Large-scale Building Height Estimation from Single VHR SAR image Using Fully Convolutional Network and GIS building footprints

Abstract. Nowadays, we are witnessing an increasing availability of large-scale airborne LiDAR (Light Detection and Ranging) data, that greatly improve our knowledge of urban areas and natural environment. In order to extract useful information from these massive point clouds, appropriate data processing is required, including point cloud classification. In this paper we present a deep learning method to efficiently perform the classification of large-scale LiDAR data, ensuring a good trade-off between speed and accuracy. The algorithm employs the projection of the point cloud into a two-dimensional image, where every pixel stores height, intensity, and echo information of the point falling in the pixel. The image is then segmented by a Fully Convolutional Network (FCN), assigning a label to each pixel and, consequently, to the corresponding point. In particular, the proposed approach is applied to process a dataset of 7700 km2 that covers the entire Friuli Venezia Giulia region (Italy), allowing to distinguish among five classes (ground, vegetation, roof, overground and power line), with an overall accuracy of 92.9%.

Download Full-text

Polarimetric SAR Image Classification Based on Edge-Aware Dual Branch Fully Convolutional Network

10.1109/igarss47720.2021.9554518 ◽

2021 ◽

Author(s):

Feng Gao ◽

Yanqiao Chen ◽

Xinghua Chai ◽

Bin Wu ◽

Cheng Peng ◽

...

Keyword(s):

Image Classification ◽

Sar Image ◽

Polarimetric Sar ◽

Convolutional Network ◽

Fully Convolutional Network

Download Full-text

Building height estimation in single SAR image using OSM building footprints

2017 Joint Urban Remote Sensing Event (JURSE) ◽

10.1109/jurse.2017.7924549 ◽

2017 ◽

Cited By ~ 2

Author(s):

Yao Sun ◽

Muhammad Shahzad ◽

Xiao Xiang Zhu

Keyword(s):

Sar Image ◽

Height Estimation ◽

Building Height

Download Full-text

A Modified Fully Convolutional Network for Crack Damage Identification Compared with Conventional Methods

Modelling and Simulation in Engineering ◽

10.1155/2021/5298882 ◽

2021 ◽

Vol 2021 ◽

pp. 1-14

Author(s):

Meng Meng ◽

Kun Zhu ◽

Keqin Chen ◽

Hang Qu

Keyword(s):

Large Scale ◽

Crack Detection ◽

Damage Identification ◽

Low Cost ◽

Convolutional Network ◽

Fully Convolutional Network ◽

Concrete Crack ◽

The Common ◽

Underwater Structures

Large-scale structural health monitoring and damage detection of concealed underwater structures are always the urgent and state-of-art problems to be solved in the field of civil engineering. With the development of artificial intelligence especially the combination of deep learning and computer vision, greater advantages have been brought to the concrete crack detection based on convolutional neural network (CNN) over the traditional methods. However, these machine learning (ML) methods still have some defects, such as it being inaccurate or not strong, having poor generalization ability, or the accuracy still needs to be improved, and the running speed is slow. In this article, a modified fully convolutional network (FCN) with more robustness and more effectiveness is proposed, which makes it convenient and low cost for long-term structural monitoring and inspection compared with other methods. Meanwhile, to improve the accuracy of recognition and prediction, innovations were conducted in this study as follows. Moreover, differed from the common simple deconvolution, it also includes a subpixel convolution layer, which can greatly reduce the sampling time. Then, the proposed method was verified its practicability with the overall recognition accuracy reaching up to 97.92% and 12% efficiency improvement.

Download Full-text

NPU RGB+D Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players

Applied Sciences ◽

10.3390/app11104426 ◽

2021 ◽

Vol 11 (10) ◽

pp. 4426

Author(s):

Chunyan Ma ◽

Ji Fan ◽

Jinghao Yao ◽

Tao Zhang

Keyword(s):

Action Recognition ◽

Large Scale ◽

Short Term Memory ◽

Evaluation Criteria ◽

Image Data ◽

Basketball Player ◽

Basketball Players ◽

Convolutional Network ◽

Atomic Actions ◽

New Feature

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

Download Full-text

Seismic Images Interpretation to Discover Salt Domes Using Deep Fully Convolutional Network

Journal of Physics Conference Series ◽

10.1088/1742-6596/1818/1/012006 ◽

2021 ◽

Vol 1818 (1) ◽

pp. 012006

Author(s):

Shms Aldeen S. Al-Duri ◽

Amel H. Abbas

Keyword(s):

Convolutional Network ◽

Fully Convolutional Network ◽

Salt Domes ◽

Seismic Images

Download Full-text

A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽

10.3390/cancers13092111 ◽

2021 ◽

Vol 13 (9) ◽

pp. 2111

Author(s):

Bo-Wei Zhao ◽

Zhu-Hong You ◽

Lun Hu ◽

Zhen-Hao Guo ◽

Lei Wang ◽

...

Keyword(s):

Drug Target ◽

Large Scale ◽

Computational Models ◽

Structural Information ◽

Characteristic Curve ◽

Representation Learning ◽

Graph Representation ◽

Convolutional Network ◽

Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

Download Full-text