This page has only limited features, please log in for full access.

Prof. Jonathan Li
Geospatial Sensing and Data Intelligence Lab, Faculty of Environment, University of Waterloo, 200 University Avenue West, Waterloo, Ontario N2L 3G1, Canada

Basic Info


Research Keywords & Expertise

0 Deep Learning
0 3D vision
0 LiDAR Remote Sensing
0 point cloud understanding
0 HD maps for smart cities and autonomous vehicles

Fingerprints

Deep Learning
HD maps for smart cities and autonomous vehicles
3D vision

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 31 August 2021 in Remote Sensing
Reads 0
Downloads 0

This study presents a novel workflow for automated Digital Terrain Model (DTM) extraction from Airborne LiDAR point clouds based on a convolutional neural network (CNN), considering a transfer learning approach. The workflow consists of three parts: feature image generation, transfer learning using ResNet, and interpolation. First, each point is transformed into a featured image based on its elevation differences with neighboring points. Then, the feature images are classified into ground and non-ground using ImageNet pretrained ResNet models. The ground points are extracted by remapping each feature image to its corresponding points. Last, the extracted ground points are interpolated to generate a continuous elevation surface. We compared the proposed workflow with two traditional filters, namely the Progressive Morphological Filter (PMF) and the Progressive Triangulated Irregular Network Densification (PTD). Our results show that the proposed workflow establishes an advantageous DTM extraction accuracy with yields of only 0.52%, 4.84%, and 2.43% for Type I, Type II, and the total error, respectively. In comparison, Type I, Type II, and the total error for PMF are 7.82%, 11.60%, and 9.48% and for PTD 1.55%, 5.37%, and 3.22%, respectively. The root means square error (RMSE) for the 1 m resolution interpolated DTM is only 7.3 cm. Moreover, we conducted a qualitative analysis to investigate the reliability and limitations of the proposed workflow.

ACS Style

Huxiong Li; Weiya Ye; Jun Liu; Weikai Tan; Saied Pirasteh; Sarah Narges Fatholahi; Jonathan Li. High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning. Remote Sensing 2021, 13, 3448 .

AMA Style

Huxiong Li, Weiya Ye, Jun Liu, Weikai Tan, Saied Pirasteh, Sarah Narges Fatholahi, Jonathan Li. High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning. Remote Sensing. 2021; 13 (17):3448.

Chicago/Turabian Style

Huxiong Li; Weiya Ye; Jun Liu; Weikai Tan; Saied Pirasteh; Sarah Narges Fatholahi; Jonathan Li. 2021. "High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning." Remote Sensing 13, no. 17: 3448.

Journal article
Published: 30 August 2021 in Remote Sensing
Reads 0
Downloads 0

An earthquake-induced landslide (EQIL) is a rapidly changing process occurring at the Earth’s surface that is strongly controlled by the earthquake in question and predisposing conditions. Predicting locations prone to EQILs on a large scale is significant for managing rescue operations and disaster mitigation. We propose a deep learning framework while considering the source area feature of EQIL to model the complex relationship and enhance spatial prediction accuracy. Initially, we used high-resolution remote sensing images and a digital elevation model (DEM) to extract the source area of an EQIL. Then, 14 controlling factors were input to a stacked autoencoder (SAE) to search for robust features by sparse optimization, and the classifier took advantage of high-level abstract features to identify the EQIL spatially. Finally, the EQIL inventory collected from the Wenchuan earthquake was used to validate the proposed model. The results show that the proposed method significantly outperformed conventional methods, achieving an overall accuracy (OA) of 91.88%, while logistic regression (LR), support vector machine (SVM), and random forest (RF) achieved 80.75%, 82.22%, and 84.16%, respectively. Meanwhile, this study reveals that shallow machine learning models only take advantage of significant factors for EQIL prediction, but deep learning models can extract more effective information related to EQIL distribution from low-value density data, which is why its prediction accuracy is growing with increasing input factors. There is hope that new knowledge of EQILs can be represented by high-level abstract features extracted by hidden layers of the deep learning model, which are typically acquired by statistical methods.

ACS Style

Yao Li; Peng Cui; Chengming Ye; JosĂŠ Marcato Junior; Zhengtao Zhang; Jian Guo; Jonathan Li. Accurate Prediction of Earthquake-Induced Landslides Based on Deep Learning Considering Landslide Source Area. Remote Sensing 2021, 13, 3436 .

AMA Style

Yao Li, Peng Cui, Chengming Ye, JosĂŠ Marcato Junior, Zhengtao Zhang, Jian Guo, Jonathan Li. Accurate Prediction of Earthquake-Induced Landslides Based on Deep Learning Considering Landslide Source Area. Remote Sensing. 2021; 13 (17):3436.

Chicago/Turabian Style

Yao Li; Peng Cui; Chengming Ye; JosĂŠ Marcato Junior; Zhengtao Zhang; Jian Guo; Jonathan Li. 2021. "Accurate Prediction of Earthquake-Induced Landslides Based on Deep Learning Considering Landslide Source Area." Remote Sensing 13, no. 17: 3436.

Journal article
Published: 30 August 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Land cover classification provides updated information regarding the Earth's resources, which is vital for agricultural investigation, urban management, and disaster monitoring. Current advances in sensor technology on satellite and aerial remote sensing (RS) devices have improved the spatial-spectral, radiometric, and temporal resolutions of images over time. These improvements offer invaluable chances of understanding land cover information. However, land cover classification from RS images is an intricate task because of the high intra-class disparities, low inter-class similarities, and image variation types. We propose a cascaded residual dilated network (CRD-Net) for land cover classification using very high spatial resolution (VHSR) images to address these challenges. The proposed hybrid network follows the encoder-decoder concept with a spatial attention block to guide the network on learnable discriminate features coupled with an intermediary loss to enhance the training process. Moreover, a cascaded residual dilated module increases the network's receptive field to enrich multi-contextual features further, thus boosting the resultant feature descriptor. Extensive experimental results demonstrate that the proposed CRD-Net outperformed state-of-the-art methods, achieving an overall accuracy (OA) of 90.73% and 90.51% on the ISPRS Potsdam land cover dataset and ISPRS Vaihingen dataset, respectively.

ACS Style

Naftaly Wambugu; Yiping Chen; Zhenlong Xiao; Mingqiang Wei; Saifullahi Aminu Bello; JosĂŠ Marcato Junior; Jonathan Li. A hybrid deep convolutional neural network for accurate land cover classification. International Journal of Applied Earth Observation and Geoinformation 2021, 103, 102515 .

AMA Style

Naftaly Wambugu, Yiping Chen, Zhenlong Xiao, Mingqiang Wei, Saifullahi Aminu Bello, JosĂŠ Marcato Junior, Jonathan Li. A hybrid deep convolutional neural network for accurate land cover classification. International Journal of Applied Earth Observation and Geoinformation. 2021; 103 ():102515.

Chicago/Turabian Style

Naftaly Wambugu; Yiping Chen; Zhenlong Xiao; Mingqiang Wei; Saifullahi Aminu Bello; JosĂŠ Marcato Junior; Jonathan Li. 2021. "A hybrid deep convolutional neural network for accurate land cover classification." International Journal of Applied Earth Observation and Geoinformation 103, no. : 102515.

Journal article
Published: 19 August 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

A catastrophic rock avalanche from a tableland escarpment occurred at the Pusa village, Guizhou Province, southwest (SW) China, causing 35 fatalities and huge economic losses. The steep slope lies in the Longtan Formation coal-bearing shale of Permian, which is widely distributed in SW China. It was overlaid by brittle superstrata in Triassic and followed by gently anticline tectonic movement in Cenozoic, thus forming large-scale tableland escarpments with an “upper brittle, lower ductile” structure. Affected by underground coal mining activity at the base, this escarpment has become unstable and prone to failure. In order to further clarify the geological conditions and other influence factors for the Pusa landslide, we propose a newly improved multiple Differential Interferometric Synthetic Aperture Radar (DInSAR), named average-DInSAR, to detect the displacements on escarpments in a broad region. Extensive experimental results show that there existed obvious pre-failure displacements on the swarming escarpments, evidencing their unstable state, which were verified by field inspection. The spatiotemporal correlation analysis suggests that this abnormal deformation is probably induced by underground coal mining in the vicinity. Further confirming that the special geological conditions and nearby coal mining activity were responsible for the 2017 Pusa rock avalanche. Our study also demonstrates that the average-DInSAR method is simple and effective, which can overcome low coherence and noise of DInSAR, especially for shorter X- or C-band SAR data. Application of proposed method would permit to detect displacement before slope failure with higher re-visiting frequency, thus helping define early warning strategies for landslides in area with similar geological conditions.

ACS Style

Xin Yao; Yiping Chen; Donglie Liu; Zhenkai Zhou; Veraldo Liesenberg; JosĂŠ Marcato Junior; Jonathan Li. Average-DInSAR method for unstable escarpments detection induced by underground coal mining. International Journal of Applied Earth Observation and Geoinformation 2021, 103, 102489 .

AMA Style

Xin Yao, Yiping Chen, Donglie Liu, Zhenkai Zhou, Veraldo Liesenberg, JosĂŠ Marcato Junior, Jonathan Li. Average-DInSAR method for unstable escarpments detection induced by underground coal mining. International Journal of Applied Earth Observation and Geoinformation. 2021; 103 ():102489.

Chicago/Turabian Style

Xin Yao; Yiping Chen; Donglie Liu; Zhenkai Zhou; Veraldo Liesenberg; JosĂŠ Marcato Junior; Jonathan Li. 2021. "Average-DInSAR method for unstable escarpments detection induced by underground coal mining." International Journal of Applied Earth Observation and Geoinformation 103, no. : 102489.

Journal article
Published: 06 August 2021 in IEEE Transactions on Intelligent Transportation Systems
Reads 0
Downloads 0

Mobile Laser Scanning (MLS) system can provide high-density and accurate 3D point clouds that enable rapid pavement crack detection for road maintenance tasks. Supervised learning-based algorithms have been proved pretty effective for handling such a large amount of inhomogeneous and unstructured point clouds. However, these algorithms often rely on a lot of annotated data, which is labor-intensive and time-consuming. This paper presents a semi-supervised point-level approach to overcome this challenge. We propose a graph-widen module to construct a reasonable graph structure for point clouds, increasing the detection performance of graph convolutional networks (GCN). The constructed graph characterizes the local features from a small amount of annotated data, avoiding information loss and dramatically reduces the dependence on annotated data. The MLS point clouds acquired by a commercial RIEGL VMX-450 system are used in this study. The experimental results demonstrate that our method outperforms the state-of-the-art point-level methods in terms of recall, F1 score, and efficiency while achieving comparable accuracy.

ACS Style

Huifang Feng; Wen Li; Zhipeng Luo; Yiping Chen; Sarah Narges Fatholahi; Ming Cheng; Cheng Wang; Jose Marcato Junior; Jonathan Li. GCN-Based Pavement Crack Detection Using Mobile LiDAR Point Clouds. IEEE Transactions on Intelligent Transportation Systems 2021, PP, 1 -10.

AMA Style

Huifang Feng, Wen Li, Zhipeng Luo, Yiping Chen, Sarah Narges Fatholahi, Ming Cheng, Cheng Wang, Jose Marcato Junior, Jonathan Li. GCN-Based Pavement Crack Detection Using Mobile LiDAR Point Clouds. IEEE Transactions on Intelligent Transportation Systems. 2021; PP (99):1-10.

Chicago/Turabian Style

Huifang Feng; Wen Li; Zhipeng Luo; Yiping Chen; Sarah Narges Fatholahi; Ming Cheng; Cheng Wang; Jose Marcato Junior; Jonathan Li. 2021. "GCN-Based Pavement Crack Detection Using Mobile LiDAR Point Clouds." IEEE Transactions on Intelligent Transportation Systems PP, no. 99: 1-10.

Review
Published: 27 July 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Deep Neural Networks (DNNs) learn representation from data with an impressive capability, and brought important breakthroughs for processing images, time-series, natural language, audio, video, and many others. In the remote sensing field, surveys and literature revisions specifically involving DNNs algorithms’ applications have been conducted in an attempt to summarize the amount of information produced in its subfields. Recently, Unmanned Aerial Vehicle (UAV)-based applications have dominated aerial sensing research. However, a literature revision that combines both “deep learning” and “UAV remote sensing” thematics has not yet been conducted. The motivation for our work was to present a comprehensive review of the fundamentals of Deep Learning (DL) applied in UAV-based imagery. We focused mainly on describing the classification and regression techniques used in recent applications with UAV-acquired data. For that, a total of 232 papers published in international scientific journal databases was examined. We gathered the published materials and evaluated their characteristics regarding the application, sensor, and technique used. We discuss how DL presents promising results and has the potential for processing tasks associated with UAV-based image data. Lastly, we project future perspectives, commentating on prominent DL paths to be explored in the UAV remote sensing field. This revision consisting of an approach to introduce, commentate, and summarize the state-of-the-art in UAV-based image applications with DNNs algorithms in diverse subfields of remote sensing, grouping it in the environmental, urban, and agricultural contexts.

ACS Style

Lucas Prado Osco; JosÊ Marcato Junior; Ana Paula Marques Ramos; Lúcio AndrÊ De Castro Jorge; Sarah Narges Fatholahi; Jonathan De Andrade Silva; Edson Takashi Matsubara; Hemerson Pistori; Wesley Nunes Gonçalves; Jonathan Li. A review on deep learning in UAV remote sensing. International Journal of Applied Earth Observation and Geoinformation 2021, 102, 102456 .

AMA Style

Lucas Prado Osco, JosÊ Marcato Junior, Ana Paula Marques Ramos, Lúcio AndrÊ De Castro Jorge, Sarah Narges Fatholahi, Jonathan De Andrade Silva, Edson Takashi Matsubara, Hemerson Pistori, Wesley Nunes Gonçalves, Jonathan Li. A review on deep learning in UAV remote sensing. International Journal of Applied Earth Observation and Geoinformation. 2021; 102 ():102456.

Chicago/Turabian Style

Lucas Prado Osco; JosÊ Marcato Junior; Ana Paula Marques Ramos; Lúcio AndrÊ De Castro Jorge; Sarah Narges Fatholahi; Jonathan De Andrade Silva; Edson Takashi Matsubara; Hemerson Pistori; Wesley Nunes Gonçalves; Jonathan Li. 2021. "A review on deep learning in UAV remote sensing." International Journal of Applied Earth Observation and Geoinformation 102, no. : 102456.

Journal article
Published: 26 July 2021 in Remote Sensing
Reads 0
Downloads 0

Hyperspectral remote sensing can obtain both spatial and spectral information of ground objects. It is an important prerequisite for a hyperspectral remote sensing application to make good use of spectral and image features. Therefore, we improved the Convolutional Neural Network (CNN) model by extracting interior-edge-adjacency features of building roof and proposed a new CNN model with a flexible structure: Building Roof Identification CNN (BRI-CNN). Our experimental results demonstrated that the BRI-CNN can not only extract interior-edge-adjacency features of building roof, but also change the weight of these different features during the training process, according to selected samples. Our approach was tested using the Indian Pines (IP) data set and our comparative study indicates that the BRI-CNN model achieves at least 0.2% higher overall accuracy than that of the capsule network model, and more than 2% than that of CNN models.

ACS Style

Chengming Ye; Hongfu Li; Chunming Li; Xin Liu; Yao Li; Jonathan Li; Wesley Gonçalves; JosÊ Junior. A Building Roof Identification CNN Based on Interior-Edge-Adjacency Features Using Hyperspectral Imagery. Remote Sensing 2021, 13, 2927 .

AMA Style

Chengming Ye, Hongfu Li, Chunming Li, Xin Liu, Yao Li, Jonathan Li, Wesley Gonçalves, JosÊ Junior. A Building Roof Identification CNN Based on Interior-Edge-Adjacency Features Using Hyperspectral Imagery. Remote Sensing. 2021; 13 (15):2927.

Chicago/Turabian Style

Chengming Ye; Hongfu Li; Chunming Li; Xin Liu; Yao Li; Jonathan Li; Wesley Gonçalves; JosÊ Junior. 2021. "A Building Roof Identification CNN Based on Interior-Edge-Adjacency Features Using Hyperspectral Imagery." Remote Sensing 13, no. 15: 2927.

Journal article
Published: 26 July 2021 in Canadian Journal of Remote Sensing
Reads 0
Downloads 0

Estimating terrestrial water storage (TWS) with high spatial resolution is crucial for hydrological and water resource management. Comparing to traditional in-situ data measurement, observation from space borne sensor such as Gravity Recovery and Climate Experiment (GRACE) satellites is quite effective to obtain a large-scale TWS data. However, the coarse resolution of the GRACE data restricts its application at a local scale. This paper presents three novel convolutional neural network (CNN) based approaches including the Super-Resolution CNN (SRCNN), the Very Deep Super-Resolution (VDSR), and the Residual Channel Attention Networks (RCAN) to spatial downscaling of the monthly GRACE TWS products using the outputs of the Ecological Assimilation of Land and Climate Observations (EALCO) model over Canada. We also compare the performance of CNN-based methods with the empirical linear regression-based downscaling method. All comparison results were evaluated by root mean square error (RMSE) between the reconstructed GRACE TWS and the original one. RMSEs over the matched pixels are 22.3, 14.4, 18.4 and 71.6 mm of SRCNN, VDSR, RCAN and linear regression-based method respectively. Obviously, VDSR shows the best accuracy among all methods. The result shows all CNN-based super resolution methods preform much better than traditional method in spatial downscaling.

ACS Style

Hongjie He; Ke Yang; ShuSen Wang; Hasti Andon Petrosians; Ming Liu; Junhua Li; JosÊ Marcato Junior; Wesley Nunes Gonçalves; Lanying Wang; Jonathan Li. Deep Learning Approaches to Spatial Downscaling of GRACE Terrestrial Water Storage Products Using EALCO Model Over Canada. Canadian Journal of Remote Sensing 2021, 1 -19.

AMA Style

Hongjie He, Ke Yang, ShuSen Wang, Hasti Andon Petrosians, Ming Liu, Junhua Li, JosÊ Marcato Junior, Wesley Nunes Gonçalves, Lanying Wang, Jonathan Li. Deep Learning Approaches to Spatial Downscaling of GRACE Terrestrial Water Storage Products Using EALCO Model Over Canada. Canadian Journal of Remote Sensing. 2021; ():1-19.

Chicago/Turabian Style

Hongjie He; Ke Yang; ShuSen Wang; Hasti Andon Petrosians; Ming Liu; Junhua Li; JosÊ Marcato Junior; Wesley Nunes Gonçalves; Lanying Wang; Jonathan Li. 2021. "Deep Learning Approaches to Spatial Downscaling of GRACE Terrestrial Water Storage Products Using EALCO Model Over Canada." Canadian Journal of Remote Sensing , no. : 1-19.

Journal article
Published: 08 July 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Human settlements are guided by the proximity or availability of a natural resource such as river or lake basins containing set of streams. The harmonious development of human activity and natural conditions along watershed areas needs close attention and in-depth study. In this paper, the urban agglomerations and ecological spaces in the Yangtze River Delta, China, the Chao Lake Basin and its surrounding watershed ecosystem is taken as research subject for its serious environmental degradation problems during social and economic development. This paper adopted an effective machine learning algorithm (kernel-ELM) to extract land use and land /cover information, and to analyze the land use/cover pattern evolution rules of the Chao Lake Basin with long term Landsat imagery. Subsequent studies were then carried out to demonstrate the flood-affected area and its ecological impact in the basin in 2020, to reveal the occupation on land cover types. The results indicate Conclusions are drawn from the experiment results: (1) There has been significant change in cultivated land, forest land and construction land out of six key land cover types with dynamic degree of −10.17%, 4.61, 67.04% respectively. (2) Algae bloom pollution was extracted from pattern classification results and it was up to 15% of the total water area by the year 2018. (3) The occupation on land use/cover types of the flood was revealed. The results prove effective application of remote sensing technology in environmental analysis and planning for data-driven evaluation of governing policy. This work serves as a scientific basis for environmental management and regional planning in the Chao Lake Basin and can be served as a basis and a reference for evaluating an ecological policy and its impact for other economic developing watershed human settlements with ecological issues.

ACS Style

Yi Lin; Tinghui Zhang; Qin Ye; Jianqing Cai; Chengzhao Wu; Awase Khirni Syed; Jonathan Li. Long-term remote sensing monitoring on LUCC around Chaohu Lake with new information of algal bloom and flood submerging. International Journal of Applied Earth Observation and Geoinformation 2021, 102, 102413 .

AMA Style

Yi Lin, Tinghui Zhang, Qin Ye, Jianqing Cai, Chengzhao Wu, Awase Khirni Syed, Jonathan Li. Long-term remote sensing monitoring on LUCC around Chaohu Lake with new information of algal bloom and flood submerging. International Journal of Applied Earth Observation and Geoinformation. 2021; 102 ():102413.

Chicago/Turabian Style

Yi Lin; Tinghui Zhang; Qin Ye; Jianqing Cai; Chengzhao Wu; Awase Khirni Syed; Jonathan Li. 2021. "Long-term remote sensing monitoring on LUCC around Chaohu Lake with new information of algal bloom and flood submerging." International Journal of Applied Earth Observation and Geoinformation 102, no. : 102413.

Journal article
Published: 02 July 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Point cloud-based object detection is vital and essential for many real-world applications, such as autonomous driving and robot vision. The PointPillars model has achieved the efficient detection of objects in front of a vehicle. However, the algorithm does not consider the spatial structures semantic information stored in the three-dimensional point cloud for a given spatial structure, thus leading to missed or false detections for objects with complex spatial structures or singular structures. We propose an approach based on PointPillars, which considers the spatial structure characteristics of 3D point clouds to enhance the detection accuracy. First, based on the specified range of the z-axis coordinates, the entire point cloud scene is divided into several layers so that the point cloud areas in the same height interval form one layer. Data from several layers are obtained. Second, the point clouds of several layers are processed with Pillar Feature Net to obtain several pseudoimages. Each pseudoimage represents the semantic information from the corresponding level of the point cloud. Third, the obtained pseudoimages from each level are merged with the pseudoimages of the entire scene to obtain a feature map with spatial structure characteristics. We apply a Region Proposal Network, and an object detection operator processes the feature map and obtains the result of object detection. Experiments show that the proposed method has a highly accurate detection effect for objects with complex spatial structures. In addition, the proposed method does not erroneously detect objects with similar semantic information after vertical dimension projection.

ACS Style

Zongyue Wang; Qiming Xia; Jing Du; Shangfeng Huang; Jinhe Su; JosĂŠ Marcato Junior; Jonathan Li; Guorong Cai. 3D MSSD: A multilayer spatial structure 3D object detection network for mobile LiDAR point clouds. International Journal of Applied Earth Observation and Geoinformation 2021, 102, 102406 .

AMA Style

Zongyue Wang, Qiming Xia, Jing Du, Shangfeng Huang, Jinhe Su, JosĂŠ Marcato Junior, Jonathan Li, Guorong Cai. 3D MSSD: A multilayer spatial structure 3D object detection network for mobile LiDAR point clouds. International Journal of Applied Earth Observation and Geoinformation. 2021; 102 ():102406.

Chicago/Turabian Style

Zongyue Wang; Qiming Xia; Jing Du; Shangfeng Huang; Jinhe Su; JosĂŠ Marcato Junior; Jonathan Li; Guorong Cai. 2021. "3D MSSD: A multilayer spatial structure 3D object detection network for mobile LiDAR point clouds." International Journal of Applied Earth Observation and Geoinformation 102, no. : 102406.

Journal article
Published: 28 June 2021 in Remote Sensing
Reads 0
Downloads 0

Deep learning models have brought great breakthroughs in building extraction from high-resolution optical remote-sensing images. Among recent research, the self-attention module has called up a storm in many fields, including building extraction. However, most current deep learning models loading with the self-attention module still lose sight of the reconstruction bias’s effectiveness. Through tipping the balance between the abilities of encoding and decoding, i.e., making the decoding network be much more complex than the encoding network, the semantic segmentation ability will be reinforced. To remedy the research weakness in combing self-attention and reconstruction-bias modules for building extraction, this paper presents a U-Net architecture that combines self-attention and reconstruction-bias modules. In the encoding part, a self-attention module is added to learn the attention weights of the inputs. Through the self-attention module, the network will pay more attention to positions where there may be salient regions. In the decoding part, multiple large convolutional up-sampling operations are used for increasing the reconstruction ability. We test our model on two open available datasets: the WHU and Massachusetts Building datasets. We achieve IoU scores of 89.39% and 73.49% for the WHU and Massachusetts Building datasets, respectively. Compared with several recently famous semantic segmentation methods and representative building extraction methods, our method’s results are satisfactory.

ACS Style

Ziyi Chen; Dilong Li; Wentao Fan; Haiyan Guan; Cheng Wang; Jonathan Li. Self-Attention in Reconstruction Bias U-Net for Semantic Segmentation of Building Rooftops in Optical Remote Sensing Images. Remote Sensing 2021, 13, 2524 .

AMA Style

Ziyi Chen, Dilong Li, Wentao Fan, Haiyan Guan, Cheng Wang, Jonathan Li. Self-Attention in Reconstruction Bias U-Net for Semantic Segmentation of Building Rooftops in Optical Remote Sensing Images. Remote Sensing. 2021; 13 (13):2524.

Chicago/Turabian Style

Ziyi Chen; Dilong Li; Wentao Fan; Haiyan Guan; Cheng Wang; Jonathan Li. 2021. "Self-Attention in Reconstruction Bias U-Net for Semantic Segmentation of Building Rooftops in Optical Remote Sensing Images." Remote Sensing 13, no. 13: 2524.

Journal article
Published: 27 June 2021 in Remote Sensing
Reads 0
Downloads 0

A multispectral light detection and ranging (LiDAR) system, which simultaneously collects spatial geometric data and multi-wavelength intensity information, opens the door to three-dimensional (3-D) point cloud classification and object recognition. Because of the irregular distribution property of point clouds and the massive data volume, point cloud classification directly from multispectral LiDAR data is still challengeable and questionable. In this paper, a point-wise multispectral LiDAR point cloud classification architecture termed as SE-PointNet++ is proposed via integrating a Squeeze-and-Excitation (SE) block with an improved PointNet++ semantic segmentation network. PointNet++ extracts local features from unevenly sampled points and represents local geometrical relationships among the points through multi-scale grouping. The SE block is embedded into PointNet++ to strengthen important channels to increase feature saliency for better point cloud classification. Our SE-PointNet++ architecture has been evaluated on the Titan multispectral LiDAR test datasets and achieved an overall accuracy, a mean Intersection over Union (mIoU), an F1-score, and a Kappa coefficient of 91.16%, 60.15%, 73.14%, and 0.86, respectively. Comparative studies with five established deep learning models confirmed that our proposed SE-PointNet++ achieves promising performance in multispectral LiDAR point cloud classification tasks.

ACS Style

Zhuangwei Jing; Haiyan Guan; Peiran Zhao; Dilong Li; Yongtao Yu; Yufu Zang; Hanyun Wang; Jonathan Li. Multispectral LiDAR Point Cloud Classification Using SE-PointNet++. Remote Sensing 2021, 13, 2516 .

AMA Style

Zhuangwei Jing, Haiyan Guan, Peiran Zhao, Dilong Li, Yongtao Yu, Yufu Zang, Hanyun Wang, Jonathan Li. Multispectral LiDAR Point Cloud Classification Using SE-PointNet++. Remote Sensing. 2021; 13 (13):2516.

Chicago/Turabian Style

Zhuangwei Jing; Haiyan Guan; Peiran Zhao; Dilong Li; Yongtao Yu; Yufu Zang; Hanyun Wang; Jonathan Li. 2021. "Multispectral LiDAR Point Cloud Classification Using SE-PointNet++." Remote Sensing 13, no. 13: 2516.

Article
Published: 18 June 2021 in Canadian Journal of Remote Sensing
Reads 0
Downloads 0

Combining Dirichlet Mixture Models (DMM) with deep learning models for road extraction is an attractive study topic. Benefiting from DMM, the manually labeling work is alleviated. However, DMM suffers from high computational complexity due to pixel by pixel computations. Also, traditional constant parameter settings of DMM may not be suitable for different target images. To address the above problems, we propose an improved DMM which embeds superpixel strategy and sparse representation into DMM. In our road extraction framework, we first use improved DMM to filter out most backgrounds. Then, a trained deep CNN model is used for further precise road area recognition. To further promote the processing speed, we also apply the superpixel scanning strategy for CNN models. We tested our method on a Shaoshan dataset and proved that our method not only can achieve better results than other compared state-of-the-art image segmentation methods, but the processing speed and accuracy of DMM are also improved.

ACS Style

Ziyi Chen; Cheng Wang; Jonathan Li; Bineng Zhong; Jixiang Du; Wentao Fan. Combined Improved Dirichlet Models and Deep Learning Models for Road Extraction from Remote Sensing Images. Canadian Journal of Remote Sensing 2021, 1 -20.

AMA Style

Ziyi Chen, Cheng Wang, Jonathan Li, Bineng Zhong, Jixiang Du, Wentao Fan. Combined Improved Dirichlet Models and Deep Learning Models for Road Extraction from Remote Sensing Images. Canadian Journal of Remote Sensing. 2021; ():1-20.

Chicago/Turabian Style

Ziyi Chen; Cheng Wang; Jonathan Li; Bineng Zhong; Jixiang Du; Wentao Fan. 2021. "Combined Improved Dirichlet Models and Deep Learning Models for Road Extraction from Remote Sensing Images." Canadian Journal of Remote Sensing , no. : 1-20.

Journal article
Published: 17 June 2021 in IEEE Transactions on Geoscience and Remote Sensing
Reads 0
Downloads 0

Building region extraction from ALS point clouds has been widely studied, whereas instance-level building mapping has been overlooked and remains unsolved. In this study, we present a method to extract individual buildings from ALS point clouds with the help of widely accessible polygonal footprints. The key idea is to merge roof segments to a set of building candidates, from which correct instances are selected by finding optimal matches between polygonal footprints and building candidates. The method has three steps: roof segmentation, building candidate generation, and instance-polygon matching. The method is tested on two large-scale scenes of different building types and can generally achieve high instance-level building mapping accuracy (around 90%) when there are large positioning errors (6.0 m) among polygons. Future work will focus on classification errors in preprocessing, shape inconsistency between point clouds and polygons, and building footprint delineation and updating in postprocessing.

ACS Style

Shaobo Xia; Sheng Xu; Ruisheng Wang; Jonathan Li; Guanghui Wang. Building Instance Mapping From ALS Point Clouds Aided by Polygonal Maps. IEEE Transactions on Geoscience and Remote Sensing 2021, PP, 1 -13.

AMA Style

Shaobo Xia, Sheng Xu, Ruisheng Wang, Jonathan Li, Guanghui Wang. Building Instance Mapping From ALS Point Clouds Aided by Polygonal Maps. IEEE Transactions on Geoscience and Remote Sensing. 2021; PP (99):1-13.

Chicago/Turabian Style

Shaobo Xia; Sheng Xu; Ruisheng Wang; Jonathan Li; Guanghui Wang. 2021. "Building Instance Mapping From ALS Point Clouds Aided by Polygonal Maps." IEEE Transactions on Geoscience and Remote Sensing PP, no. 99: 1-13.

Journal article
Published: 12 June 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Determining the effects of simultaneously operating climate change and anthropogenic impacts on mangroves remains a challenge for the Persian Gulf and the Gulf of Oman. The objective of this study was to spatially quantify the spatial extents and biomass of dwarf and tall mangroves in response to drought intensities (Standardized Precipitation Index, SPI), sea-level rise (EC), land use/land cover change (LULC), and surface runoff and freshwater inflow to upstream mangrove catchments along the coasts of southern Iran over a 35-year period (1986–2020). The study drew on a long-term time series of 105 Landsat satellite images, maritime data, rainfall data, field surveys, and models to quantify independent variables (i.e., the WetSpass-M model to quantify surface runoff) and mixed models analysis to determine the important drivers of change. Although mixed model analysis indicated that sea-level rise was the main climate change driver of the development of spatial extents and biomass of both tall and dwarf mangroves, its influence was embedded in the larger temporal climate context of the region. Our findings show that spatial extents and biomass development are neither tightly coupled nor developed temporally or directionally synchronously in dwarf and tall mangroves. This study also shows a precipitous decline in rainfall amounts, SPI, and freshwater runoff volumes starting in 1998. The ensuing long-term drought that is still ongoing but decreased slightly in intensity in the last few years shaped the overall spatiotemporal development pattern of the mangrove structures over the entire study period. The correlation between biomass and the independent variables was similar for dwarf and tall mangroves and was positive with SPI and runoff amounts and negative with EC in all three study sites.

ACS Style

Saied Pirasteh; Eric K. Zenner; Davood Mafi-Gholami; Abolfazl Jaafari; Akram Nouri Kamari; Guoxiang Liu; Qing Zhu; Jonathan Li. Modeling mangrove responses to multi-decadal climate change and anthropogenic impacts using a long-term time series of satellite imagery. International Journal of Applied Earth Observation and Geoinformation 2021, 102, 102390 .

AMA Style

Saied Pirasteh, Eric K. Zenner, Davood Mafi-Gholami, Abolfazl Jaafari, Akram Nouri Kamari, Guoxiang Liu, Qing Zhu, Jonathan Li. Modeling mangrove responses to multi-decadal climate change and anthropogenic impacts using a long-term time series of satellite imagery. International Journal of Applied Earth Observation and Geoinformation. 2021; 102 ():102390.

Chicago/Turabian Style

Saied Pirasteh; Eric K. Zenner; Davood Mafi-Gholami; Abolfazl Jaafari; Akram Nouri Kamari; Guoxiang Liu; Qing Zhu; Jonathan Li. 2021. "Modeling mangrove responses to multi-decadal climate change and anthropogenic impacts using a long-term time series of satellite imagery." International Journal of Applied Earth Observation and Geoinformation 102, no. : 102390.

Article
Published: 11 June 2021 in Canadian Journal of Remote Sensing
Reads 0
Downloads 0

This paper investigates the deep neural networks for rapid and accurate detection of building rooftops in aerial orthoimages. The networks were trained using the manually labeled rooftop vector data digitized on aerial orthoimagery covering the Kitchener-Waterloo area. The performance of the three deep learning methods, U-Net, Fully Convolutional Network (FCN), and Deeplabv3+ were compared by training, validation, and testing sets in the dataset. Our results demonstrated that DeepLabv3+ achieved 63.8% in Intersection over Union (IoU), 77.8% in mean IoU (mIoU), 74% in precision, and 78% in F1-score. After improving the performance with focal loss, training loss was greatly cut down and the convergence rate experienced a significant growth. Meanwhile, rooftop detection also achieved higher performance, as Deeplabv3+ reached 93.6% in average pixel accuracy, with 65.4% in IoU, 79.0% in mIoU, 77.6% in precision, and 79.1% in F1-score. Lastly, in order to evaluate the effects of data volume, by changing data volume from 100% to 75% and 50% in ablation study, it shows that when data volume decreased, the performance of extraction also got worse, with IoU, mIoU, precision, and F1-score also mostly decreased.

ACS Style

Yuwei Cai; Hongjie He; Ke Yang; Sarah Narges Fatholahi; Lingfei Ma; Linlin Xu; Jonathan Li. A Comparative Study of Deep Learning Approaches to Rooftop Detection in Aerial Images. Canadian Journal of Remote Sensing 2021, 1 -19.

AMA Style

Yuwei Cai, Hongjie He, Ke Yang, Sarah Narges Fatholahi, Lingfei Ma, Linlin Xu, Jonathan Li. A Comparative Study of Deep Learning Approaches to Rooftop Detection in Aerial Images. Canadian Journal of Remote Sensing. 2021; ():1-19.

Chicago/Turabian Style

Yuwei Cai; Hongjie He; Ke Yang; Sarah Narges Fatholahi; Lingfei Ma; Linlin Xu; Jonathan Li. 2021. "A Comparative Study of Deep Learning Approaches to Rooftop Detection in Aerial Images." Canadian Journal of Remote Sensing , no. : 1-19.

Journal article
Published: 02 June 2021 in International Journal of Applied Earth Observation and Geoinformation
Reads 0
Downloads 0

Non-point source (NPS) pollution has greatly threatened socio-economic development and human health due to water environment degradation. It is very important to quantitatively analyze spatio-temporal variation rules of NPS pollution sources surrounding drinking water source area (DWSA) and their impact on the water environment with time-series satellite images. In this paper, we study a systematic remote sensing monitoring method on DWSA of upper Huangpu River, Shanghai. Firstly, an optimized Extreme Learning Machine (ELM) classification algorithm, namely Mixed Kernel ELM with Particle Swarm Optimization (PSO-MK-ELM) was constructed. Based on the PSO-MK-ELM, four NPS pollution sources- farmland, building land, woodland, and water were identified accurately and efficiently. Then their corresponding spatiotemporal analysis was performed with 30 years (1989–2019) Landsat images. On the basis of NPS pollution source area and census data from 1989 to 2017, the principal pollutants discharged into DWSA were also calculated with the common Export Coefficient Model (ECM). Finally, the contributions of the spatial and temporal changes of NPS pollution sources on pollutant emissions were analyzed. The result indicates the PSO-MK-ELM has an advantage of efficiency and accuracy in NPS pollution source extraction and our results are expected to provide a scientific basis and data support for NPS pollution control and DWSA protection for better practices for environmental management in megacities worldwide.

ACS Style

Yi Lin; Lang Li; Jie Yu; Yuan Hu; Tinghui Zhang; Zhanglin Ye; Awase Syed; Jonathan Li. An optimized machine learning approach to water pollution variation monitoring with time-series Landsat images. International Journal of Applied Earth Observation and Geoinformation 2021, 102, 102370 .

AMA Style

Yi Lin, Lang Li, Jie Yu, Yuan Hu, Tinghui Zhang, Zhanglin Ye, Awase Syed, Jonathan Li. An optimized machine learning approach to water pollution variation monitoring with time-series Landsat images. International Journal of Applied Earth Observation and Geoinformation. 2021; 102 ():102370.

Chicago/Turabian Style

Yi Lin; Lang Li; Jie Yu; Yuan Hu; Tinghui Zhang; Zhanglin Ye; Awase Syed; Jonathan Li. 2021. "An optimized machine learning approach to water pollution variation monitoring with time-series Landsat images." International Journal of Applied Earth Observation and Geoinformation 102, no. : 102370.

Journal article
Published: 01 June 2021 in ISPRS Journal of Photogrammetry and Remote Sensing
Reads 0
Downloads 0

Semantic segmentation of 3D Light Detection and Ranging (LiDAR) indoor point clouds using deep learning has been an active topic in recent years. However, most deep neural networks on point clouds conduct multi-level feature fusion via a simple U-shape architecture, which lacks enough capacity on both classification and localization in the segmentation task. In this paper, we propose a Neural Architecture Search (NAS) method to search a Feature Pyramid Network (FPN) module for 3D indoor point cloud semantic segmentation. Specifically, we aim to automatically find an effective feature pyramid architecture as a feature fusion neck in a designed novel pyramidal search space covering all information communication paths for multi-level features. The searched FPN module, named SFPN, contains the most important connections among all the potential paths to fuse representations at different levels. Our proposed SFPN is generic and effective as well as capable to be added to existing segmentation networks to augment the segmentation performance. Extensive experiments on ScanNet and S3DIS show that consistent and remarkable gains of segmentation performance can be achieved by different classical networks combined with SFPN. Specially, PointNet++-SFPN achieves mIoU gains of 7.8% on ScanNet v2 and 4.7% on S3DIS, and PointConv-SFPN achieves 4.5% and 3.7% improvement respectively on the above datasets.

ACS Style

Haojia Lin; Shangbin Wu; Yiping Chen; Wen Li; Zhipeng Luo; Yulan Guo; Cheng Wang; Jonathan Li. Semantic segmentation of 3D indoor LiDAR point clouds through feature pyramid architecture search. ISPRS Journal of Photogrammetry and Remote Sensing 2021, 177, 279 -290.

AMA Style

Haojia Lin, Shangbin Wu, Yiping Chen, Wen Li, Zhipeng Luo, Yulan Guo, Cheng Wang, Jonathan Li. Semantic segmentation of 3D indoor LiDAR point clouds through feature pyramid architecture search. ISPRS Journal of Photogrammetry and Remote Sensing. 2021; 177 ():279-290.

Chicago/Turabian Style

Haojia Lin; Shangbin Wu; Yiping Chen; Wen Li; Zhipeng Luo; Yulan Guo; Cheng Wang; Jonathan Li. 2021. "Semantic segmentation of 3D indoor LiDAR point clouds through feature pyramid architecture search." ISPRS Journal of Photogrammetry and Remote Sensing 177, no. : 279-290.

Research article
Published: 24 May 2021 in Canadian Journal of Remote Sensing
Reads 0
Downloads 0

The information-accurate road network database is greatly significant and provides essential input to many transportation-related activities. Recently, remote sensing images have been an important data source for assisting rapid road network updating tasks. However, due to the diverse challenging scenarios of roads in remote sensing images, such as occlusions, shadows, material diversities, and topology variations, it is still difficult to realize highly accurate extraction of roads. This paper proposes a novel context-augmentation and self-attention capsule feature pyramid network (CS-CapsFPN) to extract roads from remote sensing images. By designing a capsule feature pyramid network architecture, the proposed CS-CapsFPN can extract and fuze different-level and different-scale high-order capsule features to provide a high-resolution and semantically strong feature representation for predicting the road region maps. By integrating the context-augmentation and self-attention modules, the proposed CS-CapsFPN can exploit multi-scale contextual properties at a high-resolution perspective and emphasize channel-wise informative features to further enhance the feature representation robustness. Quantitative evaluations on two test datasets show that the proposed CS-CapsFPN achieves a competitive performance with a precision, recall, intersection-over-union, and Fscore of 0.9470, 0.9407, 0.8957, and 0.9438, respectively. Comparative studies also confirm the feasibility and superiority of the proposed CS-CapsFPN in road extraction tasks.

ACS Style

Yongtao Yu; Jun Wang; Haiyan Guan; Shenghua Jin; Yongjun Zhang; Changhui Yu; E. Tang; Shaozhang Xiao; Jonathan Li. CS-CapsFPN: A Context-Augmentation and Self-Attention Capsule Feature Pyramid Network for Road Network Extraction from Remote Sensing Imagery. Canadian Journal of Remote Sensing 2021, 1 -19.

AMA Style

Yongtao Yu, Jun Wang, Haiyan Guan, Shenghua Jin, Yongjun Zhang, Changhui Yu, E. Tang, Shaozhang Xiao, Jonathan Li. CS-CapsFPN: A Context-Augmentation and Self-Attention Capsule Feature Pyramid Network for Road Network Extraction from Remote Sensing Imagery. Canadian Journal of Remote Sensing. 2021; ():1-19.

Chicago/Turabian Style

Yongtao Yu; Jun Wang; Haiyan Guan; Shenghua Jin; Yongjun Zhang; Changhui Yu; E. Tang; Shaozhang Xiao; Jonathan Li. 2021. "CS-CapsFPN: A Context-Augmentation and Self-Attention Capsule Feature Pyramid Network for Road Network Extraction from Remote Sensing Imagery." Canadian Journal of Remote Sensing , no. : 1-19.

Journal article
Published: 13 May 2021 in IEEE Transactions on Geoscience and Remote Sensing
Reads 0
Downloads 0

Extracting the power lines and pylons automatically and accurately from airborne LiDAR data is a critical step in inspecting the routine power line, especially in the remote mountainous areas. However, challenges arise in using existing methods to extract the targets from large scenarios of remote mountainous areas since the terrain is undulating, and the features are difficult to distinguish. In this article, to overcome these challenges, we propose a graph convolutional network (GCN)-based method to extract power lines and pylons from Airborne LiDAR point clouds. First, data augmentation and near-ground filtering methods are developed to overcome the problems of insufficient and imbalanced samples in the LiDAR data. Then, a GCN-based framework is proposed to extract the power lines and pylons, which consist of two main modules, i.e., the neighborhood dimension information (NDI) module and the neighborhood geometry information aggregation (NGIA) module. These two modules are designed to strengthen the model's ability to portray local geometric details. Besides, an attention fusion module is investigated to further improve the NDI and NGIA features. Finally, a line structure constraint algorithm is proposed to identify individual power lines, where the power corridor is reconstructed using a polynomial-based algorithm. Numerical experiments are conducted based on two different power line scenarios acquired in mountainous areas. The results demonstrate the superior performances of the proposed method over several existing algorithms, where the F₁ score and quality of the power line are 99.3% and 98.6%, and the results of the pylon are 96% and 92.4%, respectively. The identification rate of power line identification is above 98%.

ACS Style

Wen Li; Zhipeng Luo; Zhenlong Xiao; Yiping Chen; Cheng Wang; Jonathan Li. A GCN-Based Method for Extracting Power Lines and Pylons From Airborne LiDAR Data. IEEE Transactions on Geoscience and Remote Sensing 2021, PP, 1 -14.

AMA Style

Wen Li, Zhipeng Luo, Zhenlong Xiao, Yiping Chen, Cheng Wang, Jonathan Li. A GCN-Based Method for Extracting Power Lines and Pylons From Airborne LiDAR Data. IEEE Transactions on Geoscience and Remote Sensing. 2021; PP (99):1-14.

Chicago/Turabian Style

Wen Li; Zhipeng Luo; Zhenlong Xiao; Yiping Chen; Cheng Wang; Jonathan Li. 2021. "A GCN-Based Method for Extracting Power Lines and Pylons From Airborne LiDAR Data." IEEE Transactions on Geoscience and Remote Sensing PP, no. 99: 1-14.