Figure 4 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Combining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-object types. To resolve these issues, this paper c...
Context in source publication
Context 1
... [41] is a pixel-wise image semantic segmentation algorithm whose structure consists of an encoder and a decoder (Figure 4). The encoder uses the first 13 layers of the VGG-16 network and performs five iterations of double downsampling, while the decoder performs five iterations of double upsampling, showing a symmetric relationship between the two. ...
Similar publications
Many bacterial and fungal pathogens are known to affect lotus, which limits both flower quality and yield production. Treatments such as pesticides can reduce pathogens but can result in resistance. This study was conducted to identify the most common fungal, and bacterial pathogens associated with leaf spot diseases of white lotus (Nelumbo nucifer...
Citations
... Ayushi et al. (2024) considered elevation data the third most important input variable during their model building. Li et al. (2022) also highlighted the application of DSM, but they found texture indices to be efficient in reaching higher OAs, while in our case, texture indices did not ensure better OAs. In our study, less accurate results were obtained by involving only texture indices, followed by spectral indices, texture indices+bands, and texture indices+spectral indices. ...
... We can conclude that using the texture index as a standalone input may not yield efficient classification results. However, as demonstrated by Li et al. (2022), incorporating it in combination with other significant variables can enhance the classification performance. ...
Aquatic vegetation species at the genus level in an oxbow lake were identified in Hungary based on a multispectral Uncrewed Aerial System (UAS) survey within an elongated oxbow lake area of the Tisza River under continental climate. Seven and 13 classes were discriminated using three different classification methods (Support Vector Machine [SVM], Random Forest [RF], and Multivariate Adaptive Regression Splines [MARS]) using different input data in ten combinations: original spectral bands, spectral indices, Digital Surface Model (DSM), and Haralick texture indices. We achieved a high (97.1%) overall accuracies (OAs) by applying the SVM classifier, but the RF performed only <1% worse, as it was represented in the first places of the classification rank before the MARS. The highest classification accuracies (>84% OA) were obtained using the most important variables derived by the Recursive Feature Elimination (RFE) method. The best classification required DSM as an input variable. The poorest classification performance belonged to the model that used only texture indices or spectral indices. On the class level, Stratoites aloides exhibit the lowest degree of separability compared to the other classes. Accordingly, we recommend using supplementary input data for the classifications besides the original spectral bands, for example, DSM, spectral, and texture indices, as these variables significantly improve the classification accuracies in the proper combinations of the input variables.
... The mIoU decreased by 0.05 (6%) to 0.82 compared to the average mIoU of 0.87 when classifying these components separately. This finding coincides with a recent study by Li et al. [105] where binary CNN-based classifiers exceeded the multi-class situation in wetland vegetation classification with an mIoU increase by 22%. However, the processing time would significantly increase if each class is trained individually. ...
Predictive accuracy in wildland fire behavior is contingent on a thorough understanding of the 3D fuel distribution. However, this task is complicated by the complex nature of fuel forms and the associated constraints in sampling and quantification. In this study, twelve terrestrial laser scanning (TLS) plot scans were sampled within the mountain pine beetle-impacted forests of Jasper National Park, Canada. The TLS point clouds were delineated into eight classes, namely individual-tree stems, branches, foliage, downed woody logs, sapling stems, below-canopy branches, grass layer, and ground-surface points using a transformer-based deep learning classifier. The fine-scale 3D architecture of trees and branches was reconstructed using a quantitative structural model (QSM) based on the multi-class components from the previous step, with volume attributes extracted and analyzed at the branch, tree, and plot levels. The classification accuracy was evaluated by partially validating the results through field measurements of tree height, diameter-at-breast height (DBH), and live crown base height (LCBH). The extraction and reconstruction of 3D wood components enable advanced fuel characterization with high heterogeneity. The existence of ladder trees was found to increase the vertical overlap of volumes between tree branches and below-canopy branches from 8.4% to 10.8%.
... In total, 1.99 billion points with a point density of 29 points/m 2 were captured in the 68 km 2 area of interest. In reference [77], the authors evaluated and classified the vegetation of karst wetlands in Huixian Karst National Wetland Park, Guilin, South China, using a DJI Phantom 4 Pro UAV and an FC6310S camera. They collected data during 12 flights, which were processed using Pix4D Mapper software to generate orotophotomosaics and DSM. ...
... Terrain mapping and modeling [59,64,[69][70][71][72][73] Underground and surface karst areas [6,[74][75][76][77][78][79] Mining [80][81][82][83][84][85][86] Real estate cadastre [87][88][89][90][91][92][93] Industry [94][95][96][97][98][99][100] Architecture [101][102][103][104][105][106][107] ...
... Canon EOS digital camera [63,87,103,106,111,126,156] Canon PowerShot digital camera [101,120,146,147,182] Sony Alpha digital camera [125,132,135,150,165,177] Sony EXMOR digital camera [68,93,168,179] Sony ILCE digital camera [81,87,88] DJI Phantom 4 integrated camera (12,4 MP) digital camera [58,82,103,120,135,138,157] DJI Phantom 4 Pro integrated camera (20 MP) digital camera [59,61,69,71,77,79,89,107,108,115,127,129,142,161,170,198] DJI Zenmuse digital camera [62,88,110,119,148,176] Nikon digital camera [70,91,101,178,199] GoPro digital camera [102,105,131,186,188] Parrot Sequoia multispectral camera [59,60,64,69,190] Panasonic digital camera [119,154] Velodyne lidar [64,67,96,107,116] Leica lidar [76,103,158] Riegl VUX lidar [65,96,116] Ibeo LUX lidar [63,66] Odroid XU4 lidar [109] LiteMapper lidar [147] ...
Using Unmanned Aerial Vehicles (UAVs) combined with various sensors brings the benefits associated with fast, automatic, and contactless spatial data collection with high resolution and accuracy. The most frequent application is the possibility of effectively creating spatial models based on photogrammetric and lidar data. This review analyzes the current possibilities of UAVs. It provides an overview of the current state of the art and research on selected parameters regarding their history and development, classification, regulation, and application in surveying with creating spatial models. Classification and regulation are based on national sources. The importance and usability of this review are also carried out by analyzing the UAV application with selected photogrammetric and lidar sensors. The study explores and discusses results achieved by many authors in recent years, synthesizing essential facts. By analyzing the network of co-occurring High-Frequency Words, in addition, we visualized the importance of the primary keyword UAV in the context of other keywords in the literary sources processed.
... However, this scheme can result in the loss of detailed information in the fusion map, as shown in the results. A strategy was tried to retain the individual classification results with a high probability of being correct in the final fusion [58]. The strategy was to combine the class-wise and class allocation of uncertainty with the product rule rather than the conjunctive combination rule in Equation (7), which can be rewritten as ( ) ∝ ( ) × ω ( ) ( ) × ′ ( ) × ω ( ) ( ) × ( ) . ...
High-spatial-resolution (HSR) images and high-temporal-resolution (HTR) images have their unique advantages and can be replenished by each other effectively. For land cover classification, a series of spatiotemporal fusion algorithms were developed to acquire a high-resolution land cover map. The fusion processes focused on the single level, especially the pixel level, could ignore the different phenology changes and land cover changes. Based on Bayesian decision theory, this paper proposes a novel decision-level fusion for multisensor data to classify the land cover. The proposed Bayesian fusion (PBF) combines the classification accuracy of results and the class allocation uncertainty of classifiers in the estimation of conditional probability, which consider the detailed spectral information as well as the various phenology information. To deal with the scale inconsistency problem at the decision level, an object layer and an area factor are employed for unifying the spatial resolution of distinct images, which would be applied for evaluating the classification uncertainty related to the conditional probability inference. The approach was verified on two cases to obtain the HSR land cover maps, in comparison with the implementation of two single-source classification methods and the benchmark fusion methods. Analyses and comparisons of the different classification results showed that PBF outperformed the best performance. The overall accuracy of PBF for two cases rose by an average of 27.8% compared with two single-source classifications, and an average of 13.6% compared with two fusion classifications. This analysis indicated the validity of the proposed method for a large area of complex surfaces, demonstrating the high potential for land cover classification.
