Recommended Parameters
A list of recommended parameters for different camera systems to achieve best anonymization results with Celantur Container.
Go to: #DJI #Insta360 #Ladybug #Mosaic
When starting with a demo of Celantur Container, our team will send you a customized code sample.
Anonymize Panorama Images
Due to large resolution panorama images require special parametrization to achieve the best anonymization results.
Run following command after, specifying the format value according to Predefined Formats if the panorama's resolution exactly matches an item in the list of predefined formats (e.g. pano:8192):
./celantur.sh \
-a face \
-a license-plate \
--format pano:8192 \If your panorama's resolution is not part of Predefined Formats, specify the middle section (x1, y1, x2, y2) of the panorama.
./celantur.sh \
-a face \
-a license-plate \
--format '{"number":[4,1],"overlap":[300,0],"section":[0,1870,12288,4950]}' \Mosaic
Mosaic X
Panorama images (13504x6752, 91.2 MP)
./celantur.sh \
-a face \
-a license-plate \
--face-threshold 0.1 \
--license-plate-threshold 0.1 \
--model segmentatio-omnium \
-f '{"number":[5,1],"overlap":[400,0],"section":[0,2200,13504,5300]}'Optimize: Adapt thresholds (lower = better detections, potentially more false positives; higher = less false positives)
--face-threshold 0.3 , --license-plate-threshold 0.3 (Batch/Stream mode)
Mosaic 51
Panorama images (12288x6144, 75.5 MP)
./celantur.sh
-a face
-a license-plate
--face-threshold 0.1
--license-plate-threshold 0.1
--model segmentatio-omnium
-f '{"number":[4,1],"overlap":[200,0],"section":[0,1870,12288,4950]}'Insta360
Insta360 X4
Panorama images (11904x5952):
celantur.sh \
-a face \
-a license-plate \
--model segmentatio-omnium \
-f '{"number":[4,1],"overlap":[200,0],"section":[0,2000,11904,4900]}' GoPro
GoPro MAX
Panorama images (5760x2880)
celantur.sh \
-a face \
-a license-plate \
--model segmentatio-omnium \
-f '{"number":[4,1],"overlap":[100,0],"section":[0,1000,5760,2340]}'
Ladybug
Ladybug5+
Panorama images (8000x4000)
celantur.sh \
-a face \
-a license-plate \
--license-plate-threshold 0.2 \
--model segmentatio-omnium \
-f pano:8000 Anonymize Drone Images
Example for images (4032x3024) from a DJI Mini 3 Pro.
Persons and vehicles:
celantur.sh \
-a person \
-a vehicle \
--model segmentatio-omnium \
-f '{"number":[4,3],"overlap":[200,200]}' \
--vehicle-threshold 0.4 \
--person-threshold 0.3Faces and license plates:
celantur.sh \
-a face \
-a license-plate \
--model segmentatio-omnium \
-f '{"number":[4,3],"overlap":[200,200]}' \
--face-threshold 0.1 \
--license-plate-threshold 0.1DJI
DJI Mini 3 Pro
Images (4032x3024):
celantur.sh \
-a person \
-a vehicle \
--model segmentatio-omnium \
-f '{"number":[4,3],"overlap":[200,200]}' \
--vehicle-threshold 0.4 \
--person-threshold 0.3celantur.sh \
-a face \
-a license-plate \
--model segmentatio-omnium \
-f '{"number":[4,3],"overlap":[200,200]}' \
--face-threshold 0.1 \
--license-plate-threshold 0.1Anonymize FullHD Videos
Check if your video's codec is supported.
Run following command:
celantur.sh \
-a face \
-a license-plate \
--model segmentatio-omnium \
--face-threshold 0.2 \
--license-plate-threshold 0.2 \
--video \
--keep-bit-rateAnonymize FullHD Dashcam Frames
Run following command:
celantur.sh \
-a face \
-a license-plate \
--model segmentatio-omnium \
--face-threshold 0.2 \
--license-plate-threshold 0.2Last updated