“Looking for the trees in the forest“ An attempt to finding the best segmentation-based methodology to discriminate deciduous trees in the Dubbarp area, Sweden
(2021) In Student thesis series INES NGEM01 20201Dept of Physical Geography and Ecosystem Science
- Abstract
- Finding a solution to automatically identify tree crowns in has been a well discussed topic in the academic community. Different ideas have been put to practice, with researches mainly targeting coniferous forests. In a global context, papers concerning deciduous trees are rare and their results differ in relation to their respective study zone. Segmentation-based methodologies are a newcomer in the world of wide area remote sensing and their predicting power still needs to be put to test.
Modern software such as Trimble’s eCognition enables the end-user the power to easily configure the parametrizations of complex object creating algorithms. This paper applies the multi-resolution segmentation algorithm to a study area in in southern... (More) - Finding a solution to automatically identify tree crowns in has been a well discussed topic in the academic community. Different ideas have been put to practice, with researches mainly targeting coniferous forests. In a global context, papers concerning deciduous trees are rare and their results differ in relation to their respective study zone. Segmentation-based methodologies are a newcomer in the world of wide area remote sensing and their predicting power still needs to be put to test.
Modern software such as Trimble’s eCognition enables the end-user the power to easily configure the parametrizations of complex object creating algorithms. This paper applies the multi-resolution segmentation algorithm to a study area in in southern Sweden, in an attempt to find the best methodology for automatic tree crown recognition of trees worthy of protection. Trees worthy of protection host a wide variety of entomofauna and have been defined by the Swedish Environment Protection Agency as important elements in their plan to preserve the country’s endangered ecosystems. They are usually old deciduous trees with an extended crown.
Fourteen experiments based on different parametrizations of the multi-resolution segmentation algorithm have been carried on available LiDAR and near-infrared data from the study area. Their results show that two dimensional elevation data and seasonal difference in near-infrared value are not sufficient conditions to accurately pinpoint the location of the crowns belonging to the trees worthy of protection.
Discussion about the possible shortcomings of the research and suggestions for future exploration are also provided in the paper. (Less) - Popular Abstract
- Remote sensing is the scientific field which allows researchers to analyze Earth’s features from a far. It makes use of a wide array of modern technologies such as the analysis of aerial and satellite imagery. Remote sensing has many applications including the study of vegetal associations and ecosystem functionality. The Green Infrastructure Project, coined by the Swedish Environmental Protection Agency (in Swedish: Naturvårdsverket) intends to create a network of natural corridors that would enable species to spread and move in the landscape and protect vulnerable species, including old trees. Old trees are home to a wide variety of species and their identification in the field would be essential to trace the contours of the future green... (More)
- Remote sensing is the scientific field which allows researchers to analyze Earth’s features from a far. It makes use of a wide array of modern technologies such as the analysis of aerial and satellite imagery. Remote sensing has many applications including the study of vegetal associations and ecosystem functionality. The Green Infrastructure Project, coined by the Swedish Environmental Protection Agency (in Swedish: Naturvårdsverket) intends to create a network of natural corridors that would enable species to spread and move in the landscape and protect vulnerable species, including old trees. Old trees are home to a wide variety of species and their identification in the field would be essential to trace the contours of the future green corridors. Such an attempt would be very time consuming by employing specialists to do field recognition. Therefore the usage of remote sensing based solutions has been proposed. This paper presents an attempt to use a remote sensing specific methodology to automatically recognize trees worthy of protection (old) based on satellite and aerial imagery. A study area near Osby, Scania, covered mainly by deciduous forest is chosen to test the success rate of a remote sensing imagery processing algorithm, the multi-resolution segmentation for identifying the crowns of the trees worthy of protection. The multi-resolution segmentation algorithm creates “image patches”, known as objects, based on input imagery and user defined parameters of the algorithm. A number of 14 experiments which test different parameter configurations of the algorithm demonstrate that elevation and near-infrared information are not enough to provide an accurate description of tree crowns in the study area. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9037357
- author
- Patrascu, Mihai LU
- supervisor
-
- Jonas Ardö LU
- organization
- course
- NGEM01 20201
- year
- 2021
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Physical Geography and Ecosystem analysis, segmentation analysis, tree crown recognition, eCognition, Scania, Geomatics
- publication/series
- Student thesis series INES
- report number
- 531
- language
- English
- id
- 9037357
- date added to LUP
- 2021-01-26 10:18:07
- date last changed
- 2021-01-26 10:18:07
@misc{9037357,
abstract = {{Finding a solution to automatically identify tree crowns in has been a well discussed topic in the academic community. Different ideas have been put to practice, with researches mainly targeting coniferous forests. In a global context, papers concerning deciduous trees are rare and their results differ in relation to their respective study zone. Segmentation-based methodologies are a newcomer in the world of wide area remote sensing and their predicting power still needs to be put to test.
Modern software such as Trimble’s eCognition enables the end-user the power to easily configure the parametrizations of complex object creating algorithms. This paper applies the multi-resolution segmentation algorithm to a study area in in southern Sweden, in an attempt to find the best methodology for automatic tree crown recognition of trees worthy of protection. Trees worthy of protection host a wide variety of entomofauna and have been defined by the Swedish Environment Protection Agency as important elements in their plan to preserve the country’s endangered ecosystems. They are usually old deciduous trees with an extended crown.
Fourteen experiments based on different parametrizations of the multi-resolution segmentation algorithm have been carried on available LiDAR and near-infrared data from the study area. Their results show that two dimensional elevation data and seasonal difference in near-infrared value are not sufficient conditions to accurately pinpoint the location of the crowns belonging to the trees worthy of protection.
Discussion about the possible shortcomings of the research and suggestions for future exploration are also provided in the paper.}},
author = {{Patrascu, Mihai}},
language = {{eng}},
note = {{Student Paper}},
series = {{Student thesis series INES}},
title = {{“Looking for the trees in the forest“ An attempt to finding the best segmentation-based methodology to discriminate deciduous trees in the Dubbarp area, Sweden}},
year = {{2021}},
}