Agrocam multispectral problem

Good morning to all.
I need some advice from the community.
I tried to process a set of 112 images (56 NIR + 56 RGB) but WebODM, after an hour of processing, replies that “=====[ERROR] Uh oh! Processing stopped because of strange values in the reconstruction. This is often a sign that the input data has some issues or the software cannot deal with it. Have you followed best practices for data acquisition?”
Do you have any ideas why?
WebODM 1.9.14 on Windows 8.1 16 gb ram and vmdk disk expanded to 150gb
Thank’s
I attach two images of the set and report WebODM.



console.pdf (227.7 KB)

1 Like

Good morning to all.
I renew elaboration with a small lot of images (only 10 RGB annd 10 NIR).
I renamed the photos to xxx_RGB and xxx_NIR but an error occurred:

===== Dumping Info for Geeks (developers need this to fix bugs) =====
Child returned 1
Traceback (most recent call last):
File “/code/stages/odm_app.py”, line 94, in execute
self.first_stage.run()
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 328, in run
self.process(self.args, outputs)
File “/code/stages/run_opensfm.py”, line 193, in process
octx.run(‘export_visualsfm --points’)
File “/code/opendm/osfm.py”, line 34, in run
system.run(’"%s" %s “%s”’ %
File “/code/opendm/system.py”, line 106, in run
raise SubprocessException(“Child returned {}”.format(retcode), retcode)
opendm.system.SubprocessException: Child returned 1

Do youa have any ideas to help me?
Thank’s

1 Like

Are you able to share the data?

hi,
thank’s to your help.
You need the 20 photos of my last activity?

1 Like

Hi,
this is link to the 20 photos
Data link
Thank’s for you help

1 Like

Hi,

I am interesting to buy a Agrocam. What drone do you use? How about this cam working?
Can you share some experience? Thank you
I also processing your dataset to see how it works.
But this set is way too small. Can you share some big one? Thank you.

1 Like

your data is too small and only one way. I used ICE instead , it works for RGB and NIR

If you can share the whole dataset, maybe the webODM can process them.

This Is my first experience with Agrocam.
The problem Is modality “Multispectral”.
When i process in “Predefined” mode only one set of images it’s ok.

Maybe no enough images.

I run as
20

00:10:52

Cannot process dataset

Created on: 7/1/2022, 9:29:10 AM
Processing Node: node-odm-1 (auto)
Options: auto-boundary: true, fast-orthophoto: true, feature-quality: ultra, pc-quality: ultra, radiometric-calibration: camera, resize-to: -1, skip-3dmodel: true, texturing-skip-global-seam-leveling: true

d 76009 points in 63.78647971153259s
2022-07-01 16:34:27,929 DEBUG: done
2022-07-01 16:34:27,929 DEBUG: done
2022-07-01 16:34:28,050 DEBUG: Found 72434 points in 66.01153540611267s
2022-07-01 16:34:28,050 DEBUG: done
2022-07-01 16:34:28,936 DEBUG: Found 69769 points in 64.3764181137085s
2022-07-01 16:34:28,937 DEBUG: done
2022-07-01 16:34:34,822 DEBUG: No segmentation for 003_NIR.JPG, no features masked.
2022-07-01 16:34:41,155 DEBUG: No segmentation for 002_NIR.JPG, no features masked.
2022-07-01 16:34:41,870 DEBUG: No segmentation for 008_NIR.JPG, no features masked.
2022-07-01 16:34:42,113 DEBUG: No segmentation for 004_NIR.JPG, no features masked.
2022-07-01 16:34:43,188 DEBUG: No segmentation for 006_NIR.JPG, no features masked.
2022-07-01 16:34:43,188 DEBUG: No segmentation for 006_RGB.JPG, no features masked.
2022-07-01 16:34:43,803 DEBUG: No segmentation for 003_RGB.JPG, no features masked.
2022-07-01 16:34:43,862 DEBUG: No segmentation for 007_NIR.JPG, no features masked.
2022-07-01 16:34:45,588 DEBUG: No segmentation for 001_NIR.JPG, no features masked.
2022-07-01 16:34:45,780 DEBUG: No segmentation for 002_RGB.JPG, no features masked.
2022-07-01 16:34:46,480 DEBUG: Found 43006 points in 26.624876499176025s
2022-07-01 16:34:46,481 DEBUG: done
2022-07-01 16:34:46,772 DEBUG: Found 38795 points in 26.916388750076294s
2022-07-01 16:34:46,772 DEBUG: done
2022-07-01 16:34:48,821 DEBUG: Found 35699 points in 31.983975172042847s
2022-07-01 16:34:48,822 DEBUG: done
2022-07-01 16:34:50,920 DEBUG: No segmentation for 001_RGB.JPG, no features masked.
2022-07-01 16:34:54,674 DEBUG: No segmentation for 010_RGB.JPG, no features masked.
2022-07-01 16:34:54,987 DEBUG: No segmentation for 010_NIR.JPG, no features masked.
2022-07-01 16:34:55,036 DEBUG: No segmentation for 008_RGB.JPG, no features masked.
2022-07-01 16:34:56,713 DEBUG: No segmentation for 004_RGB.JPG, no features masked.
2022-07-01 16:34:57,176 DEBUG: No segmentation for 009_RGB.JPG, no features masked.
2022-07-01 16:34:58,044 DEBUG: No segmentation for 005_RGB.JPG, no features masked.
2022-07-01 16:35:01,812 DEBUG: No segmentation for 007_RGB.JPG, no features masked.
2022-07-01 16:35:04,712 DEBUG: No segmentation for 009_NIR.JPG, no features masked.
2022-07-01 16:35:04,875 DEBUG: No segmentation for 005_NIR.JPG, no features masked.
[INFO] running “/code/SuperBuild/install/bin/opensfm/bin/opensfm” match_features “/var/www/data/836c3ce2-0e85-409a-88f3-f32c18473465/opensfm”
2022-07-01 16:35:09,390 INFO: Matching 180 image pairs
2022-07-01 16:35:09,416 INFO: Computing pair matching with 24 processes
2022-07-01 16:35:10,220 DEBUG: No segmentation for 008_NIR.JPG, no features masked.
2022-07-01 16:35:10,254 DEBUG: No segmentation for 004_NIR.JPG, no features masked.
2022-07-01 16:35:10,284 DEBUG: No segmentation for 003_NIR.JPG, no features masked.
2022-07-01 16:35:10,347 DEBUG: No segmentation for 001_NIR.JPG, no features masked.
2022-07-01 16:35:10,410 DEBUG: No segmentation for 007_NIR.JPG, no features masked.
2022-07-01 16:35:10,474 DEBUG: No segmentation for 002_NIR.JPG, no features masked.
2022-07-01 16:35:11,183 DEBUG: No segmentation for 006_NIR.JPG, no features masked.
2022-07-01 16:35:11,313 DEBUG: No segmentation for 009_NIR.JPG, no features masked.
2022-07-01 16:35:12,202 DEBUG: Matching 004_NIR.JPG and 003_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 2.684 T-robust: 0.031 T-total: 2.721 Matches: 469 Robust: 443 Success: True
2022-07-01 16:35:12,289 DEBUG: No segmentation for 005_NIR.JPG, no features masked.
2022-07-01 16:35:12,801 DEBUG: No segmentation for 009_RGB.JPG, no features masked.
2022-07-01 16:35:12,806 DEBUG: Matching 001_NIR.JPG and 007_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 3.265 T-robust: 0.064 T-total: 3.332 Matches: 21 Robust: 9 Success: False
2022-07-01 16:35:12,907 DEBUG: No segmentation for 007_RGB.JPG, no features masked.
2022-07-01 16:35:12,984 DEBUG: No segmentation for 003_RGB.JPG, no features masked.
2022-07-01 16:35:13,186 DEBUG: No segmentation for 002_RGB.JPG, no features masked.
2022-07-01 16:35:13,275 DEBUG: No segmentation for 010_NIR.JPG, no features masked.
2022-07-01 16:35:13,278 DEBUG: No segmentation for 010_RGB.JPG, no features masked.
2022-07-01 16:35:13,428 DEBUG: No segmentation for 001_RGB.JPG, no features masked.
2022-07-01 16:35:13,677 DEBUG: Matching 001_NIR.JPG and 006_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 4.139 T-robust: 0.073 T-total: 4.220 Matches: 36 Robust: 12 Success: False
2022-07-01 16:35:13,746 DEBUG: No segmentation for 008_RGB.JPG, no features masked.
2022-07-01 16:35:13,827 DEBUG: No segmentation for 006_RGB.JPG, no features masked.
2022-07-01 16:35:14,424 DEBUG: Matching 002_NIR.JPG and 006_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 1.514 T-robust: 0.075 T-total: 1.609 Matches: 42 Robust: 11 Success: False
2022-07-01 16:35:14,818 DEBUG: No segmentation for 004_RGB.JPG, no features masked.
2022-07-01 16:35:14,866 DEBUG: Matching 001_NIR.JPG and 009_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 5.334 T-robust: 0.025 T-total: 5.359 Matches: 43 Robust: 10 Success: False
2022-07-01 16:35:15,213 DEBUG: Matching 008_NIR.JPG and 005_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 5.750 T-robust: 0.005 T-total: 5.755 Matches: 97 Robust: 63 Success: True
2022-07-01 16:35:15,559 DEBUG: Matching 004_NIR.JPG and 005_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 6.083 T-robust: 0.011 T-total: 6.095 Matches: 494 Robust: 432 Success: True
2022-07-01 16:35:16,687 DEBUG: Matching 008_NIR.JPG and 009_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 1.448 T-robust: 0.025 T-total: 1.473 Matches: 75 Robust: 38 Success: True
2022-07-01 16:35:17,135 DEBUG: No segmentation for 005_RGB.JPG, no features masked.
2022-07-01 16:35:17,142 DEBUG: Matching 003_NIR.JPG and 009_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 7.658 T-robust: 0.022 T-total: 7.681 Matches: 42 Robust: 10 Success: False
2022-07-01 16:35:17,262 DEBUG: Matching 006_NIR.JPG and 009_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 5.037 T-robust: 0.021 T-total: 5.058 Matches: 33 Robust: 10 Success: False
2022-07-01 16:35:17,542 DEBUG: Matching 009_NIR.JPG and 010_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 8.054 T-robust: 0.005 T-total: 8.060 Matches: 1589 Robust: 1444 Success: True
2022-07-01 16:35:17,670 DEBUG: Matching 004_NIR.JPG and 009_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 1.996 T-robust: 0.114 T-total: 2.110 Matches: 50 Robust: 11 Success: False
2022-07-01 16:35:17,845 DEBUG: Matching 001_NIR.JPG and 010_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 8.340 T-robust: 0.047 T-total: 8.386 Matches: 55 Robust: 11 Success: False
2022-07-01 16:35:18,120 DEBUG: Matching 002_NIR.JPG and 008_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 0.823 T-robust: 0.034 T-total: 0.857 Matches: 31 Robust: 10 Success: False
2022-07-01 16:35:18,941 DEBUG: Matching 007_NIR.JPG and 001_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 9.467 T-robust: 0.022 T-total: 9.490 Matches: 25 Robust: 11 Success: False
2022-07-01 16:35:19,118 DEBUG: Matching 007_RGB.JPG and 008_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 9.626 T-robust: 0.040 T-total: 9.667 Matches: 64 Robust: 31 Success: True
2022-07-01 16:35:19,695 DEBUG: Matching 003_NIR.JPG and 005_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 1.834 T-robust: 0.014 T-total: 1.849 Matches: 166 Robust: 127 Success: True
2022-07-01 16:35:20,252 DEBUG: Matching 001_NIR.JPG and 006_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 10.777 T-robust: 0.022 T-total: 10.799 Matches: 36 Robust: 10 Success: False
2022-07-01 16:35:20,413 DEBUG: Matching 007_NIR.JPG and 009_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 3.200 T-robust: 0.066 T-total: 3.266 Matches: 49 Robust: 19 Success: False
2022-07-01 16:35:20,704 DEBUG: Matching 007_NIR.JPG and 005_RGB.JPG. Matcher: FLANN (symmetric) T-desc: 3.993 T-robust: 0.022 T-total: 4.016 Matches: 52 Robust: 16 Success: False
2022-07-01 16:35:20,792 DEBUG: Matching 003_NIR.JPG and 009_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 1.627 T-robust: 0.042 T-total: 1.670 Matches: 46 Robust: 11 Success: False
2022-07-01 16:35:21,167 DEBUG: Matching 001_NIR.JPG and 005_NIR.JPG. Matcher: FLANN (symmetric) T-desc: 3.418 T-robust: 0.066 T-total: 3.485 Matches: 41 Robust: 11 Success: False
2022-07-01 16:35:21,487 DEBUG: Matching 003_RGB.

Hi, thank’s for your help.
it’s the same thing (see error reported in the “console” file even with 112 images…
I think it is something related to the fact that it does not see images as Multicamera or Multiband
I have attached only 10 images for simplicity and to avoid long waiting times in the various attempts but if you think it is better I insert all 112 images (300mb)
The error that it gives me and that you can see too is the same both with 112 images and with 20

1 Like

Can you share the 300 dataset?

I check the website, African also use odm to process. About should works.

The 10 small set doesn’t have side overlap. Maybe this is the problem.

1 Like

Do you have the camera specification sheet?

1 Like

“The 10 small set doesn’t have side overlap. Maybe this is the problem.”

impossible, the same error with all 112 images

1 Like

Hi, this is the dataset complete of 112 images (NIR+RGB).
Dataset 112 images
Consider that if I process 56 RGB photos or 56 NIR photos individually I have no problems in Default mode.
The problem is when I try to process all photos (NIR + RGB) in Multispectral mode.
Specifications of the camera:
Technical specification of AgroCam Pro NIR camera.pdf (184.3 KB)
Technical specification of AgroCam Pro RGB camera.pdf (177.9 KB)

2 Likes

Analyzing the log of the two processing processes in multispectral mode, the problem seems to be identified independently by the number of images processed.
WebODM looks for an image that cannot exist because my files are all JPGs:

PIL.UnidentifiedImageError: cannot identify image file <_io.BufferedReader name=’/var/www/data/77b2e2c0-7b97-42b7-a114-d4970e80eb3b/opensfm/undistorted/images/008_NIR.JPG.tif’>

Why are you looking for a tiff file? maybe the multispectral can only be processed with .tif?

My two trys both fail.

WebODM 1.9.14

2022-07-02 20:18:43,411 DEBUG: Undistorting image 2022_0624_101546_003_geotag.JPG
2022-07-02 20:18:44,802 DEBUG: Undistorting image 2022_0624_101814_055_geotag.JPG
[INFO] running “/code/SuperBuild/install/bin/opensfm/bin/opensfm” export_visualsfm --points “/var/www/data/9eebe2fa-69e6-492a-84df-34c93dda0fa3/opensfm”
Traceback (most recent call last):
File “/code/SuperBuild/install/bin/opensfm/bin/opensfm_main.py”, line 25, in
commands.command_runner(
File “/code/SuperBuild/install/bin/opensfm/opensfm/commands/command_runner.py”, line 38, in command_runner
command.run(data, args)
File “/code/SuperBuild/install/bin/opensfm/opensfm/commands/command.py”, line 13, in run
self.run_impl(data, args)
File “/code/SuperBuild/install/bin/opensfm/opensfm/commands/export_visualsfm.py”, line 13, in run_impl
export_visualsfm.run_dataset(dataset, args.points, args.image_list)
File “/code/SuperBuild/install/bin/opensfm/opensfm/actions/export_visualsfm.py”, line 29, in run_dataset
export(reconstructions[0], tracks_manager, udata, points, export_only)
File “/code/SuperBuild/install/bin/opensfm/opensfm/actions/export_visualsfm.py”, line 49, in export
shot_size_cache[shot.id] = udata.undistorted_image_size(shot.id)
File “/code/SuperBuild/install/bin/opensfm/opensfm/dataset.py”, line 766, in undistorted_image_size
return self.io_handler.image_size(self._undistorted_image_file(image))
File “/code/SuperBuild/install/bin/opensfm/opensfm/io.py”, line 1501, in image_size
return image_size_from_fileobject(fb)
File “/code/SuperBuild/install/bin/opensfm/opensfm/io.py”, line 1340, in image_size_from_fileobject
with Image.open(fb) as img:
File “/usr/local/lib/python3.9/dist-packages/PIL/Image.py”, line 3023, in open
raise UnidentifiedImageError(
PIL.UnidentifiedImageError: cannot identify image file <_io.BufferedReader name=’/var/www/data/9eebe2fa-69e6-492a-84df-34c93dda0fa3/opensfm/undistorted/images/2022_0624_101755_031_geotag.JPG.tif’>

===== Dumping Info for Geeks (developers need this to fix bugs) =====
Child returned 1
Traceback (most recent call last):
File “/code/stages/odm_app.py”, line 94, in execute
self.first_stage.run()
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 328, in run
self.process(self.args, outputs)
File “/code/stages/run_opensfm.py”, line 193, in process
octx.run(‘export_visualsfm --points’)
File “/code/opendm/osfm.py”, line 34, in run
system.run(’"%s" %s “%s”’ %
File “/code/opendm/system.py”, line 106, in run
raise SubprocessException(“Child returned {}”.format(retcode), retcode)
opendm.system.SubprocessExceptio


n: Child returned 1

===== Done, human-readable information to follow… =====

[ERROR] Uh oh! Processing stopped because of strange values in the reconstruction. This is often a sign that the input data has some issues or the software cannot deal with it. Have you followed best practices for data acquisition? See Flying Tips — OpenDroneMap 2.8.5 documentation

===== Dumping Info for Geeks (developers need this to fix bugs) =====
Child returned 1
Traceback (most recent call last):
File “/code/stages/odm_app.py”, line 94, in execute
self.first_stage.run()
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 347, in run
self.next_stage.run(outputs)
File “/code/opendm/types.py”, line 328, in run
self.process(self.args, outputs)
File “/code/stages/run_opensfm.py”, line 193, in process
octx.run(‘export_visualsfm --points’)
File “/code/opendm/osfm.py”, line 34, in run
system.run(’"%s" %s “%s”’ %
File “/code/opendm/system.py”, line 106, in run
raise SubprocessException(“Child returned {}”.format(retcode), retcode)
opendm.system.SubprocessException: Child returned 1

===== Done, human-readable information to follow… =====

[ERROR] Uh oh! Processing stopped because of strange values in the reconstruction. This is often a sign that the input data has some issues or the software cannot deal with it. Have you followed best practices for data acquisition? See Flying Tips — OpenDroneMap 2.8.5 documentation

RGB only runs great.

But only NIR photos, fail.
===== Dumping Info for Geeks (developers need this to fix bugs) ===== Child returned 1 Traceback (most recent call last): File “/code/stages/odm_app.py”, line 94, in execute self.first_stage.run() File “/code/opendm/types.py”, line 347, in run self.next_stage.run(outputs) File “/code/opendm/types.py”, line 347, in run self.next_stage.run(outputs) File “/code/opendm/types.py”, line 347, in run self.next_stage.run(outputs) File “/code/opendm/types.py”, line 328, in run self.process(self.args, outputs) File “/code/stages/run_opensfm.py”, line 193, in process octx.run(‘export_visualsfm --points’) File “/code/opendm/osfm.py”, line 34, in run system.run(’"%s" %s “%s”’ % File “/code/opendm/system.py”, line 106, in run raise SubprocessException(“Child returned {}”.format(retcode), retcode) opendm.system.SubprocessException: Child returned 1 ===== Done, human-readable information to follow… ===== [ERROR] Uh oh! Processing stopped because of strange values in the reconstruction. This is often a sign that the input data has some issues or the software cannot deal with it. Have you followed best practices for data acquisition? See Flying Tips — OpenDroneMap 2.8.5 documentation

Edit

Restart

Delete

1 Like

In “Predefinited” modality i have elaborated separately NIR and RGB.
The problem Is “Multispectral” modality.