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