Tracking Object Merger

Purpose

This package try to merge two tracking objects from different sensor.

Inner-workings / Algorithms

Merging tracking objects from different sensor is a combination of data association and state fusion algorithms.

Detailed process depends on the merger policy.

decorative_tracker_merger

In decorative_tracker_merger, we assume there are dominant tracking objects and sub tracking objects. The name decorative means that sub tracking objects are used to complement the main objects.

Usually the dominant tracking objects are from LiDAR and sub tracking objects are from Radar or Camera.

Here show the processing pipeline.

time sync

Sub object(Radar or Camera) often has higher frequency than dominant object(LiDAR). So we need to sync the time of sub object to dominant object.

data association

In the data association, we use the following rules to determine whether two tracking objects are the same object.

• gating
  • distance gate: distance between two tracking objects
  • angle gate: angle between two tracking objects
  • mahalanobis_distance_gate: Mahalanobis distance between two tracking objects
  • min_iou_gate: minimum IoU between two tracking objects
  • max_velocity_gate: maximum velocity difference between two tracking objects
• score
  • score used in matching is equivalent to the distance between two tracking objects

tracklet update

Sub tracking objects are merged into dominant tracking objects.

Depends on the tracklet input sensor state, we update the tracklet state with different rules.

tracklet management

We use the existence_probability to manage tracklet.

• When we create a new tracklet, we set the existence_probability to $p_{sensor}$ value.
• In each update with specific sensor, we set the existence_probability to $p_{sensor}$ value.
• When tracklet does not have update with specific sensor, we reduce the existence_probability by decay_rate
• Object can be published if existence_probability is larger than publish_probability_threshold and time from last update is smaller than max_dt
• Object will be removed if existence_probability is smaller than remove_probability_threshold and time from last update is larger than max_dt

These parameter can be set in config/decorative_tracker_merger.param.yaml.

tracker_state_parameter:
  remove_probability_threshold: 0.3
  publish_probability_threshold: 0.6
  default_lidar_existence_probability: 0.7
  default_radar_existence_probability: 0.6
  default_camera_existence_probability: 0.6
  decay_rate: 0.1
  max_dt: 1.0

input/parameters

Default parameters are set in config/decorative_tracker_merger.param.yaml.

• the detail of tracker_state_parameter is described in tracklet management

File truncated at 100 lines see the full file

Changelog for package autoware_tracking_object_merger

0.53.0 (2026-09-29)

0.52.0 (2026-06-30)

• Merge remote-tracking branch 'origin/main' into tmp/bot/bump_version_base

• chore(data_association_matrix.param.yaml): remove OVERRIDE marker from master file (#12802) chore: remove OVERRIDE marker from master file

• feat(autoware_tracking_object_merger): update parameter to add ANIMAL and HAZARD classes (#12778) update parameter to add ANIMAL and HAZARD classes

• feat(decorative_tracker_merger): apply [agnocast_wrapper::Node]{.title-ref} to [decorative_tracker_merger]{.title-ref} (#12709)

  • apply agnocast_wrapper::Node
  • fix
  • style(pre-commit): autofix
  • fix clang-format
  • fix cpplint

  * apply copilot fix ---------Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>

• Contributors: Koichi Imai, Masaki Baba, Taeseung Sohn, github-actions

0.51.0 (2026-05-01)

• Merge remote-tracking branch 'origin/main' into tmp/bot/bump_version_base

• feat(perception): replace autoware_universe_utils with specific autoware_utils sub-packages (#12425)

• chore(perception): move perception node configuration file to each package (#12440) move perception node configuration file to each package

• feat(decorative_tracker_merger): apply autoware_agnocast_wrapper for CIE (#12331) feat(autoware_tracking_object_merger): apply autoware_agnocast_wrapper for CIE

• refactor(autoware_universe): use autoware_ament_auto_package in perception packages (#12275) Co-authored-by: github-actions <<github-actions@github.com>>

• perf(perception): use emplace_back and emplace to avoid temporary object creation (#12201)

  • perf(perception): use emplace_back to avoid temporary object creation
  • style(pre-commit): autofix
  • perf(perception): use emplace/emplace_back for most containers

  * style(pre-commit): autofix ---------Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com> Co-authored-by: Taekjin LEE <<taekjin.lee@tier4.jp>>

• feat(autowar_tracking_object_merger): remove glog (#12165) feat: remove glog

• Contributors: Taekjin LEE, Tetsuhiro Kawaguchi, Vishal Chauhan, atsushi yano, github-actions, nishikawa-masaki

0.50.0 (2026-02-14)

• Merge remote-tracking branch 'origin/main' into humble
• feat!: remove ROS 2 Galactic codes (#11905)
• Contributors: Ryohsuke Mitsudome

0.49.0 (2025-12-30)

0.48.0 (2025-11-18)

• Merge remote-tracking branch 'origin/main' into humble
• fix: tf2 uses hpp headers in rolling (and is backported) (#11620)
• Contributors: Ryohsuke Mitsudome, Tim Clephas

0.47.1 (2025-08-14)

File truncated at 100 lines see the full file