channel, with length equal to number of channels
  netScaleFactor: 0.01735207    # Scaling factor for reid network input after substracting offsets
  keepAspc: 1    # Whether to keep aspc ratio when resizing input objects for reid

  # [Output Postprocessing]
  addFeatureNormalization: 1       # If reid feature is not normalized in network, adding normalization on output so each reid feature has l2 norm equal to 1
  minVisibility4GalleryUpdate: 0.6 # Add ReID embedding to the gallery only if the visibility is not lower than this

  # [Paths and Names]
  # onnxFile: "/home/ubuntu/landmark/falcon-zone-analytics-deepstream/onnx_models/swin_tiny_market1501_aicity156_featuredim256.onnx"
  modelEngineFile: "onnx_models/resnet50_market1501_aicity156.onnx_b100_gpu0_fp16.engine" # Engine file path

I wanted to get an idea regarding what kind of distance metric is used over the feature vector outputs from the ReIdentificationNet model. Is there any way to modify this distance calculation backend process?

3

The Re-ID similarity between a detector object and a target is the cosine similarity. You can refer here: Gst-nvtracker — DeepStream documentation 6.4 documentation
Why you need modify the distance calculation?

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

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