Detections Filter

Class: DetectionsFilterBlockV1

Source: inference.core.workflows.core_steps.transformations.detections_filter.v1.DetectionsFilterBlockV1

Conditionally filter out model predictions.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
operations	List[Union[ClassificationPropertyExtract, ConvertDictionaryToJSON, ConvertImageToBase64, ConvertImageToJPEG, DetectionsFilter, DetectionsOffset, DetectionsPropertyExtract, DetectionsRename, DetectionsSelection, DetectionsShift, DetectionsToDictionary, Divide, ExtractDetectionProperty, ExtractFrameMetadata, ExtractImageProperty, LookupTable, Multiply, NumberRound, NumericSequenceAggregate, PickDetectionsByParentClass, RandomNumber, SequenceAggregate, SequenceApply, SequenceElementsCount, SequenceLength, SequenceMap, SortDetections, StringMatches, StringSubSequence, StringToLowerCase, StringToUpperCase, TimestampToISOFormat, ToBoolean, ToNumber, ToString]]	Definition of filtering logic..	❌

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 Filter in version v1.

• inputs: Crop Visualization, Grid Visualization, Object Detection Model, Detections Merge, Byte Tracker, VLM as Classifier, Florence-2 Model, Google Vision OCR, Dimension Collapse, Velocity, Single-Label Classification Model, Barcode Detection, Data Aggregator, Perspective Correction, Line Counter Visualization, Dot Visualization, Dynamic Crop, Local File Sink, Instance Segmentation Model, Bounding Box Visualization, Ellipse Visualization, Anthropic Claude, Roboflow Custom Metadata, Keypoint Detection Model, Moondream2, Label Visualization, Relative Static Crop, Property Definition, Identify Outliers, Object Detection Model, Delta Filter, Multi-Label Classification Model, Distance Measurement, VLM as Classifier, Gaze Detection, Keypoint Visualization, Slack Notification, Time in Zone, OpenAI, Email Notification, Blur Visualization, Image Preprocessing, Path Deviation, Twilio SMS Notification, JSON Parser, Template Matching, OCR Model, Detections Stitch, Camera Calibration, Time in Zone, Multi-Label Classification Model, Florence-2 Model, Image Slicer, Single-Label Classification Model, Halo Visualization, Absolute Static Crop, Corner Visualization, VLM as Detector, Qwen2.5-VL, OpenAI, Stability AI Inpainting, Cache Get, LMM For Classification, Google Gemini, Detections Classes Replacement, Line Counter, Image Blur, YOLO-World Model, Clip Comparison, Detections Stabilizer, SIFT, Detections Transformation, Keypoint Detection Model, First Non Empty Or Default, Roboflow Dataset Upload, Line Counter, Detections Consensus, Perception Encoder Embedding Model, Stability AI Outpainting, Dominant Color, Llama 3.2 Vision, Depth Estimation, Detections Filter, Image Contours, Background Color Visualization, CLIP Embedding Model, Camera Focus, Bounding Rectangle, Color Visualization, Roboflow Dataset Upload, Cache Set, QR Code Detection, Stitch Images, Identify Changes, SmolVLM2, Byte Tracker, SIFT Comparison, Reference Path Visualization, Expression, Stitch OCR Detections, Webhook Sink, Buffer, Instance Segmentation Model, Path Deviation, Model Monitoring Inference Aggregator, Segment Anything 2 Model, Image Threshold, Image Slicer, SIFT Comparison, Dynamic Zone, Stability AI Image Generation, CogVLM, Trace Visualization, Classification Label Visualization, Mask Visualization, PTZ Tracking (ONVIF).md), Image Convert Grayscale, Overlap Filter, Byte Tracker, Pixel Color Count, Polygon Zone Visualization, Rate Limiter, CSV Formatter, Icon Visualization, Model Comparison Visualization, Pixelate Visualization, QR Code Generator, Continue If, Cosine Similarity, Environment Secrets Store, VLM as Detector, OpenAI, Detection Offset, Size Measurement, Circle Visualization, Triangle Visualization, LMM, Clip Comparison, Polygon Visualization
• outputs: Byte Tracker, Crop Visualization, Stability AI Inpainting, Detections Merge, Stitch OCR Detections, Distance Measurement, Byte Tracker, Detections Classes Replacement, Line Counter, Detections Stabilizer, Path Deviation, Keypoint Visualization, Florence-2 Model, Model Monitoring Inference Aggregator, Time in Zone, Segment Anything 2 Model, Detections Transformation, Blur Visualization, Velocity, Dynamic Zone, Trace Visualization, Roboflow Dataset Upload, Line Counter, Path Deviation, PTZ Tracking (ONVIF).md), Mask Visualization, Overlap Filter, Byte Tracker, Color Visualization, Detections Consensus, Perspective Correction, Detections Stitch, Icon Visualization, Dot Visualization, Model Comparison Visualization, Time in Zone, Dynamic Crop, Pixelate Visualization, Florence-2 Model, Bounding Box Visualization, Bounding Rectangle, Halo Visualization, Detections Filter, Ellipse Visualization, Background Color Visualization, Detection Offset, Circle Visualization, Size Measurement, Corner Visualization, Triangle Visualization, Roboflow Custom Metadata, Roboflow Dataset Upload, Label Visualization, Polygon Visualization

Input and Output Bindings

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

Bindings

• input

  • predictions (Union[keypoint_detection_prediction, object_detection_prediction, instance_segmentation_prediction]): Model predictions to filter..
  • operations_parameters (*): References to additional parameters that may be provided in runtime to parametrise operations.

• output

  • predictions (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_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.

Example JSON definition of step Detections Filter in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/detections_filter@v1",
    "predictions": "$steps.object_detection_model.predictions",
    "operations": [
        {
            "filter_operation": {
                "statements": [
                    {
                        "comparator": {
                            "type": "in (Sequence)"
                        },
                        "left_operand": {
                            "operations": [
                                {
                                    "property_name": "class_name",
                                    "type": "ExtractDetectionProperty"
                                }
                            ],
                            "type": "DynamicOperand"
                        },
                        "right_operand": {
                            "operand_name": "classes",
                            "type": "DynamicOperand"
                        },
                        "type": "BinaryStatement"
                    }
                ],
                "type": "StatementGroup"
            },
            "type": "DetectionsFilter"
        }
    ],
    "operations_parameters": {
        "classes": "$inputs.classes"
    }
}