1CELESTE_STANDALONE(1)                HUGIN               CELESTE_STANDALONE(1)
2
3
4

NAME

6       celeste_standalone - Cloud identification
7

SYNOPSIS

9       celeste_standalone [options] image1 image2 [..]
10

DESCRIPTION

12       Celeste has been trained using Support vector machine techniques to
13       identify clouds in photos and remove control points from these areas.
14       celeste_standalone is a command-line tool with all the same
15       functionality as Celeste in hugin.
16
17       Simple usage is to just 'clean' an existing project file:
18
19        celeste_standalone -i project.pto -o project.pto
20

OPTIONS

22       -i <filename>
23           Input Hugin PTO file. Control points over SVM threshold will be
24           removed before being written to the output file. If -m is set to 1,
25           images in the file will be also be masked.
26
27       -o <filename>
28           Output Hugin PTO file. Default: '<filename>_celeste.pto'
29
30       -d <filename>
31           SVM model file. Default: 'data/celeste.model'
32
33       -s <int>
34           Maximum dimension for re-sized image prior to processing. A higher
35           value will increase the resolution of the mask but is significantly
36           slower. Default: 800
37
38       -t <float>
39           SVM threshold. Raise this value to remove fewer control points,
40           lower it to remove more. Range 0 to 1. Default: 0.5
41
42       -m <1|0>
43           Create masks when processing Hugin PTO file. Default: 0
44
45       -f <string>
46           Mask file format. Options are PNG, JPEG, BMP, GIF and TIFF.
47           Default: PNG
48
49       -r <1|0>
50           Filter radius. 0 = large (more accurate), 1 = small (higher
51           resolution mask, slower, less accurate). Default: 0
52
53       -h  Print usage.
54

AUTHORS

56       Written by Tim Nugent.
57
58
59
60"Version: 2021.0.0"               2022-02-10             CELESTE_STANDALONE(1)
Impressum