Dcf tracker issue

Hi
I am using deepstream 4.02. I observed that DCF not able to tracker a single person which moving inside the closed area.
Camera is put on ceiling and person is clearly visible. Person detection model output is satisfactory but tracking is not good.
Some time frequently ID get change in single person tracking. Some time tracker is not able to tracke a person standing for some time.
Below the configuration that I used for DCF
%YAML:1.0

NvDCF:
maxTargetsPerStream: 30 # Max number of targets to track per stream. Recommended to set >10. Note: this value should account for the targets being tracked in shadow mode as well. Max value depends on the GPU memory capacity

filterLr: 0.1 # learning rate for DCF filter in exponential moving average. Valid Range: [0.0, 1.0]
gaussianSigma: 0.75 # Standard deviation for Gaussian for desired response when creating DCF filter

minDetectorConfidence: 0.4 # If the confidence of a detector bbox is lower than this, then it won’t be considered for tracking
minTrackerConfidence: 0.6 # If the confidence of an object tracker is lower than this on the fly, then it will be tracked in shadow mode. Valid Range: [0.0, 1.0]

featureImgSizeLevel: 5 # Size of a feature image. Valid range: {1, 2, 3, 4, 5}, from the smallest to the largest
SearchRegionPaddingScale: 3 # Search region size. Determines how large the search region should be scaled from the target bbox. Valid range: {1, 2, 3}, from the smallest to the largest

maxShadowTrackingAge: 24 # Max length of shadow tracking (the shadow tracking age is incremented when (1) there’s detector input yet no match or (2) tracker confidence is lower than minTrackerConfidence). Once reached, the tracker will be terminated.
probationAge: 2 # Once the tracker age (incremented at every frame) reaches this, the tracker is considered to be valid
earlyTerminationAge: 4 # Early termination age (in terms of shadow tracking age) during the probation period

minVisibiilty4Tracking: 0.2 # If the visibility of the bbox of a tracker gets lower, then it will be terminated

could you suggest the best tuned parameters based on your experience?

Would you please move to use the latest DeepStream SDK 5.0.1 version?

Hi
I tried to tune parameters of DCF in latest version. Still single person is not able to track inside the room.

1.Plse make sure to use the latest DS version DS 5.0.1
2.Refer below section to tune maxShadowTrackingAge minTrackingConfidenceDuringInactive and minVisibiilty4Tracking to see if the issue is mitigated

Once the tracker for an object is activated, it is put into inactive mode only when (1) no matching detector input is found during the data association, or (2) the tracker confidence falls below a threshold defined by minTrackerConfidence. The per-object tracker will be put into active mode again if a matching detector input is found. The length of period during which a per-object tracker is in inactive mode is called the shadow tracking age; if it reaches the threshold defined by maxShadowTrackingAge, the tracker is terminated. Even if an object is being tracked in inactive mode, if the tracker confidence value is higher than minTrackingConfidenceDuringInactive, then the tracker will put the output into the metadata. Note if the value of minTrackingConfidenceDuringInactive is set too low, then some lingering bounding boxes may be observed occasionally after the objects disappear from the scene. If the bounding box of an object being tracked goes partially out of the image frame and so its visibility falls below a predefined threshold defined by minVisibiilty4Tracking, the tracker is also terminated.

For

Could you try as following section

Frequent tracking ID changes although no nearby objects

It is highly likely that the tracker cannot detect the target from the correlation response map. It is recommended to start with lower minimum qualification for the target. Thus first set minTrackerConfidence with a relatively low value like 0.5. Also, in case the state estimator is enabled, the prediction may not be accurate enough. Thus, one may consider tuning the state estimator parameters based on the expected motion dynamics.

In addition, it will be better if you can share the video with us.

will try your suggestion and let you know.