We studied the use of self-attention mechanism networks (SAN) and convolutional neural networks (CNNs) for forest tree species classification using unmanned aerial vehicle (UAV) remote sensing imagery in Dongtai Forest Farm, Jiangsu Province, China. We trained and validated representative CNN models, such as ResNet and ConvNeXt, as well as the SAN model, which incorporates Transformer models such as Swin Transformer and Vision Transformer (ViT). Our goal was to compare and evaluate the performance and accuracy of these networks when used in parallel. Due to various factors, such as noise, motion blur, and atmospheric scattering, the quality of low-altitude aerial images may be compromised, resulting in indistinct tree crown edges and deficient texture. To address these issues, we adopted Real-ESRGAN technology for image super-resolution reconstruction. Our results showed that the image dataset after reconstruction improved classification accuracy for both the CNN and Transformer models. The final classification accuracies, validated by ResNet, ConvNeXt, ViT, and Swin Transformer, were 96.71%, 98.70%, 97.88%, and 98.59%, respectively, with corresponding improvements of 1.39%, 1.53%, 0.47%, and 1.18%. Our study highlights the potential benefits of Transformer and CNN for forest tree species classification and the importance of addressing the image quality degradation issues in low-altitude aerial images.
More accurate tree models, such as branch skeleton, are needed to acquire forest inventory data. Currently available algorithms for constructing a branch skeleton from a LiDAR point cloud have low accuracy with problems such as irrational connection near trunk bifurcation, excessive central deviation and topological errors. Using the C++ and PCL library, a novel algorithm of the incomplete simulation of tree transmitting water and nutrients (ISTTWN), based on geometric characteristics for tree branch skeleton extraction, was developed in this research. The algorithm is an incomplete simulation of tree transmitting water and nutrients. Improvements were made to improve the time and memory consumption. The result show that the ISTTWN algorithm without any improvements is quite time consuming but has consecutive output. After improvement with iteration, the process is faster and has more detailed output. Breakpoint connection is added to recover continuity. The ISTTWN algorithm with improvements can produce a more accurate skeleton and cost less time than a previous algorithm. The superiority and effectiveness of the method are demonstrated, which provides a reference for the subsequent study of tree modeling and a prospect of application in other fields, such as virtual reality, computer games and movie scenes.
The ISTTWN algorithm overcame the defect of separating the production process of skeleton points and skeleton lines in tree branch point cloud skeleton extraction and improved the accuracy of the extracted initial skeletons, but the skeletons need further optimization. In the existing skeleton optimization, it is difficult to see the stump adjustment, and most of the bifurcation optimization and skeleton smoothness adopt fitting. Based on the characteristics of the initial skeletons extracted by the ISTTWN algorithm, this research optimizes the skeleton from four aspects. An algorithm for the stump adjustment for reconstructing the stump based on the layer and hierarchical relationship and an algorithm for the bifurcation optimization based on the local branch point cloud and cosine correlation are proposed, and an existing pruning method and a skeleton smoothing method are used. The results show that the skeleton optimization method proposed or used in this research has a high computational efficiency in general and can ultimately retain the necessary skeleton lines. In a visual analysis, the optimized skeleton is obviously much more natural and more in line with the actual topology of trees. In the quantitative analysis, the completeness, accuracy and effectiveness reached 97.82%, 95.72% and 89.47%, respectively. In this study, in addition to the existing tree parameters extracted by the skeleton or generalized cylinder model, the generated skeleton is used to extract the branch attributes. The R2 of the deflection angle of the branch tip, distance from branch tip and branch length are about 0.897, 0.986 and 0.988, respectively, which illustrates that their models are very good. This research can further expand the application of the skeleton.
This paper focuses on the estimation of green land variation with similarity theory by using two temporal spatial data in Shenzhen. The location, shape and areas of green land units have been used as the similarity elements. Thus the similarity coefficients can be defined. The ratio of overlapping number of green patches to the intersecting number of green patches indicates the location variation of green land. The ratio of minimum to maximum shape index of green land indicates the shape variation of green land. With the same method, the areas variation coefficient has also been obtained. Combined with the analytic hierarchy process, the weights of three similarity elements coefficients can be decided. By comparison with the distinguished threshold the estimation of different green land variation has been made. The result shows that the estimation of green land variation based on similarity theory is feasible. The research of this paper has also provided effective method for the further assessment of green land development in Shenzhen special economic zone.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.