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

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[object_detection_prediction, instance_segmentation_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
}