TY - JOUR
T1 - An approach based on Deep Learning for tree species classification in LiDAR data acquired in mixed forest
AU - Marinelli, Daniele
AU - Paris, C.
AU - Bruzzone, Lorenzo
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2022
Y1 - 2022
N2 - This letter proposes a novel method based on Deep Learning (DL) to forest species classification in airborne Light Detection and Ranging (LiDAR) data. Differently from the state-of-the-art approaches, the proposed method: 1) does not assume any prior knowledge either on the forest to be classified or on the sensor used to acquire the LiDAR data and 2) can be applied to heterogeneous forest characterized by mixed species. First, the 3-D point cloud of each individual tree is decomposed into eight angular sectors to generate a multislice representation of the vertical structure of the tree. This representation models the foliage, the stem, and the branches of the tree crown as well as depicts the internal and external crown properties. Then, a multiview convolutional neural network (MVCNN) DL automatically extracts features used to discriminate the different tree species. This network is pretrained on the massive ImageNet database, thus guaranteeing fast convergence with a relatively small number of ground reference data. Experiments were carried out on high-density airborne LiDAR data collected over a multilayer multiage forest characterized by four conifers and three broadleaf species. The proposed method outperformed the state-of-the-art approaches increasing the Overall Accuracy (OA) up to 16% and 18.9% compared to a DL and a shallow tree species classification methods, respectively. When applied to coniferous or broadlaef forests, the proposed method showed an increase of OA 10.1% and 15.9% (for conifers) and 9.5% and 21.6% (for broadleafs) compared to the DL and shallow methods, respectively.
AB - This letter proposes a novel method based on Deep Learning (DL) to forest species classification in airborne Light Detection and Ranging (LiDAR) data. Differently from the state-of-the-art approaches, the proposed method: 1) does not assume any prior knowledge either on the forest to be classified or on the sensor used to acquire the LiDAR data and 2) can be applied to heterogeneous forest characterized by mixed species. First, the 3-D point cloud of each individual tree is decomposed into eight angular sectors to generate a multislice representation of the vertical structure of the tree. This representation models the foliage, the stem, and the branches of the tree crown as well as depicts the internal and external crown properties. Then, a multiview convolutional neural network (MVCNN) DL automatically extracts features used to discriminate the different tree species. This network is pretrained on the massive ImageNet database, thus guaranteeing fast convergence with a relatively small number of ground reference data. Experiments were carried out on high-density airborne LiDAR data collected over a multilayer multiage forest characterized by four conifers and three broadleaf species. The proposed method outperformed the state-of-the-art approaches increasing the Overall Accuracy (OA) up to 16% and 18.9% compared to a DL and a shallow tree species classification methods, respectively. When applied to coniferous or broadlaef forests, the proposed method showed an increase of OA 10.1% and 15.9% (for conifers) and 9.5% and 21.6% (for broadleafs) compared to the DL and shallow methods, respectively.
KW - Deep Learning (DL)
KW - Light detection and ranging (LiDAR)
KW - Mixed forest
KW - Remote sensing (RS)
KW - Tree species
KW - 22/4 OA procedure
KW - ITC-ISI-JOURNAL-ARTICLE
U2 - 10.1109/LGRS.2022.3181680
DO - 10.1109/LGRS.2022.3181680
M3 - Article
AN - SCOPUS:85132726581
SN - 1545-598X
VL - 19
JO - IEEE geoscience and remote sensing letters
JF - IEEE geoscience and remote sensing letters
M1 - 7004305
ER -