A New CBAM-P-Net Model for Few-Shot Forest Species Classification Using Airborne Hyperspectral Images

High-precision automatic identification and mapping of forest tree species composition is an important content of forest resource survey and monitoring. The airborne hyperspectral image contains rich spectral and spatial information, which provides the possibility of high-precision classification and mapping of forest tree species. Few-shot learning, as an application of deep learning, has become an effective method of image classification. Prototypical networks (P-Net) is a simple and practical deep learning network, which has significant advantages in solving few-shot classification problems. Considering the high band correlation and large data volume associated with airborne hyperspectral images, how to fully extract effective features, filter or reduce redundant features is the key to improving the classification accuracy of P-Net, in order to extract effective features in hyperspectral images and obtain a high-precision forest tree species classification model with limited samples. In this research, we embedded the convolutional block attention module (CBAM) between the convolution blocks of P-Net, the CBAM-P-Net was constructed, and a method to improve the feature extraction efficiency of the P-Net was proposed, although this method makes the network more complex and increases the computational cost to a certain extent. The results show that the combination strategy using Channel First for CBAM greatly improves the feature extraction efficiency of the model. In different sample windows, CBAM-P-Net has an average increase of 1.17% and 0.0129 in testing overall accuracy (OA) and kappa coefficient (Kappa). The optimal classification window is 17×17, the OA reaches 97.28%, and Kappa reaches 0.97, which is an increase of 1.95% and 0.0214 along with just 49 s of training time expended, respectively, compared with P-Net. Therefore, using a suitable sample window and applying the proposed CBAM-P-Net to classify airborne hyperspectral images can achieve high-precision classification and mapping of forest tree species.

Download Full-text

The Effect of Topographic Correction on Forest Tree Species Classification Accuracy

Remote Sensing ◽

10.3390/rs12050787 ◽

2020 ◽

Vol 12 (5) ◽

pp. 787

Author(s):

Chao Dong ◽

Gengxing Zhao ◽

Yan Meng ◽

Baihong Li ◽

Bo Peng

Keyword(s):

Remote Sensing ◽

Tree Species ◽

Forest Tree ◽

Species Classification ◽

Illumination Condition ◽

Topographic Correction ◽

Forest Tree Species ◽

Tree Species Classification ◽

Inconsistency Rate ◽

Rotation Model

Topographic correction can reduce the influences of topographic factors and improve the accuracy of forest tree species classification when using remote-sensing data to investigate forest resources. In this study, the Mount Taishan forest farm is the research area. Based on Landsat 8 OLI data and field survey subcompartment data, four topographic correction models (cosine model, C model, solar-canopy-sensor (SCS)+C model and empirical rotation model) were used on the Google Earth Engine (GEE) platform to carry out algorithmic data correction. Then, the tree species in the study area were classified by the random forest method. Combined with the tree species classification process, the topographic correction effects were analyzed, and the effects, advantages and disadvantages of each correction model were evaluated. The results showed that the SCS+C model and empirical rotation model were the best models in terms of visual effect, reducing the band standard deviation and adjusting the reflectance distribution. When we used the SCS+C model to correct the remote-sensing image, the total accuracy increased by 4% when using the full-coverage training areas to classify tree species and by nearly 13% when using the shadowless training area. In the illumination condition interval of 0.4–0.6, the inconsistency rate decreased significantly; however, the inconsistency rate increased with increasing illumination condition values. Topographic correction can enhance reflectance information in shaded areas and can significantly improve the image quality. Topographic correction can be used as a pretreatment method for forest species classification when the study area’s dominant tree species are in a low light intensity area.

Download Full-text

Mapping Tree Species Composition Using OHS-1 Hyperspectral Data and Deep Learning Algorithms in Changbai Mountains, Northeast China

Forests ◽

10.3390/f10090818 ◽

2019 ◽

Vol 10 (9) ◽

pp. 818

Author(s):

Yanbiao Xi ◽

Chunying Ren ◽

Zongming Wang ◽

Shiqing Wei ◽

Jialing Bai ◽

...

Keyword(s):

Deep Learning ◽

Tree Species ◽

Classification Accuracy ◽

Learning Algorithms ◽

Spectral Characteristics ◽

Great Influence ◽

Hyperspectral Images ◽

Changbai Mountains ◽

Species Classification ◽

Tree Species Classification

The accurate characterization of tree species distribution in forest areas can help significantly reduce uncertainties in the estimation of ecosystem parameters and forest resources. Deep learning algorithms have become a hot topic in recent years, but they have so far not been applied to tree species classification. In this study, one-dimensional convolutional neural network (Conv1D), a popular deep learning algorithm, was proposed to automatically identify tree species using OHS-1 hyperspectral images. Additionally, the random forest (RF) classifier was applied to compare to the algorithm of deep learning. Based on our experiments, we drew three main conclusions: First, the OHS-1 hyperspectral images used in this study have high spatial resolution (10 m), which reduces the influence of mixed pixel effect and greatly improves the classification accuracy. Second, limited by the amount of sample data, Conv1D-based classifier does not need too many layers to achieve high classification accuracy. In addition, the size of the convolution kernel has a great influence on the classification accuracy. Finally, the accuracy of Conv1D (85.04%) is higher than that of RF model (80.61%). Especially for broadleaf species with similar spectral characteristics, such as Manchurian walnut and aspen, the accuracy of Conv1D-based classifier is significantly higher than RF classifier (87.15% and 71.77%, respectively). Thus, the Conv1D-based deep learning framework combined with hyperspectral imagery can efficiently improve the accuracy of tree species classification and has great application prospects in the future.

Download Full-text

Spectral and Texture Features Combined for Forest Tree species Classification with Airborne Hyperspectral Imagery

Journal of the Indian Society of Remote Sensing ◽

10.1007/s12524-014-0392-6 ◽

2014 ◽

Vol 43 (1) ◽

pp. 101-107 ◽

Cited By ~ 20

Author(s):

Yuanyong Dian ◽

Zengyuan Li ◽

Yong Pang

Keyword(s):

Tree Species ◽

Hyperspectral Imagery ◽

Texture Features ◽

Forest Tree ◽

Species Classification ◽

Forest Tree Species ◽

Tree Species Classification

Download Full-text

FUSION OF LIDAR AND HYPERSPECTRAL DATA FOR SEMANTIC SEGMENTATION OF FOREST TREE SPECIES

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2020-487-2020 ◽

2020 ◽

Vol XLIII-B3-2020 ◽

pp. 487-494

Author(s):

E. Tusa ◽

J. M. Monnet ◽

J. B. Barré ◽

M. Dalla Mura ◽

J. Chanussot

Keyword(s):

Tree Species ◽

Semantic Segmentation ◽

Forest Tree ◽

Feature Reduction ◽

Lidar Data ◽

Topographic Effects ◽

Species Classification ◽

Forest Tree Species ◽

Tree Species Classification ◽

Feature Descriptors

Abstract. Hyperspectral images (HI) and Light Detection and Ranging (LiDAR) provide high resolution radiometric and geometric information for monitoring forests at individual tree crown (ITC) level. It has many important applications for sustainable forest management, biodiversity assessment and healthy ecosystem preservation. However, the integration of different remote sensing modalities is a challenging task for tree species classification due to different artifacts such as the lighting variability, the topographic effects and the atmospheric conditions of the data acquisition. The characterization of ITC can benefit from the extraction and selection of robust feature descriptors that solve these issues. This paper aims to investigate the integration of feature descriptors from HI and LiDAR by using the intra-set and inter-set feature importance for the semantic segmentation of forest tree species. A fusion methodology is proposed between high-density LiDAR data – (20 pulses m−2) and VNIR HI – (160 bands and 0.80 m spatial resolution) acquired on French temperate forests along an altitude gradient. The proposed scheme has three inputs: the field inventory information, the HI and the LiDAR data. Our approach can be described in nine stages: polygon projection, non-overlapping pixel selection, vegetation and shadow removal, LiDAR feature extraction, height mask, robust PCA (rPCA), feature reduction and classification. The overall accuracy of tree species classification at pixel-level was 68.9% by using random forest (RF) classifier. Our approach showed that 74.0% of trees were correctly assigned overall, by having conifer species such as Norway Spruce (Picea abies) with a producer’s accuracy of 97.4%.

Download Full-text

FOREST TREE SPECIES DISTRIBUTION MAPPING USING LANDSAT SATELLITE IMAGERY AND TOPOGRAPHIC VARIABLES WITH THE MAXIMUM ENTROPY METHOD IN MONGOLIA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xli-b8-593-2016 ◽

2016 ◽

Vol XLI-B8 ◽

pp. 593-596 ◽

Cited By ~ 1

Author(s):

Shou Hao Chiang ◽

Miguel Valdez ◽

Chi-Farn Chen

Keyword(s):

Maximum Entropy ◽

Satellite Imagery ◽

Tree Species ◽

Maximum Entropy Method ◽

Forest Tree ◽

Entropy Method ◽

Surface Reflectance ◽

Species Classification ◽

Forest Tree Species ◽

Tree Species Classification

Forest is a very important ecosystem and natural resource for living things. Based on forest inventories, government is able to make decisions to converse, improve and manage forests in a sustainable way. Field work for forestry investigation is difficult and time consuming, because it needs intensive physical labor and the costs are high, especially surveying in remote mountainous regions. A reliable forest inventory can give us a more accurate and timely information to develop new and efficient approaches of forest management. The remote sensing technology has been recently used for forest investigation at a large scale. To produce an informative forest inventory, forest attributes, including tree species are unavoidably required to be considered. <br><br> In this study the aim is to classify forest tree species in Erdenebulgan County, Huwsgul province in Mongolia, using Maximum Entropy method. The study area is covered by a dense forest which is almost 70% of total territorial extension of Erdenebulgan County and is located in a high mountain region in northern Mongolia. For this study, Landsat satellite imagery and a Digital Elevation Model (DEM) were acquired to perform tree species mapping. The forest tree species inventory map was collected from the Forest Division of the Mongolian Ministry of Nature and Environment as training data and also used as ground truth to perform the accuracy assessment of the tree species classification. Landsat images and DEM were processed for maximum entropy modeling, and this study applied the model with two experiments. The first one is to use Landsat surface reflectance for tree species classification; and the second experiment incorporates terrain variables in addition to the Landsat surface reflectance to perform the tree species classification. All experimental results were compared with the tree species inventory to assess the classification accuracy. Results show that the second one which uses Landsat surface reflectance coupled with terrain variables produced better result, with the higher overall accuracy and kappa coefficient than first experiment. The results indicate that the Maximum Entropy method is an applicable, and to classify tree species using satellite imagery data coupled with terrain information can improve the classification of tree species in the study area.

Download Full-text

FOREST TREE SPECIES DISTRIBUTION MAPPING USING LANDSAT SATELLITE IMAGERY AND TOPOGRAPHIC VARIABLES WITH THE MAXIMUM ENTROPY METHOD IN MONGOLIA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xli-b8-593-2016 ◽

2016 ◽

Vol XLI-B8 ◽

pp. 593-596 ◽

Cited By ~ 1

Author(s):

Shou Hao Chiang ◽

Miguel Valdez ◽

Chi-Farn Chen

Keyword(s):

Maximum Entropy ◽

Satellite Imagery ◽

Tree Species ◽

Maximum Entropy Method ◽

Forest Tree ◽

Entropy Method ◽

Surface Reflectance ◽

Species Classification ◽

Forest Tree Species ◽

Tree Species Classification

Download Full-text

USING SENTINEL 2 TIME SERIES FOR FOREST TREE SPECIES CLASSIFICATION. CASE STUDY: NE OF ROMANIA

19th SGEM International Multidisciplinary Scientific GeoConference EXPO Proceedings19th, Science and Technologies in Geology, Exploration And Mining ◽

10.5593/sgem2019v/1.4/s03.054 ◽

2019 ◽

Author(s):

Alexandra-Petronela Stoleriu

Keyword(s):

Time Series ◽

Tree Species ◽

Forest Tree ◽

Species Classification ◽

Forest Tree Species ◽

Tree Species Classification ◽

Sentinel 2

Download Full-text

How Spatial Resolution Affects Forest Phenology and Tree-Species Classification Based on Satellite and Up-Scaled Time-Series Images

Remote Sensing ◽

10.3390/rs13142716 ◽

2021 ◽

Vol 13 (14) ◽

pp. 2716

Author(s):

Kaijian Xu ◽

Zhaoying Zhang ◽

Wanwan Yu ◽

Ping Zhao ◽

Jibo Yue ◽

...

Keyword(s):

Remote Sensing ◽

Time Series ◽

Spatial Resolution ◽

Tree Species ◽

Deciduous Forest ◽

Forest Tree ◽

Image Resolution ◽

Species Classification ◽

Forest Tree Species ◽

Time Series Images

The distribution of forest tree species provides crucial data for regional forest management and ecological research. Although medium-high spatial resolution remote sensing images are widely used for dynamic monitoring of forest vegetation phenology and species identification, the use of multiresolution images for similar applications remains highly uncertain. Moreover, it is necessary to explore to what extent spectral variation is responsible for the discrepancies in the estimation of forest phenology and classification of various tree species when using up-scaled images. To clarify this situation, we studied the forest area in Harqin Banner in northeast China by using year-round multiple-resolution time-series images (at four spatial resolutions: 4, 10, 16, and 30 m) and eight phenological metrics of four deciduous forest tree species in 2018, to explore potential impacts of relevant results caused by various resolutions. We also investigated the effect of using up-scaled time-series images by comparing the corresponding results that use pixel-aggregation algorithms with the four spatial resolutions. The results indicate that both phenology and classification accuracy of the dominant forest tree species are markedly affected by the spatial resolution of time-series remote sensing data (p < 0.05): the spring phenology of four deciduous forest tree species first rises and then falls as the image resolution varies from 4 to 30 m; similarly, the accuracy of tree species classification increases as the image resolution varies from 4 to 10 m, and then decreases as the image resolution gradually falls to 30 m (p < 0.05). Therefore, there remains a profound discrepancy between the results obtained by up-scaled and actual remote sensing data at the given spatial resolutions (p < 0.05). The results also suggest that combining phenological metrics and time-series NDVI data can be applied to identify the regional dominant tree species across different spatial resolutions, which would help advance the use of multiscale time-series satellite data for forest resource management.

Download Full-text

An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images

Remote Sensing ◽

10.3390/rs12071128 ◽

2020 ◽

Vol 12 (7) ◽

pp. 1128 ◽

Cited By ~ 6

Author(s):

Kaili Cao ◽

Xiaoli Zhang

Keyword(s):

Deep Learning ◽

Tree Species ◽

Classification Accuracy ◽

Southern China ◽

Forest Tree ◽

Image Features ◽

Support Vector ◽

Learning Technology ◽

Species Classification ◽

Tree Species Classification

Tree species classification is important for the management and sustainable development of forest resources. Traditional object-oriented tree species classification methods, such as support vector machines, require manual feature selection and generally low accuracy, whereas deep learning technology can automatically extract image features to achieve end-to-end classification. Therefore, a tree classification method based on deep learning is proposed in this study. This method combines the semantic segmentation network U-Net and the feature extraction network ResNet into an improved Res-UNet network, where the convolutional layer of the U-Net network is represented by the residual unit of ResNet, and linear interpolation is used instead of deconvolution in each upsampling layer. At the output of the network, conditional random fields are used for post-processing. This network model is used to perform classification experiments on airborne orthophotos of Nanning Gaofeng Forest Farm in Guangxi, China. The results are then compared with those of U-Net and ResNet networks. The proposed method exhibits higher classification accuracy with an overall classification accuracy of 87%. Thus, the proposed model can effectively implement forest tree species classification and provide new opportunities for tree species classification in southern China.

Download Full-text

Classification of Typical Tree Species in Laser Point Cloud Based on Deep Learning

Remote Sensing ◽

10.3390/rs13234750 ◽

2021 ◽

Vol 13 (23) ◽

pp. 4750

Author(s):

Jianchang Chen ◽

Yiming Chen ◽

Zhengjun Liu

Keyword(s):

Feature Extraction ◽

Deep Learning ◽

Tree Species ◽

Classification Accuracy ◽

Point Cloud ◽

Laser Scanning ◽

Species Classification ◽

Tree Species Classification ◽

Network Mapping

We propose the Point Cloud Tree Species Classification Network (PCTSCN) to overcome challenges in classifying tree species from laser data with deep learning methods. The network is mainly composed of two parts: a sampling component in the early stage and a feature extraction component in the later stage. We used geometric sampling to extract regions with local features from the tree contours since these tend to be species-specific. Then we used an improved Farthest Point Sampling method to extract the features from a global perspective. We input the intensity of the tree point cloud as a dimensional feature and spatial information into the neural network and mapped it to higher dimensions for feature extraction. We used the data obtained by Terrestrial Laser Scanning (TLS) and Unmanned Aerial Vehicle Laser Scanning (UAVLS) to conduct tree species classification experiments of white birch and larch. The experimental results showed that in both the TLS and UAVLS datasets, the input tree point cloud density and the highest feature dimensionality of the mapping had an impact on the classification accuracy of the tree species. When the single tree sample obtained by TLS consisted of 1024 points and the highest dimension of the network mapping was 512, the classification accuracy of the trained model reached 96%. For the individual tree samples obtained by UAVLS, which consisted of 2048 points and had the highest dimension of the network mapping of 1024, the classification accuracy of the trained model reached 92%. TLS data tree species classification accuracy of PCTSCN was improved by 2–9% compared with other models using the same point density, amount of data and highest feature dimension. The classification accuracy of tree species obtained by UAVLS was up to 8% higher. We propose PCTSCN to provide a new strategy for the intelligent classification of forest tree species.

Download Full-text