swarmsort.integration module

Integration utilities for SwarmSort when used within the swarmtracker pipeline.

This module provides compatibility layers and integration helpers that allow SwarmSort to seamlessly work with the full swarmtracker ecosystem while maintaining standalone functionality.

class swarmsort.integration.AdaptiveSwarmSortTracker(config=None)

Bases: object

Adaptive wrapper for SwarmSortTracker that automatically handles both standalone and swarmtracker integration modes.

property config

Access tracker configuration.

get_statistics()

Get tracker statistics.

reset()

Reset tracker state.

update(detections)

Update tracker with detections in any supported format.

Parameters:

detections – List of detection objects (any supported format)

Returns:

List of tracked objects in the appropriate format

swarmsort.integration.StandaloneSwarmSort

alias of _StandaloneSwarmSortWrapper

swarmsort.integration.SwarmSort

alias of AdaptiveSwarmSortTracker

swarmsort.integration.convert_any_detection(detection)

Universal detection converter that handles various detection formats.

This function provides a single entry point for converting detections from any format to the SwarmSort StandaloneDetection format. It handles: - SwarmSort Detection objects (passthrough) - SwarmTracker detection objects - Objects with position/bbox and confidence attributes - Dictionaries with ‘position’/’bbox’ and ‘confidence’ keys

Parameters:

detection – Detection in any supported format

Returns:

Converted detection compatible with SwarmSort

Return type:

StandaloneDetection

Raises:

ValueError – If position cannot be extracted from the detection

Example

>>> # Works with dict
>>> det = convert_any_detection({'position': [100, 200], 'confidence': 0.9})
>>> # Works with objects
>>> det = convert_any_detection(some_detector_output)

swarmsort.integration.convert_swarmtracker_detection(swarmtracker_det)

Convert a swarmtracker Detection to standalone Detection.

Parameters:

swarmtracker_det – Detection object from swarmtracker

Returns:

Converted detection

Return type:

StandaloneDetection

swarmsort.integration.convert_to_swarmtracker_tracked_object(standalone_obj)

Convert a standalone TrackedObject to swarmtracker format.

Parameters:

standalone_obj (TrackedObject) – StandaloneTrackedObject instance

Returns:

Swarmtracker compatible tracked object

swarmsort.integration.create_adaptive_detection_converter()

Create a detection converter that automatically handles both formats.

Returns:

Callable that converts any detection to standalone format

swarmsort.integration.create_adaptive_tracker_output_converter()

Create an output converter that returns the appropriate format.

Returns:

Callable that converts tracked objects to the expected format

swarmsort.integration.create_tracker(config=None, force_standalone=False)

Factory function to create the appropriate tracker instance.

Parameters:

• config – Configuration (SwarmSortConfig, dict, or path to YAML file)

• force_standalone – If True, always create standalone tracker

Returns:

Tracker instance (adaptive or standalone)

swarmsort.integration.get_swarmtracker_detection_class()

Get the swarmtracker Detection class if available.

Return type:

Optional[Type]

Returns:

Detection class from swarmtracker or None if not available

swarmsort.integration.get_swarmtracker_tracked_object_class()

Get the swarmtracker TrackedObject class if available.

Return type:

Optional[Type]

Returns:

TrackedObject class from swarmtracker or None if not available

swarmsort.integration.is_within_swarmtracker()

Detect if SwarmSort is being used within the swarmtracker pipeline.

Returns:

True if running within swarmtracker, False if standalone

Return type:

bool

swarmsort.integration.load_swarmtracker_config(config_path)

Load configuration from swarmtracker YAML format if available.

Parameters:

config_path (str) – Path to swarmtracker configuration file

Returns:

Converted configuration

Return type:

SwarmSortConfig