SORTTrackerInference
Python template · sinapsis_rf_trackers.templates.sort_tracker_inference
Overview
This template provides the logic to use the SORT tracker from Roboflow's trackers library. It processes detection annotations from upstream templates and adds tracking IDs to maintain object identity across video frames.
Capabilities
Capabilities: not setInstallation
Install the published package using pip or uv.
pip install sinapsis-rf-trackers==1.0.0uv pip install sinapsis-rf-trackers==1.0.0uv add sinapsis-rf-trackers==1.0.0Configuration
Effective fields from the inspector schema, including nested Pydantic model fields.
Optional
Default: null
The frame rate of the video sequence being processed. This affects the temporal dynamics of the tracking algorithm. Defaults to 30.0.
Optional
Default: 30
Number of frames to buffer when a track is lost. Increasing lost_track_buffer enhances occlusion handling, significantly reducing the likelihood of track fragmentation or disappearance caused by brief detection gaps. Defaults to 30.
Optional
Default: 30
Minimum IoU threshold for associating detections with tracks. Higher values require better spatial overlap for association, improving precision but potentially reducing recall. Defaults to 0.3.
Optional
Default: 0.3
Number of consecutive frames that an object must be tracked before it is considered a 'valid' track. Increasing minimum_consecutive_frames prevents the creation of accidental tracks from false detection or double detection, but risks missing shorter tracks. Defaults to 3.
Optional
Default: 3
Detection confidence threshold for track activation. Increasing track_activation_threshold improves accuracy and stability but might miss true detections. Decreasing it increases completeness but risks introducing noise and instability. Defaults to 0.25.
Optional
Default: 0.25
Configuration example
Example from the Python docstring:
agent:
name: sort_tracker_agent
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: SORTTrackerInference
class_name: SORTTrackerInference
template_input: InputTemplate
attributes:
track_activation_threshold: 0.25
lost_track_buffer: 30
minimum_consecutive_frames: 3
minimum_iou_threshold: 0.3
frame_rate: 30Show schema-based configuration skeleton
templates:
- template_name: "SORTTrackerInference"
class_name: "SORTTrackerInference"
attributes:
frame_rate: 30
lost_track_buffer: 30
minimum_iou_threshold: 0.3
minimum_consecutive_frames: 3
track_activation_threshold: 0.25
Inheritance
sinapsis_rf_trackers.templates.rf_tracker_base.RFTrackerBaseEnvironment variables
Environment definitions belong to their canonical Python modules.
No directly related environment variables listed.