Gaze Detection¶
Run L2CS Gaze detection model on faces in images.
This block can: 1. Detect faces in images and estimate their gaze direction 2. Estimate gaze direction on pre-cropped face images
The gaze direction is represented by yaw and pitch angles in degrees.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/gaze@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
do_run_face_detection |
bool |
Whether to run face detection. Set to False if input images are pre-cropped face images.. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Available Connections¶
Check what blocks you can connect to Gaze Detection in version v1.
- inputs:
Reference Path Visualization,Label Visualization,Polygon Zone Visualization,Model Monitoring Inference Aggregator,Roboflow Dataset Upload,Stability AI Inpainting,Triangle Visualization,Absolute Static Crop,Trace Visualization,Halo Visualization,Local File Sink,Ellipse Visualization,SIFT,SIFT Comparison,Identify Outliers,Slack Notification,Pixelate Visualization,Image Blur,Email Notification,Twilio SMS Notification,Dot Visualization,Model Comparison Visualization,Classification Label Visualization,VLM as Detector,Dynamic Crop,SIFT Comparison,Image Slicer,Mask Visualization,VLM as Classifier,Perspective Correction,Background Color Visualization,Crop Visualization,Grid Visualization,Relative Static Crop,Line Counter Visualization,Detections Consensus,Webhook Sink,VLM as Classifier,Image Convert Grayscale,Image Contours,Stitch Images,JSON Parser,Blur Visualization,Image Threshold,Color Visualization,Roboflow Custom Metadata,Image Preprocessing,Identify Changes,VLM as Detector,Polygon Visualization,Circle Visualization,Camera Focus,Roboflow Dataset Upload,Bounding Box Visualization,Corner Visualization,Keypoint Visualization - outputs:
Model Monitoring Inference Aggregator,Roboflow Dataset Upload,Triangle Visualization,Trace Visualization,Ellipse Visualization,Detections Classes Replacement,Pixelate Visualization,Detections Transformation,Anthropic Claude,Dot Visualization,Model Comparison Visualization,Dynamic Crop,Background Color Visualization,Crop Visualization,Line Counter Visualization,Detections Consensus,Google Gemini,Webhook Sink,Detections Filter,Blur Visualization,Florence-2 Model,Color Visualization,Roboflow Custom Metadata,Bounding Box Visualization,Template Matching,Florence-2 Model,Distance Measurement,Segment Anything 2 Model,Detection Offset,OpenAI,Roboflow Dataset Upload,Circle Visualization,Label Visualization,Corner Visualization,Keypoint Visualization
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Gaze Detection in version v1 has.
Bindings
-
input
-
output
face_predictions(keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.yaw_degrees(float): Float value.pitch_degrees(float): Float value.
Example JSON definition of step Gaze Detection in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/gaze@v1",
"images": "$inputs.image",
"do_run_face_detection": "<block_does_not_provide_example>"
}