Extracting Urban Impervious Surface from WorldView-2 and Airborne LiDAR Data Using 3D Convolutional Neural Networks

Sun, Zhongchang; Zhao, Binru; Wu, Mengfan; Wang, Cuizhen

doi:10.1007/s12524-018-0917-5

Cited by 31 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deep learning scholars propose next results: overall kappa = 0.89 (Sun et al, 2018a), F 1 of roofs = 0.93 and F 1 of impervious surfaces = 0.90 (Yang et al, 2017), F 1 score of buildings = 0.95 (Sun et al, 2018b); that is close to the mean F 1 score for ISPRS data (WEB, b). Therefore, it can be concluded, that the proposed method has potential, which is comparable to deep learning methods, but it does not require training and the high-performance computing as deep learning solutions.…”

Section: Table 6 Classification Rules Of Buildingssupporting

confidence: 64%

“…And the understandable supervised solution, expected high precision, available open data, plenty of training courses and simple tuning model only increases the number of deep learning scholars. Therefore, nowadays, the deep learning is massively used for image classification including LiDAR data processing (Yang et al, 2017;Rizaldy et al, 2018;Sun et al, 2018aSun et al, , 2018b. The deep learning is based on the application of the artificial neural networks and it is intuitive to use 2D projection of LiDAR data as input that is actually applied in practise.…”

Section: Table 6 Classification Rules Of Buildingsmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Man-Made Constructions Using LiDAR Data and Decision Trees

Kodors¹

2019

BJMC

View full text Add to dashboard Cite

Real estate monitoring is very important aspect of country economics, but old manual methods of land survey are time and resources consuming processes as geodata actualization tasks. Actual, precise, multidimensional and detailed information is the main instrument of geospatial intelligence to understand current economic situation and to make effective decision. Actualization of geoinformation using remote sensing is the modern approach of the computer age to complete Earth observation and human environment monitoring. This article describes multi-stage classification model, which detects man-made constructions in LiDAR point cloud. Proposed classification model applies decision tree and geometrical features of shape to remove noises. The goal of study is to experimentally compare decision trees with crisp and fuzzy logic (ID3 algorithms) to select the more suitable algorithm for noise reduction task. Algorithms are compared using total accuracy and Cohen's Kappa coefficient.

show abstract

Section: Table 6 Classification Rules Of Buildingssupporting

confidence: 64%

Section: Table 6 Classification Rules Of Buildingsmentioning

confidence: 99%

Detection of Man-Made Constructions Using LiDAR Data and Decision Trees

Kodors¹

2019

BJMC

View full text Add to dashboard Cite

show abstract

“…In their review, Ma et al [26] showed that nearly 200 publications using deep convolutional neural networks (CNNs) have been published in the field of remote sensing by early 2019 of which most focused on land use land cover (LULC) classification [28], urban feature extraction [29][30][31], and crop detection [32,33]. Deep learning approaches often require a large amount of training data, and there are benchmark datasets publicly available for training and testing of deep learning approaches in the abovementioned remote sensing fields.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images

Sun

Huang

et al. 2019

Forests

View full text Add to dashboard Cite

The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon–Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (R2Margalef = 0.4562, root-mean-square error RMSEMargalef = 0.5629; R2Shannon–Wiener = 0.7948, RMSEShannon–Wiener = 0.7202; R2Simpson = 0.7907, RMSESimpson = 0.1038; and R2Pielou = 0.5875, RMSEPielou = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.

show abstract

“…Nowadays, the popular solution for semantic segmentation is deep learning. For example, deep learning scholars propose next results for building detection using airborne LiDAR data: overall kappa -0.89 [8] and F1 score 0.93 [9] and 0.95 [10]. So, the accuracy of graph-cut method, which provided kappa 0.888 and F1 score 0.933 (recalculating confusion matrix), is comparable with deep learning solutions.…”

Section: (R) the Number Of Classified Buildings In Tables Ii-v Is Different Comparing With Table I Because Tablementioning

confidence: 99%

Comparison of Algorithms for Construction Detection Using Airborne Laser Scanning and NDSM Classification

Kodors¹

2019

ETR

View full text Add to dashboard Cite

Traditional approach to classify the point cloud of airborne laser scanning is based on the processing of a normalized digital surface model (nDSM), when ground facilities are detected and classified. The main feature to detect a ground facility is height difference between adjacent points. The simplest method to extract a ground facility is region-growing algorithm, which applies threshold to identify the connection between two points. Region growing algorithm is working with the constant value of height difference. Therefore, it is not applicable due to diverse conditions of earth surface, when height difference must be defined for each region separately. As result, researchers propose hierarchical, statistical and cluster methods to solve this problem. The study goal is to compare four algorithms to generate nDSM: region growing, progressive morphological filter, adaptive TIN surfaces and graph-cut. The experiment is divided into two stages: 1) to calculate the number of detected and lost buildings in nDSM; 2) to measure the classification accuracy of extracted shapes. The experiment results have showed that progressive morphological filter and graph-cut provides the minimal loss of buildings (only 1%). The most effective algorithm for ground facility detection is the graph-cut (total accuracy 0.95, Cohen’s Kappa 0.89, F1 score 0.93).

show abstract

Extracting Urban Impervious Surface from WorldView-2 and Airborne LiDAR Data Using 3D Convolutional Neural Networks

Cited by 31 publications

References 37 publications

Detection of Man-Made Constructions Using LiDAR Data and Decision Trees

Detection of Man-Made Constructions Using LiDAR Data and Decision Trees

Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images

Comparison of Algorithms for Construction Detection Using Airborne Laser Scanning and NDSM Classification

Contact Info

Product

Resources

About