Web Cameras In Automatic Autumn Colour Monitoring

Heikki Astola, Matthieu Molinier, Tapani Mikkola, Eero Kubin

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

6 Citations (Scopus)

Abstract

The objective of ForSe - Season Monitoring study was to develop an automatic method to analyze web-camera images of nature. As the outcome the image analysis produces indices that indicate the seasonal development stage of the forest (e.g. degree of autumn colour of deciduous trees). IP web-cameras of a pilot camera network were programmed to take one image in 15 minute interval on daylight hours during autumn period. One camera was used as a source of the training data (Enontekiö), and one for testing data (Oulanka). The image data was preprocessed to reduce noise and to and spectral angle feature was calculated to compensate the illumination variations between consequential images and within a single image. Selected areas of the training site camera images of autumn season were classified into six classes describing the seasonal status of the leaves (green, light green, yellow, red, brown, fallen). The spectral angle features were calculated for these areas and clustered by K-means into 30 clusters. Class labels were assigned to the cluster centres using k-NN method (k=5). To see the progress of a certain colour class in the time series of images of a test site camera, the classified pixels within selected regions of interest (ROI) were used to produce a continuous season colour index (SCI). The behaviour of the index was compared with a reference classification supplied by phenology experts from Finnish Forest Research Institute (Metla). The results were well in line with the reference classification, and show that the implemented processing chain can be used to obtain a numerical index describing the seasonal status of deciduous leaves' colour.
Original languageEnglish
Title of host publicationProceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008
PublisherIEEE Institute of Electrical and Electronic Engineers
PagesIII824-III827
ISBN (Print)978-1-4244-2807-6, 978-1-4244-2808-3
DOIs
Publication statusPublished - 2008
MoE publication typeA4 Article in a conference publication
EventIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2008 - Boston, MA, United States
Duration: 7 Jul 200811 Jul 2008

Conference

ConferenceIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2008
Abbreviated titleIGARSS 2008
CountryUnited States
CityBoston, MA
Period7/07/0811/07/08

Fingerprint

autumn
monitoring
deciduous tree
image analysis
phenology
pixel
time series
index
method

Keywords

  • change detection
  • SAR
  • dual-polarisation
  • TerraSAR-X
  • clearcuts

Cite this

Astola, H., Molinier, M., Mikkola, T., & Kubin, E. (2008). Web Cameras In Automatic Autumn Colour Monitoring. In Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008 (pp. III824-III827). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/IGARSS.2008.4779476
Astola, Heikki ; Molinier, Matthieu ; Mikkola, Tapani ; Kubin, Eero. / Web Cameras In Automatic Autumn Colour Monitoring. Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008. IEEE Institute of Electrical and Electronic Engineers , 2008. pp. III824-III827
@inproceedings{910dd564df5342cdaae2df9f10080431,
title = "Web Cameras In Automatic Autumn Colour Monitoring",
abstract = "The objective of ForSe - Season Monitoring study was to develop an automatic method to analyze web-camera images of nature. As the outcome the image analysis produces indices that indicate the seasonal development stage of the forest (e.g. degree of autumn colour of deciduous trees). IP web-cameras of a pilot camera network were programmed to take one image in 15 minute interval on daylight hours during autumn period. One camera was used as a source of the training data (Enonteki{\"o}), and one for testing data (Oulanka). The image data was preprocessed to reduce noise and to and spectral angle feature was calculated to compensate the illumination variations between consequential images and within a single image. Selected areas of the training site camera images of autumn season were classified into six classes describing the seasonal status of the leaves (green, light green, yellow, red, brown, fallen). The spectral angle features were calculated for these areas and clustered by K-means into 30 clusters. Class labels were assigned to the cluster centres using k-NN method (k=5). To see the progress of a certain colour class in the time series of images of a test site camera, the classified pixels within selected regions of interest (ROI) were used to produce a continuous season colour index (SCI). The behaviour of the index was compared with a reference classification supplied by phenology experts from Finnish Forest Research Institute (Metla). The results were well in line with the reference classification, and show that the implemented processing chain can be used to obtain a numerical index describing the seasonal status of deciduous leaves' colour.",
keywords = "change detection, SAR, dual-polarisation, TerraSAR-X, clearcuts",
author = "Heikki Astola and Matthieu Molinier and Tapani Mikkola and Eero Kubin",
note = "Project code: 18947",
year = "2008",
doi = "10.1109/IGARSS.2008.4779476",
language = "English",
isbn = "978-1-4244-2807-6",
pages = "III824--III827",
booktitle = "Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Astola, H, Molinier, M, Mikkola, T & Kubin, E 2008, Web Cameras In Automatic Autumn Colour Monitoring. in Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008. IEEE Institute of Electrical and Electronic Engineers , pp. III824-III827, IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2008, Boston, MA, United States, 7/07/08. https://doi.org/10.1109/IGARSS.2008.4779476

Web Cameras In Automatic Autumn Colour Monitoring. / Astola, Heikki; Molinier, Matthieu; Mikkola, Tapani; Kubin, Eero.

Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008. IEEE Institute of Electrical and Electronic Engineers , 2008. p. III824-III827.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Web Cameras In Automatic Autumn Colour Monitoring

AU - Astola, Heikki

AU - Molinier, Matthieu

AU - Mikkola, Tapani

AU - Kubin, Eero

N1 - Project code: 18947

PY - 2008

Y1 - 2008

N2 - The objective of ForSe - Season Monitoring study was to develop an automatic method to analyze web-camera images of nature. As the outcome the image analysis produces indices that indicate the seasonal development stage of the forest (e.g. degree of autumn colour of deciduous trees). IP web-cameras of a pilot camera network were programmed to take one image in 15 minute interval on daylight hours during autumn period. One camera was used as a source of the training data (Enontekiö), and one for testing data (Oulanka). The image data was preprocessed to reduce noise and to and spectral angle feature was calculated to compensate the illumination variations between consequential images and within a single image. Selected areas of the training site camera images of autumn season were classified into six classes describing the seasonal status of the leaves (green, light green, yellow, red, brown, fallen). The spectral angle features were calculated for these areas and clustered by K-means into 30 clusters. Class labels were assigned to the cluster centres using k-NN method (k=5). To see the progress of a certain colour class in the time series of images of a test site camera, the classified pixels within selected regions of interest (ROI) were used to produce a continuous season colour index (SCI). The behaviour of the index was compared with a reference classification supplied by phenology experts from Finnish Forest Research Institute (Metla). The results were well in line with the reference classification, and show that the implemented processing chain can be used to obtain a numerical index describing the seasonal status of deciduous leaves' colour.

AB - The objective of ForSe - Season Monitoring study was to develop an automatic method to analyze web-camera images of nature. As the outcome the image analysis produces indices that indicate the seasonal development stage of the forest (e.g. degree of autumn colour of deciduous trees). IP web-cameras of a pilot camera network were programmed to take one image in 15 minute interval on daylight hours during autumn period. One camera was used as a source of the training data (Enontekiö), and one for testing data (Oulanka). The image data was preprocessed to reduce noise and to and spectral angle feature was calculated to compensate the illumination variations between consequential images and within a single image. Selected areas of the training site camera images of autumn season were classified into six classes describing the seasonal status of the leaves (green, light green, yellow, red, brown, fallen). The spectral angle features were calculated for these areas and clustered by K-means into 30 clusters. Class labels were assigned to the cluster centres using k-NN method (k=5). To see the progress of a certain colour class in the time series of images of a test site camera, the classified pixels within selected regions of interest (ROI) were used to produce a continuous season colour index (SCI). The behaviour of the index was compared with a reference classification supplied by phenology experts from Finnish Forest Research Institute (Metla). The results were well in line with the reference classification, and show that the implemented processing chain can be used to obtain a numerical index describing the seasonal status of deciduous leaves' colour.

KW - change detection

KW - SAR

KW - dual-polarisation

KW - TerraSAR-X

KW - clearcuts

U2 - 10.1109/IGARSS.2008.4779476

DO - 10.1109/IGARSS.2008.4779476

M3 - Conference article in proceedings

SN - 978-1-4244-2807-6

SN - 978-1-4244-2808-3

SP - III824-III827

BT - Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Astola H, Molinier M, Mikkola T, Kubin E. Web Cameras In Automatic Autumn Colour Monitoring. In Proceedings of 2008 IEEE International Conference on Geoscience and Remote Sensing Symposium, IGARSS 2008. IEEE Institute of Electrical and Electronic Engineers . 2008. p. III824-III827 https://doi.org/10.1109/IGARSS.2008.4779476