Skip to content

SORT Tracker

Class: SORTBlockV1

Source: inference.core.workflows.core_steps.trackers.sort.v1.SORTBlockV1

Track objects across video frames using the SORT algorithm from the roboflow/trackers package.

SORT pairs a Kalman filter motion model with single-stage IoU-based Hungarian assignment. It has the fewest parameters and lowest overhead, processing hundreds of frames per second. However, it lacks re-identification and occlusion-recovery mechanisms, so tracks may fragment or switch IDs when objects are temporarily hidden.

When to use SORT: - Controlled environments with reliable, high-confidence detections. - Real-time pipelines where maximum throughput is critical. - Simple scenes with minimal occlusion and predictable linear motion.

When to consider alternatives: - If you see fragmented tracks or missed weak detections, try ByteTrack. - If objects undergo heavy occlusion or non-linear motion, try OC-SORT.

Outputs three detection sets: - tracked_detections: All confirmed tracked detections with assigned track IDs. - new_instances: Detections whose track ID appears for the first time. - already_seen_instances: Detections whose track ID has been seen in a prior frame.

The block maintains separate tracker state and instance cache per video_identifier, enabling multi-stream tracking within a single workflow.

Type identifier

Use the following identifier in step "type" field: roboflow_core/trackers_sort@v1to add the block as as step in your workflow.

Properties

Name Type Description Refs
name str Enter a unique identifier for this step.. ❌
minimum_iou_threshold float Minimum IoU required to associate a detection with an existing track. Default: 0.3.. ✅
minimum_consecutive_frames int Number of consecutive frames a track must be matched before it is emitted as a confirmed track (tracker_id != -1). Default: 3.. ✅
lost_track_buffer int Number of frames to keep a track alive after it loses its matched detection. Higher values improve occlusion recovery. Default: 30.. ✅
track_activation_threshold float Minimum detection confidence required to spawn a new track. Detections below this threshold are not used to create new tracks. Default: 0.25.. ✅
instances_cache_size int Maximum number of track IDs retained in the instance cache for new/already-seen categorisation. Uses FIFO eviction. Default: 16384.. ❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Runtime compatibility

soft — runtime hosted_serverless, dedicated_deployment; execution remote; input video
Block keeps per-video state in process memory (keyed by video_metadata.video_identifier). With remote step execution on stateless or multi-replica HTTP runtimes, successive requests may be served by different worker processes, so the state resets between calls and the output is meaningless for tracking / counting / aggregation. Use local step execution in an InferencePipeline for stable cross-frame results.
soft — input image
Block depends on temporal context from video or repeated-frame workflows. With a still image/photo, there is no meaningful history to track, compare, aggregate, or visualize, so the block provides little or no benefit.

Available Connections

Compatible Blocks

Check what blocks you can connect to SORT Tracker in version v1.

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SORT Tracker in version v1 has.

Bindings

  • input

    • image (image): Input image with embedded video metadata (fps and video_identifier). Used to initialise and retrieve per-video tracker state..
    • detections (Union[instance_segmentation_prediction, object_detection_prediction, rle_instance_segmentation_prediction, keypoint_detection_prediction]): Detection predictions for the current frame to track..
    • minimum_iou_threshold (float_zero_to_one): Minimum IoU required to associate a detection with an existing track. Default: 0.3..
    • minimum_consecutive_frames (integer): Number of consecutive frames a track must be matched before it is emitted as a confirmed track (tracker_id != -1). Default: 3..
    • lost_track_buffer (integer): Number of frames to keep a track alive after it loses its matched detection. Higher values improve occlusion recovery. Default: 30..
    • track_activation_threshold (float_zero_to_one): Minimum detection confidence required to spawn a new track. Detections below this threshold are not used to create new tracks. Default: 0.25..

  • output

    • tracked_detections (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction, rle_instance_segmentation_prediction]): Prediction with detected bounding boxes in form of sv.Detections(...) object if object_detection_prediction or Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object if instance_segmentation_prediction or Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object if keypoint_detection_prediction or Prediction with detected bounding boxes and RLE-encoded segmentation masks in form of sv.Detections(...) object if rle_instance_segmentation_prediction.
    • new_instances (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction, rle_instance_segmentation_prediction]): Prediction with detected bounding boxes in form of sv.Detections(...) object if object_detection_prediction or Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object if instance_segmentation_prediction or Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object if keypoint_detection_prediction or Prediction with detected bounding boxes and RLE-encoded segmentation masks in form of sv.Detections(...) object if rle_instance_segmentation_prediction.
    • already_seen_instances (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction, rle_instance_segmentation_prediction]): Prediction with detected bounding boxes in form of sv.Detections(...) object if object_detection_prediction or Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object if instance_segmentation_prediction or Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object if keypoint_detection_prediction or Prediction with detected bounding boxes and RLE-encoded segmentation masks in form of sv.Detections(...) object if rle_instance_segmentation_prediction.
Example JSON definition of step SORT Tracker in version v1 
{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/trackers_sort@v1",
    "image": "<block_does_not_provide_example>",
    "detections": "$steps.object_detection_model.predictions",
    "minimum_iou_threshold": 0.3,
    "minimum_consecutive_frames": 3,
    "lost_track_buffer": 30,
    "track_activation_threshold": 0.25,
    "instances_cache_size": "<block_does_not_provide_example>"
}