Feat/core/refactor tracklet kalman filter#310
Open
AlexBodner wants to merge 78 commits intodevelopfrom
Open
Conversation
…w/trackers into feat/core/ocsort-release
…w/trackers into feat/core/ocsort-release
…d update also when unmatched detections = 0
…w/trackers into feat/core/ocsort-release
- Add `tracker_id = "ocsort"` class variable to enable CLI auto-registration via BaseTracker's registry mechanism - Export OCSORTTracker in `__all__` for public API discoverability
- Remove module-level docstring from state_representations.py - Remove section divider comment from state_representations.py - Remove duplicate/truncated headers from converters.py and kalman_filter.py
double backticks in state_representations.py.
- Add backticks to variable references (`x1`, `y1`, `scale`, etc.)
- Replace Sphinx-style :class:/:meth: with plain backticks
- Remove bullet points (poor mkdocs rendering)
- Expand StateRepresentation, XCYCSRKalmanFilter, XYXYKalmanFilter
docstrings with variable explanations and behavioral implications
- Add doctests with full input/output examples - Add unit tests covering conversions, edge cases, and round-trips - Add API documentation under Trackers > Utilities section
…eemed redundant because oc-sort activates them earlier
…er evaluating in sportsmot and getting same metrics
…es of StateKalmanFilters
…-tracklet-kalman-filter
…ecause we changed kalman filter it uses and now the initialization is aligned to the original implementation
…s the original one from byte
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Refactors KalmanBoxTracker to Tracklet classes so decouples Kalman Filter logic from the tracklet, also creating a unique Kalman Filter that will be used by all the algorithms based on the OC-SORT paper implementation of the KF. This also supports swappable kalman filter state coordinates, using the abstraction StateEstimator.
Beware that:
OC-SORT and SORT metrics remain the same BUT ByteTrack ones has small changes (at least with default parameters) because it now uses the same kalman filter as OC-SORT (which has slight differences in implementation that make it better in OC-SORT) but here it drops 0.1%. Initialization for bytetrack remains the same as we now support custom initializations per tracker.
ByteTrack has a behaviour difference wrt other trackers, to match original it initializes tracklets number_of_successful_consecutive_updates to 1, while in the other ones it is initalized to 0. Changing this gives slighter worse performance (-2% HOTA). So we might have to consider changing something around this to have same behaviour out of same parameters around trackers.
Type of Change