DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET
The assessment of the forests’ health conditions is an important task for biodiversity, forest management, global environment monitoring, and carbon dynamics. Several research works were proposed to evaluate the state condition of a forest based on remote sensing technology. Concerning existing tech...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2019-09-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W16/127/2019/isprs-archives-XLII-2-W16-127-2019.pdf |
id |
doaj-72bf32b7b76344f4b04816c03d4dc2d8 |
---|---|
record_format |
Article |
spelling |
doaj-72bf32b7b76344f4b04816c03d4dc2d82020-11-24T21:27:49ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342019-09-01XLII-2-W1612713310.5194/isprs-archives-XLII-2-W16-127-2019DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENETS. Jiang0W. Yao1W. Yao2M. Heurich3Department of Land Surveying and Geo-informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, ChinaDepartment of Land Surveying and Geo-informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, ChinaResearch Institute for Sustainable Urban Development, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, ChinaDept. for Conservation and Research, Bavarian Forest National Park, 94481 Grafenau, GermanyThe assessment of the forests’ health conditions is an important task for biodiversity, forest management, global environment monitoring, and carbon dynamics. Several research works were proposed to evaluate the state condition of a forest based on remote sensing technology. Concerning existing technologies, employing traditional machine learning approaches to detect the dead wood in aerial colour-infrared (CIR) imagery is one of the major trends due to its spectral capability to explicitly capturing vegetation health conditions. However, the complicated scene with background noise restricted the accuracy of existing approaches as those detectors normally utilized hand-crafted features. Currently, deep neural networks are widely used in computer vision tasks and prove that features learnt by the model itself perform much better than the hand-crafted features. The semantic image segmentation is a pixel-level classification task, which is best suitable to dead wood detection in very high resolution (VHR) mode because it enables the model to identify and classify very dense and detailed components on the tree objects. In this paper, an optimized FCN-DenseNet is proposed to detect dead wood (i.e. standing dead tree and fallen tree) in a complicated temperate forest environment. Since the appearance of dead trees generally occupies greatly different scales and sizes; several pooling procedures are employed to extract multi-scale features and dense connection is employed to enhance the inline connection among the scales. Our proposed deep neural network is evaluated over VHR CIR imagery (GSD-10cm) captured in a natural temperate forest in Bavarian national forest park, Germany, which has undergone on-site bark beetle attack. The results show that the boundary of dead trees can be accurately segmented, and the classification are performed with a high accuracy, even though only one labelled image with moderate size is used for training the deep neural network.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W16/127/2019/isprs-archives-XLII-2-W16-127-2019.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
S. Jiang W. Yao W. Yao M. Heurich |
spellingShingle |
S. Jiang W. Yao W. Yao M. Heurich DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
author_facet |
S. Jiang W. Yao W. Yao M. Heurich |
author_sort |
S. Jiang |
title |
DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET |
title_short |
DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET |
title_full |
DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET |
title_fullStr |
DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET |
title_full_unstemmed |
DEAD WOOD DETECTION BASED ON SEMANTIC SEGMENTATION OF VHR AERIAL CIR IMAGERY USING OPTIMIZED FCN-DENSENET |
title_sort |
dead wood detection based on semantic segmentation of vhr aerial cir imagery using optimized fcn-densenet |
publisher |
Copernicus Publications |
series |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
issn |
1682-1750 2194-9034 |
publishDate |
2019-09-01 |
description |
The assessment of the forests’ health conditions is an important task for biodiversity, forest management, global environment monitoring, and carbon dynamics. Several research works were proposed to evaluate the state condition of a forest based on remote sensing technology. Concerning existing technologies, employing traditional machine learning approaches to detect the dead wood in aerial colour-infrared (CIR) imagery is one of the major trends due to its spectral capability to explicitly capturing vegetation health conditions. However, the complicated scene with background noise restricted the accuracy of existing approaches as those detectors normally utilized hand-crafted features. Currently, deep neural networks are widely used in computer vision tasks and prove that features learnt by the model itself perform much better than the hand-crafted features. The semantic image segmentation is a pixel-level classification task, which is best suitable to dead wood detection in very high resolution (VHR) mode because it enables the model to identify and classify very dense and detailed components on the tree objects. In this paper, an optimized FCN-DenseNet is proposed to detect dead wood (i.e. standing dead tree and fallen tree) in a complicated temperate forest environment. Since the appearance of dead trees generally occupies greatly different scales and sizes; several pooling procedures are employed to extract multi-scale features and dense connection is employed to enhance the inline connection among the scales. Our proposed deep neural network is evaluated over VHR CIR imagery (GSD-10cm) captured in a natural temperate forest in Bavarian national forest park, Germany, which has undergone on-site bark beetle attack. The results show that the boundary of dead trees can be accurately segmented, and the classification are performed with a high accuracy, even though only one labelled image with moderate size is used for training the deep neural network. |
url |
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W16/127/2019/isprs-archives-XLII-2-W16-127-2019.pdf |
work_keys_str_mv |
AT sjiang deadwooddetectionbasedonsemanticsegmentationofvhraerialcirimageryusingoptimizedfcndensenet AT wyao deadwooddetectionbasedonsemanticsegmentationofvhraerialcirimageryusingoptimizedfcndensenet AT wyao deadwooddetectionbasedonsemanticsegmentationofvhraerialcirimageryusingoptimizedfcndensenet AT mheurich deadwooddetectionbasedonsemanticsegmentationofvhraerialcirimageryusingoptimizedfcndensenet |
_version_ |
1725973181127196672 |