False Positives After 99 Frames

[eliahaghbin]

I am utilizing your code to segment and track multiple fish in a video. However, I am encountering an issue where the algorithm detects 96 fish instead of the 32 selected after frame 99, including numerous false positives in the background. Could there be any hardcoded parameters causing this error from frame 100 onwards? Additionally, are there any adjustments I can make to reduce these false positives?

[RCLaplace]

I encountered the same problem

[Yashi-Nan]

same issue, unexpected objects were segmented

[ebozcal]

The reason for this is that SAM is involving by default after the 99th frame and automatically detects the other objects. To avoid this, you can simply increase the SAM gap which is 100 by default in the web app to a number higher than your current frame numbers.