AMDNet: A Modern UAV RGB Remote-Sensing Tree Species Image Segmentation Model Based on Dual-Attention Residual and Structure Re-Parameterization

Tree species classification is an important and challenging task in image recognition and the management of forest resources. Moreover, the task of tree species classification based on remote sensing images can significantly improve the efficiency of the tree species survey and save costs. In recent years, many large models have achieved high accuracy in the task of tree species classification in an airborne remote-sensing manner, but due to their fixed geometric structure, traditional convolutional neural networks are inherently limited to the local receptive field and can only provide segmental context information. The limitation of insufficient context information greatly affects the segmentation accuracy. In this paper, a dual-attention residual network (AMDNet) and a re-parameterized model approach are proposed to capture the global context information, fuse the weight, reduce the model volume, and maintain the computational efficiency. Firstly, we propose MobileNetV2 as the backbone network for feature extraction to further improve the feature identification by modeling semantic dependencies in the spatial dimension and channel dimension and adding the output of the two attention modules. Then, the attention perception features are generated by stacking the attention modules, and the in-depth residual attention network is trained using attention residual learning, through which more accurate segmentation results can be obtained. Secondly, we adopt the approach of structure re-parameterization, use a multi-branch topology for training, carry out weighted averaging on multiple trained models, and fuse multiple branch modules into a completely equivalent module in inference. The proposed approach results in a reduction in the number of parameters and an accelerated inference speed while also achieving improved classification accuracy. In addition, the model training strategy is optimized based on Transformer to enhance the accuracy of segmentation. The model was used to conduct classification experiments on aerial orthophotos of Hongya Forest Farm in Sichuan, China, and the MIOU of tree species recognition using the test equipment reached 93.8%. Compared with current models such as UNet, our model exhibits a better performance in terms of both speed and accuracy, in addition to its enhanced deployment capacity, and its speed advantage is more conducive to real-time segmentation, thereby representing a novel approach for the classification of tree species in remote sensing imagery with significant potential for practical applications.

[1]  Guijun Yang,et al.  Estimation of Leaf Nitrogen Content in Rice Using Vegetation Indices and Feature Variable Optimization with Information Fusion of Multiple-Sensor Images from UAV , 2023, Remote. Sens..

[2]  Guijun Yang,et al.  Estimating canopy-scale chlorophyll content in apple orchards using a 3D radiative transfer model and UAV multispectral imagery , 2022, Comput. Electron. Agric..

[3]  Guoqi Chai,et al.  ACE R-CNN: An Attention Complementary and Edge Detection-Based Instance Segmentation Algorithm for Individual Tree Species Identification Using UAV RGB Images and LiDAR Data , 2022, Remote. Sens..

[4]  Jian Zhang,et al.  Extraction of Olive Crown Based on UAV Visible Images and the U2-Net Deep Learning Model , 2022, Remote. Sens..

[5]  Yongshuo H. Fu,et al.  Machine Learning-Based Approaches for Predicting SPAD Values of Maize Using Multi-Spectral Images , 2022, Remote. Sens..

[6]  Huaipeng Liu Classification of urban tree species using multi-features derived from four-season RedEdge-MX data , 2022, Comput. Electron. Agric..

[7]  B. St-Onge,et al.  Effect of feature standardization on reducing the requirements of field samples for individual tree species classification using ALS data , 2022, ISPRS Journal of Photogrammetry and Remote Sensing.

[8]  Jiangjian Xie,et al.  Patch-U-Net: tree species classification method based on U-Net with class-balanced jigsaw resampling , 2022, International Journal of Remote Sensing.

[9]  Shaohui Mei,et al.  Hyperspectral Image Classification Using Group-Aware Hierarchical Transformer , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Heather Reese,et al.  Tree species classification using Sentinel-2 imagery and Bayesian inference , 2021, Int. J. Appl. Earth Obs. Geoinformation.

[11]  Sebastian Schmidtlein,et al.  Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[12]  Evandro Orfanó Figueiredo,et al.  Individual tree detection and species classification of Amazonian palms using UAV images and deep learning , 2020, Forest Ecology and Management.

[13]  Zhenhai Li,et al.  Extracting apple tree crown information from remote imagery using deep learning , 2020, Comput. Electron. Agric..

[14]  Kaili Cao,et al.  An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images , 2020, Remote. Sens..

[15]  Fabian Ewald Fassnacht,et al.  Tree species identification within an extensive forest area with diverse management regimes using airborne hyperspectral data , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[16]  Thor-Bjørn Ottosen,et al.  Tree cover mapping based on Sentinel-2 images demonstrate high thematic accuracy in Europe , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[17]  Michele Dalponte,et al.  Individual tree crown delineation and tree species classification with hyperspectral and LiDAR data , 2019, PeerJ.

[18]  Michael A. Lefsky,et al.  Review of studies on tree species classification from remotely sensed data , 2016 .

[19]  Michele Dalponte,et al.  Tree Species Classification in Boreal Forests With Hyperspectral Data , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Moses Azong Cho,et al.  Mapping tree species composition in South African savannas using an integrated airborne spectral and LiDAR system , 2012 .

[21]  Wu Honggan Development of Hyperspectral Remote Sensing Application in Forest Species Identification , 2009 .

[22]  Zhang Xiaoli Research Advances and Countermeasures of Remote Sensing Classification of Forest Vegetation , 2004 .

[23]  M. Fladeland,et al.  Remote sensing for biodiversity science and conservation , 2003 .