Perspective Correction

Class: PerspectiveCorrectionBlockV1

Source: inference.core.workflows.core_steps.transformations.perspective_correction.v1.PerspectiveCorrectionBlockV1

The PerspectiveCorrectionBlock is a transformer block designed to correct coordinates of detections based on transformation defined by two polygons. This block is best suited when produced coordinates should be considered as if camera was placed directly above the scene and was not introducing distortions.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
perspective_polygons	List[Any]	Perspective polygons (for each batch at least one must be consisting of 4 vertices).	✅
transformed_rect_width	int	Transformed rect width.	✅
transformed_rect_height	int	Transformed rect height.	✅
extend_perspective_polygon_by_detections_anchor	str	If set, perspective polygons will be extended to contain all bounding boxes. Allowed values: CENTER, CENTER_LEFT, CENTER_RIGHT, TOP_CENTER, TOP_LEFT, TOP_RIGHT, BOTTOM_LEFT, BOTTOM_CENTER, BOTTOM_RIGHT, CENTER_OF_MASS and ALL to extend to contain whole bounding box.	✅
warp_image	bool	If set to True, image will be warped into transformed rect.	✅

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 Perspective Correction in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Perspective Correction in version v1 has.

Bindings

• input

  • predictions (Union[object_detection_prediction, instance_segmentation_prediction]): Predictions.
  • images (image): The input image for this step..
  • perspective_polygons (list_of_values): Perspective polygons (for each batch at least one must be consisting of 4 vertices).
  • transformed_rect_width (integer): Transformed rect width.
  • transformed_rect_height (integer): Transformed rect height.
  • extend_perspective_polygon_by_detections_anchor (string): If set, perspective polygons will be extended to contain all bounding boxes. Allowed values: CENTER, CENTER_LEFT, CENTER_RIGHT, TOP_CENTER, TOP_LEFT, TOP_RIGHT, BOTTOM_LEFT, BOTTOM_CENTER, BOTTOM_RIGHT, CENTER_OF_MASS and ALL to extend to contain whole bounding box.
  • warp_image (boolean): If set to True, image will be warped into transformed rect.

• output

  • corrected_coordinates (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.
  • warped_image (image): Image in workflows.
  • extended_transformed_rect_width (integer): Integer value.
  • extended_transformed_rect_height (integer): Integer value.

Example JSON definition of step Perspective Correction in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/perspective_correction@v1",
    "predictions": "$steps.object_detection_model.predictions",
    "images": "$inputs.image",
    "perspective_polygons": "$steps.perspective_wrap.zones",
    "transformed_rect_width": 1000,
    "transformed_rect_height": 1000,
    "extend_perspective_polygon_by_detections_anchor": "CENTER",
    "warp_image": false
}