Detections Stabilizer

Class: StabilizeTrackedDetectionsBlockV1

Source: inference.core.workflows.core_steps.transformations.stabilize_detections.v1.StabilizeTrackedDetectionsBlockV1

This block stores last known position for each bounding box If box disappears then this block will bring it back so short gaps are filled with last known box position The block requires detections to be tracked (i.e. each object must have unique tracker_id assigned, which persists between frames) WARNING: this block will produce many short-lived bounding boxes for unstable trackers!

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
smoothing_window_size	int	Predicted movement of detection will be smoothed based on historical measurements of velocity, this parameter controls number of historical measurements taken under account when calculating smoothed velocity. Detections will be removed from generating smoothed predictions if they had been missing for longer than this number of frames..	✅
bbox_smoothing_coefficient	float	Bounding box smoothing coefficient applied when given tracker_id is present on current frame. This parameter must be initialized with value between 0 and 1.	✅

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

Available Connections

Compatible Blocks

Check what blocks you can connect to Detections Stabilizer in version v1.

• inputs: Detections Consensus, Circle Visualization, Polygon Zone Visualization, Image Slicer, Reference Path Visualization, Image Contours, Dynamic Crop, Detections Filter, VLM as Detector, Distance Measurement, Blur Visualization, Detection Offset, Stability AI Inpainting, SIFT Comparison, Instance Segmentation Model, Absolute Static Crop, Trace Visualization, Classification Label Visualization, Crop Visualization, Camera Calibration, Stitch Images, Segment Anything 2 Model, Line Counter Visualization, Corner Visualization, Time in Zone, Google Vision OCR, Path Deviation, Line Counter, Moondream2, Perspective Correction, Object Detection Model, Triangle Visualization, Path Deviation, Image Blur, Pixel Color Count, Clip Comparison, Detections Classes Replacement, VLM as Detector, Image Preprocessing, Pixelate Visualization, Background Color Visualization, Polygon Visualization, Stability AI Outpainting, Grid Visualization, Byte Tracker, Identify Changes, Color Visualization, Bounding Rectangle, Relative Static Crop, Bounding Box Visualization, Identify Outliers, YOLO-World Model, Halo Visualization, Image Convert Grayscale, Camera Focus, Template Matching, Ellipse Visualization, Mask Visualization, Dynamic Zone, Detections Transformation, Object Detection Model, Model Comparison Visualization, Line Counter, Detections Stitch, Dot Visualization, Stability AI Image Generation, Byte Tracker, Depth Estimation, Velocity, Instance Segmentation Model, Keypoint Visualization, Byte Tracker, Time in Zone, Image Threshold, SIFT Comparison, Detections Merge, SIFT, PTZ Tracking (ONVIF).md), Label Visualization, Image Slicer, Detections Stabilizer, Overlap Filter
• outputs: Background Color Visualization, Detections Consensus, Circle Visualization, Roboflow Custom Metadata, Polygon Visualization, Byte Tracker, Color Visualization, Size Measurement, Dynamic Crop, Detections Filter, Distance Measurement, Blur Visualization, Bounding Rectangle, Detection Offset, Model Monitoring Inference Aggregator, Stability AI Inpainting, Bounding Box Visualization, Trace Visualization, Halo Visualization, Crop Visualization, Segment Anything 2 Model, Florence-2 Model, Corner Visualization, Time in Zone, Ellipse Visualization, Path Deviation, Line Counter, Mask Visualization, Roboflow Dataset Upload, Perspective Correction, Dynamic Zone, Detections Transformation, Overlap Filter, Triangle Visualization, Model Comparison Visualization, Path Deviation, Line Counter, Dot Visualization, Byte Tracker, Velocity, Byte Tracker, Detections Classes Replacement, Time in Zone, Roboflow Dataset Upload, Florence-2 Model, Stitch OCR Detections, Detections Merge, PTZ Tracking (ONVIF).md), Label Visualization, Detections Stabilizer, Pixelate Visualization, Detections Stitch

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Detections Stabilizer in version v1 has.

Bindings

• input

  • image (image): not available.
  • detections (Union[instance_segmentation_prediction, object_detection_prediction]): Tracked detections.
  • smoothing_window_size (integer): Predicted movement of detection will be smoothed based on historical measurements of velocity, this parameter controls number of historical measurements taken under account when calculating smoothed velocity. Detections will be removed from generating smoothed predictions if they had been missing for longer than this number of frames..
  • bbox_smoothing_coefficient (float_zero_to_one): Bounding box smoothing coefficient applied when given tracker_id is present on current frame. This parameter must be initialized with value between 0 and 1.

• output

  • tracked_detections (Union[object_detection_prediction, 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.

Example JSON definition of step Detections Stabilizer in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/stabilize_detections@v1",
    "image": "<block_does_not_provide_example>",
    "detections": "$steps.object_detection_model.predictions",
    "smoothing_window_size": 5,
    "bbox_smoothing_coefficient": 0.2
}