Halo Visualization¶
Version v1
¶
The HaloVisualization
block uses a detected polygon
from an instance segmentation to draw a halo using
sv.HaloAnnotator
.
Type identifier¶
Use the following identifier in step "type"
field: roboflow_core/halo_visualization@v1
to add the block as
as step in your workflow.
Properties¶
Name | Type | Description | Refs |
---|---|---|---|
name |
str |
The unique name of this step.. | ❌ |
copy_image |
bool |
Duplicate the image contents (vs overwriting the image in place). Deselect for chained visualizations that should stack on previous ones where the intermediate state is not needed.. | ✅ |
color_palette |
str |
Color palette to use for annotations.. | ✅ |
palette_size |
int |
Number of colors in the color palette. Applies when using a matplotlib color_palette .. |
✅ |
custom_colors |
List[str] |
List of colors to use for annotations when color_palette is set to "CUSTOM".. |
✅ |
color_axis |
str |
Strategy to use for mapping colors to annotations.. | ✅ |
opacity |
float |
Transparency of the halo overlay.. | ✅ |
kernel_size |
int |
Size of the average pooling kernel used for creating the halo.. | ✅ |
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 Halo Visualization
in version v1
.
- inputs:
Color Visualization
,Detections Filter
,Image Contours
,Path deviation
,Image Preprocessing
,Mask Visualization
,Dot Visualization
,Corner Visualization
,Model Comparison Visualization
,Image Slicer
,Detection Offset
,Image Blur
,Label Visualization
,Time in zone
,Relative Static Crop
,Polygon Visualization
,Camera Focus
,Detections Classes Replacement
,Dynamic Crop
,Halo Visualization
,Segment Anything 2 Model
,Crop Visualization
,Image Threshold
,SIFT
,Circle Visualization
,SIFT Comparison
,Path deviation
,Stability AI Inpainting
,Image Convert Grayscale
,Line Counter Visualization
,Absolute Static Crop
,Background Color Visualization
,Perspective Correction
,Detections Stitch
,Detections Transformation
,Bounding Box Visualization
,Polygon Zone Visualization
,Ellipse Visualization
,Pixelate Visualization
,Time in zone
,Triangle Visualization
,Instance Segmentation Model
,Bounding Rectangle
,Stitch Images
,Blur Visualization
- outputs:
Color Visualization
,Image Contours
,Image Preprocessing
,Mask Visualization
,Dot Visualization
,Corner Visualization
,Model Comparison Visualization
,Image Slicer
,Keypoint Detection Model
,Image Blur
,OCR Model
,Label Visualization
,Time in zone
,Relative Static Crop
,Florence-2 Model
,Camera Focus
,Clip Comparison
,Polygon Visualization
,Image Convert Grayscale
,Dynamic Crop
,YOLO-World Model
,Halo Visualization
,LMM For Classification
,Segment Anything 2 Model
,Crop Visualization
,Image Threshold
,Multi-Label Classification Model
,QR Code Detection
,Google Vision OCR
,SIFT
,Clip Comparison
,LMM
,Roboflow Dataset Upload
,Barcode Detection
,OpenAI
,Circle Visualization
,SIFT Comparison
,VLM as Detector
,Google Gemini
,CogVLM
,Anthropic Claude
,Object Detection Model
,Pixel Color Count
,Stability AI Inpainting
,OpenAI
,Absolute Static Crop
,Background Color Visualization
,Perspective Correction
,Detections Stitch
,Line Counter Visualization
,Dominant Color
,Template Matching
,Bounding Box Visualization
,Polygon Zone Visualization
,Ellipse Visualization
,Pixelate Visualization
,Triangle Visualization
,Roboflow Dataset Upload
,Instance Segmentation Model
,Single-Label Classification Model
,VLM as Classifier
,Stitch Images
,Blur Visualization
The available connections depend on its binding kinds. Check what binding kinds
Halo Visualization
in version v1
has.
Bindings
-
input
image
(image
): The input image for this step..copy_image
(boolean
): Duplicate the image contents (vs overwriting the image in place). Deselect for chained visualizations that should stack on previous ones where the intermediate state is not needed..predictions
(instance_segmentation_prediction
): Predictions.color_palette
(string
): Color palette to use for annotations..palette_size
(integer
): Number of colors in the color palette. Applies when using a matplotlibcolor_palette
..custom_colors
(list_of_values
): List of colors to use for annotations whencolor_palette
is set to "CUSTOM"..color_axis
(string
): Strategy to use for mapping colors to annotations..opacity
(float_zero_to_one
): Transparency of the halo overlay..kernel_size
(integer
): Size of the average pooling kernel used for creating the halo..
-
output
image
(image
): Image in workflows.
Example JSON definition of step Halo Visualization
in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/halo_visualization@v1",
"image": "$inputs.image",
"copy_image": true,
"predictions": "$steps.instance_segmentation_model.predictions",
"color_palette": "DEFAULT",
"palette_size": 10,
"custom_colors": [
"#FF0000",
"#00FF00",
"#0000FF"
],
"color_axis": "CLASS",
"opacity": 0.8,
"kernel_size": 40
}