| Gamma | 5 | Recommend by Celantur |
|
| Beta | 4 | Recommend by Celantur |
|
| Alpha | 3 |
|
| Batch and Stream mode | /pages/iiet2gwTQcsmzQHN5m7V | ||
| REST API mode | /pages/1kDwd1vwz9Vsw3JrdLqP | ||
| TCP mode | /pages/LwShShWOdjwgQLVtReAS |
Activate Docker WSL 2 integration, by checking "Use WSL 2 based engine" in the settings.
| â Release Notes Discover the newest features and improvements for Celantur Container. | /pages/VSDnBH3L56bKpZEgXGOt |
| Parameter | Description |
|---|---|
| REQUIRED. Select what you want to anonymise. Options: |
--method METHOD | Choose anonymisation method. Options:
|
--bbox | Anonymise whole bounding boxes instead of segmentation. |
--debug | Visualise bounding boxes, anonymisation and tiling. |
| Print the confidence scores for the detected objects on images (only if --debug is enabled). |
--save-mask TYPE | Save binary mask or instance mask or both (all). See /pages/omGhPCeIYcpHVDD8Y0zg. |
--mask-scale [0..100] | Downscale binary or segmentation mask (only if --save-mask). |
--overwrite | Overwrite existing files in output folder. If not specified, files in input folder will be skipped if file with same name exists in output folder. |
--quality [0..100] | Quality of output JPEG image. |
| See #format-tiling |
| Select file type for processing. Default: only images selected. Since v26.01.1. |
| Parameter | Description |
|---|---|
--face-anonymization-gradient-start | Margin of gradual face blurring |
--face-anonymization-gradient-stop | Padding of gradual face blurring |
--license-plate-anonymization-gradient-start | Margin of gradual license plate blurring |
--license-plate-anonymization-gradient-stop | Padding of gradual license plate blurring |
--kernel-size-face | Kernel size for face blur. |
--kernel-size-person | Kernel size for person blur. |
--kernel-size-license-plate | Kernel size for license plate blur. |
--kernel-size-vehicle | Kernel size for vehicle blur. |
| Parameter | Description |
|---|---|
| Select inference model. Current default is segmentatio-omnium |
--face-threshold [0..1] | Threshold for face detection. Defaul: 0.2. |
--license-plate-threshold [0..1] | Threshold for license plate detection. Default: 0.2. |
--vehicle-threshold [0..1] | Threshold for vehicle detection. Default: 0.4. |
--person-threshold [0..1] | Threshold for person detection. Default: 0.4. |
--cpu-mode | Disable GPU support, /pages/Y5Qy2XKl1Dzb69Aei1vH. |
| Parameter | Description |
|---|---|
--video | Anonymise videos, skip images. Alias for -t video and no -t image |
--no-object-tracking | Disables /pages/lJ3DUakQZ80cWR6DtRIr which reduces flickering of anonymized objects in videos. |
--keep-bit-rate | Using this flag will encode the anonymised video with a bitrate close to the original video and ensure a nearly identically file size of the processed video, at the cost of 10% to 20% higher processing time. |
--no-ffmpeg-merge | Usually after processing the frames, in the post-processing process,
With |
| Parameter | Resolution |
|---|---|
pano:4096 | 4096x2048 |
pano:5400 | 5400x2700 |
pano:5640 | 5640x2816 |
pano:7060 | 7060x3530 |
pano:7680 | 7680x3840 |
pano:8000 | 8000x4000 |
pano:7680 | 7680x3840 |
pano:8000 | 8000x4000 |
pano:8192 | 8192x4096 |
pano:11000 | 11000x5500 |
whole | default, valid for all resolutions |
| Parameter | Description |
|---|---|
| nx | Number of horizontal tiles |
| ny | Number of vertical tiles |
| ox | Horizontal overlap between tiles in pixels |
| oy | Vertical overlap between tiles in pixels |
--format '{"number":[3,2],"overlap":[ox,oy],"section":[x1,y1,x2,y2]}'
| Parameter | Description |
|---|---|
| x1, y1 | Top left coordinate of the section |
| x2, y2 | Bottom right coordinate of the section |
| Parameter | Description |
|---|---|
| Path of the license file. |
| Input file or directory. |
| Output directory. |
--log-level LEVEL | Logging level. Options: |
--log-dir FOLDER | Location of the log files. |
--pid-file FILE | Path of PID file. |
--monitor FILE.json | [EXPERIMENTAL] Gather hardware utilisation in FILE.json |
./celantur.sh -a face -a license-plate \
--format '{"number":[4,1],"overlap":[300,0],"section":[0,1870,12288,4950]}'
./celantur.sh -a face -a license-plate -f pano:8000
| Parameter | Description |
|---|---|
| Streaming mode (Wait time in seconds). |
| Parameter | Description |
|---|---|
--api | Start container in REST API mode. |
--api-endpoint URL | Specify the API endpoint that is returned with the requests. URL for downloading the anonymised images, binary masks and metadata. |
Enum: blur, pixelate, blacken, detect
Default: blur
Specifies processing method.
Method detect only returns segmentation and binary masks, not an anonymized image.
Default: whole
Example:
format={"number": \[2,2], "overlap": \[0, 0]}
Tiling of the input image
| | ignores | String |Default: ""
Example: ignores=\[{"topLeftX": 182,"topLeftY": 154,"width":2000,"height":2000}]
Areas of the image that are not going to be anonymized
| | face-threshold | Number |Specifies detection threshold 0..1 for faces.
Default: 0.5
DEPRECATED
Specifies detection threshold value for segmentation.
ⶠUse person-threshold and vehicle-threshold instead.
Specifies detection threshold 0..1 for vehicles.
Default: 0.4
Specifies detection threshold 0..1 for persons.
Default: 0.4
Specifies detection threshold 0..1 for license plates.
Default: 0.5
Specifies whether the bitrate of the anonymized video should remain very close to the one of the original video.
Enabling keep-bit-rate will ensure a nearly identically file size of the processed video, at the cost of 10% to 20% higher processing time.
Default: false
Enables async processing.
Values: true or false
Default: false
Images:
fileobject=@/path/to/input/image;
See /pages/iiet2gwTQcsmzQHN5m7V#supported-image-formats
Videos:
Specify the video type
fileobject=@/path/to/input/video;type=video/mp4
See /pages/iiet2gwTQcsmzQHN5m7V#supported-video-codecs
| {% tabs %} {% tab title="200: OK JSON (image upload)" %} ```javascript { "content_type": "image/jpeg", "id": "string (uuid)", "metadata_url": "string", "binary_mask_url": "string", "instance_mask_url": "string", "anonymised_url": "string" } ``` {% endtab %} {% tab title="422: Unprocessable Entity JSON" %} ```javascript { "detail": "..." } ``` {% endtab %} {% tab title="500: Internal Server Error " %} {% endtab %} {% tab title="200: OK JSON (video upload)" %} ```json { "content_type": "video/mp4", "id": "string (uuid)", "anonymized_video": "string", "metadata_url": "string" } ``` {% endtab %} {% endtabs %} ## Download anonymized image `GET` `https://localhost/v1/file/{id}/anonymised` Download anonymized image #### Path Parameters | Name | Type | Description | | ------------------------------------ | ------ | ---------------------------------------------------- | | id\* | String | The `id` (UUID) of the file that will be downloaded. | #### Query Parameters | Name | Type | Description | | -------------- | ------ | ----------------------------------------------------------------------------------------------------------------- | | download | String |Enum: JPEG or PNG
Whether the image should be downloaded as a JPEG or PNG.
| | quality | Number |Specifies quality level for JPEG images ranging from 1 .. 100.
Default: 90
Specifies compression level for PNG images ranging from 0 .. 9.
Default: 5
Specifies the ratio at which the mask file will be scaled down, range between 0 .. 100.
Default: 100
Specifies the ratio at which the mask file will be scaled down, range between 0 .. 100.
Default: 100
Specifies the first frame of the range of frames for which the metadata will be downloaded. Range: 0 .. last\_frame.
Default: 0
Specifies the last frame of the range of frames for which the metadata will be downloaded. Range: 1 .. last\_frame.
Default: last\_frame
[
{
"id": 0,
"detections": [
{
"id": 0,
"parent_image": 0,
"offset": [
1501,
1280
],
"bbox": [
1504,
1280,
1563,
1337
],
"type": 103,
"score": 0.8185984492301941,
"is_anonymised": true,
"type_label": "face",
"color": null
}
],
"size": [
2160,
3840
],
"duration": 0.3577723959897412
},
{
"id": 1,
"detections": [
{
"id": 0,
"parent_image": 1,
"offset": [
1499,
1283
],
"bbox": [
1513,
1283,
1574,
1335
],
"type": 103,
"score": 0.8149935007095337,
"is_anonymised": true,
"type_label": "face",
"color": null
}
],
"size": [
2160,
3840
],
"duration": 0.3155565749912057
}, ...
]
task-and-files to delete everything.only-files to delete only files, keeping the records.
Default: task-and-files
task-and-files to delete everything.only-files to delete only files, keeping the records.
Default: task-and-files
| Parameter | Description |
|---|---|
--server <host:port> | TCP mode for JPEG image transfer. |
--server-array <host:port> | TCP mode for NumPy array transfer. |
Anonymization, binary segmentation and instance segmentation applied to an image with Celantur software.
| Attribute | Description |
|---|---|
| id | The id of the image (file name) or video frame (sequential number) |
| detections | List of detections, see #detected-instances-objects-provided-as-a-list-under-the-detections-attribute |
| size | Size of the image or frame in [width, height] |
| duration | Duration of processing (inference and anonymization) an image or video frame. Does not include IO, e.g. read/write from hard drive. |
| filename | Name of the file |
| folder | Name of the folder (relative to root input folder) |
| Attribute | Description |
|---|---|
| id | The id of the detection, a sequential number starting from 0. |
| parent_image | The name of the image or the id of the video frame the detected instance/object was found on |
| offset | The offset of the detection's bounding box from the upper left corner of the image (x/y coordinates in pixels) |
| bbox | The coordinates of the detection's bounding box (x1, y1, x2, y2) |
| score | The detection's confidence score. States how confident the model is about the detection being a specific label (see type_label) between 0.0 and 1.0. |
| is_anonymized | Specifies whether the detection was anonymized (or detected with method = detect). |
| type_label | The detection's label assigned by the model. E.g. face, license plates, etc. |
| type | Numerical representation of the type_label. |
| color | The detections color (RGB) in the instance segmentation mask. |
| duration | Processing duration for a video frame (only for videos). |