Cheng Wang

Cheng Wang
Xiamen University | XMU · Department of Computer Science

IET Fellow - Professor of Computer Science - Ph.D

About

379
Publications
91,709
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
5,525
Citations
Introduction
current research interests: 3D Vision, LiDAR, Mobile Mapping, Geospatial Big Data Analysis.
Additional affiliations
August 2011 - present
Xiamen University
Position
  • Professor (Full)
June 2006 - June 2007
The University of Calgary
Position
  • Visiting Scientist
December 2002 - August 2011
National University of Defense Technology
Position
  • Professor (Associate)

Publications

Publications (379)
Article
Rigid transformation poses a big challenge for many deep learning models on 3D point clouds as the point coordinates can be drastically changed. To tackle this issue, we proposed Point Distance Convolution (PDConv). Relying on distance information, it extracts invariant features from the set of points regardless of the rigid transformations it unde...
Conference Paper
Point cloud segmentation plays an important role in AI applications such as autonomous driving, AR, and VR. However, previous point cloud segmentation neural networks rarely pay attention to the topological correctness of the segmentation results. In this paper, focusing on the perspective of topology awareness. First, to optimize the distribution...
Conference Paper
Full-text available
Existing motion capture datasets are largely short-range and cannot yet fit the need of long-range applications. We propose LiDARHuman26M, a new human motion capture dataset captured by LiDAR at a much longer range to overcome this limitation. Our dataset also includes the ground truth human motions acquired by the IMU system and the synchronous RG...
Article
Automated extraction of roads from remotely sensed data come forth various usages ranging from digital twins for smart cities, intelligent transportation, urban planning, autonomous driving, to emergency management. Many studies have focused on promoting the progress of methods for automated road extraction from aerial and satellite optical images,...
Article
Full-text available
Event camera is a new vision sensor that produces independent asynchronous responses to each pixel's change of illumination intensity. The unique principle of event camera has many advantages over traditional cameras, such as low latency, high temporal resolution, and high dynamic range (HDR). These advantages make event camera ideal for dealing wi...
Article
Full-text available
Feature normalization has been a crucial step in convolutional neural networks (CNNs) in the past few years. Discriminative feature abstraction is indispensable for boosting the overall performance of learning models. For 3D data, in both point cloud and mesh models, the inner product (cosine similarity) is frequently applied for similarity estimat...
Conference Paper
Full-text available
Learning the embeddings for urban regions from human mobility data can reveal the functionality of regions, and then enables the correlated but distinct tasks such as crime prediction. Human mobility data contains rich but abundant information, which yields to the comprehensive region embed-dings for cross domain tasks. In this paper, we propose mu...
Article
Graph convolution networks (GCNs) have been proven powerful in describing unstructured data. Currently, most of existing GCNs aim on more accuracy by constructing deeper models. However, these methods show limited benefits, and they often suffer from the common drawbacks brought by deep networks, such as large model size, high memory consumption an...
Article
Visual localization is critical to many robotics and computer vision applications. Absolute pose regression performs localization by encoding scene features followed by pose regression, which has achieved impressive results in localization. It recovers 6-DoF poses from captured scene data alone. However, current methods suffer from being retrained...
Preprint
Full-text available
Existing motion capture datasets are largely short-range and cannot yet fit the need of long-range applications. We propose LiDARHuman26M, a new human motion capture dataset captured by LiDAR at a much longer range to overcome this limitation. Our dataset also includes the ground truth human motions acquired by the IMU system and the synchronous RG...
Preprint
Full-text available
We propose Human-centered 4D Scene Capture (HSC4D) to accurately and efficiently create a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, and rich interactions between humans and environments. Using only body-mounted IMUs and LiDAR, HSC4D is space-free without any external devices' constraints and map-fre...
Article
Natural disasters cause extensive damages to urban cities, demanding authorities to take urgent and effective measures to restore normalcy on transportation. During a disaster, restoring road transportation in a timely manner for rescue, supply and also prevent the risk of road accidents due to obstacles is of vital importance. Traditional post-dis...
Article
Full-text available
The key challenge in processing point clouds lies in the inherent lack of ordering and irregularity of the 3D points. By relying on perpoint multi-layer perceptions (MLPs), most existing point-based approaches only address the first issue yet ignore the second one. Directly convolving kernels with irregular points will result in loss of shape infor...
Conference Paper
Full-text available
Road markings extraction (RME) from 3D point clouds acquired by mobile LiDAR systems has been widely used for road safety and autonomous driving. However, due to the increasing awareness of personal data protection and national information security regulations, most autonomous driving companies are not willing to share their private point clouds da...
Article
Full-text available
Robust local cross-domain feature descriptors of 2D images and 3D point clouds play an important role in 2D and 3D vision applications, e.g. augmented Reality (AR) and robot navigation. Essentially, the robust local cross-domain feature descriptors have the potential to establish a spatial relationship between 2D space and 3D space. However, it is...
Article
Accurate high-resolution downscaling of surface climate variables (such as surface temperature) over urban areas has long been a critical yet unresolved research problem in the field of urban climate and environmental sciences. In this paper, we propose a novel physics informed neural network (PINN) based framework: DeepUrbanDownscale (DUD) for hig...
Article
With the rapid development of deep learning, many deep learning-based approaches have made great achievements in object detection tasks. It is generally known that deep learning is a data-driven approach. Data directly impact the performance of object detectors to some extent. Although existing datasets include common objects in remote sensing imag...
Preprint
Learning the embeddings for urban regions from human mobility data can reveal the functionality of regions, and then enables the correlated but distinct tasks such as crime prediction. Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks. In this paper, we propose mul...
Article
Large-scale semantic segmentation point cloud is an ongoing research topic for on-land environments. However, there is a rare deep learning research study for the sub-surface environment. Although, PointNet and its successor PointNet++ have become the cornerstone of point cloud segmentation. However, these techniques handle a relatively small numbe...
Article
Full-text available
A micro vibration signal extraction method based on deep neural network is proposed. Rough surface of vibrating object modulates the illuminating laser wave front and generates speckle pattern, which is recorded by a linear array CMOS and preprocessed and input into a 16-layer convolution neural network (CNN) trained with specially prepared data. T...
Article
Due to the advantages of 3D point clouds over 2D optical images, the related researches on scene understanding in 3D point clouds have been increasingly attracting wide attention from academy and industry. However, many 3D scene understanding methods largely require abundant supervised information for training a data-driven model. The acquisition o...
Article
Individual tree detection is critical for forest investigation and monitoring. Several existing methods have difficulties to detect trees in complex forest environment due to insufficiently mining descriptive features. This study proposes a deep learning framework based on a designed multi-channel information complementarity representation for dete...
Preprint
Full-text available
Recent studies focus on formulating the traffic forecasting as a spatio-temporal graph modeling problem. They typically construct a static spatial graph at each time step and then connect each node with itself between adjacent time steps to construct the spatio-temporal graph. In such a graph, the correlations between different nodes at different t...
Chapter
Organoid, a 3D in vitro cell culture, has high similarities with derived tissues or organs in vivo, which makes it widely used in personalized drug screening. Although organoids play an essential role in drug screening, the existing methods are difficult to accurately evaluate the viability of organoids, making the existing methods still have many...
Article
Full-text available
Gulangyu Island is a special case of social development and changes since modern China. In the past, Chinese and foreign people lived together and Chinese and Western cultures coexisted, resulting in an international community with outstanding cultural diversity and modern quality of life. As a functional carrier, space is of great reference signif...
Article
Automatic building facade point cloud semantic segmentation is an important step in 3D urban building reconstruction. How to correctly segment the components(e.g., windo ws, walls, columns) from the building facade is still a challenging task. According to the characteristics of building facade point clouds, we introduce LFA-Net, an efficient neura...
Article
Background and Objective: Deep convolutional networks are powerful tools for single-modality medical image segmentation, whereas generally require semantic labelling or annotation that is laborious and time-consuming. However, domain shift among various modalities critically deteriorates the performance of deep convolutional networks if only traine...
Article
Registering the 2D images (2D space) with the 3D model of the environment (3D space) provides a promising solution to outdoor Augmented Reality (AR) virtual-real registration. In this work, we use the position and orientation of the ground camera image to synthesize a corresponding rendered image from the outdoor large-scale 3D image-based point cl...
Article
The semantic segmentation of building facades is critical for various construction applications, such as urban building reconstruction and damage assessments. As there is a lack of 3D point cloud datasets related to fine-grained building facades, in this work we construct the first large-scale point cloud benchmark dataset for building facade seman...
Chapter
The 2D-3D matching determine the spatial relationship between 2D and 3D space, which can be used for Augmented Reality (AR) and robot pose estimation, and provides support for multi-sensor fusion. Specifically, the cross-domain descriptor extraction between 2D images and 3D point clouds is a solution to achieve 2D-3D matching. Essentially, the 3D p...
Article
Water wave monitoring is a vital issue for coastal research and plays a key role in geomorphological changes, erosion and sediment transportation, coastal hazards, risk assessment, and decision making. However, despite missing data and the difficulty of capturing the data of nearshore fieldwork, the analysis of water wave surface parameters is stil...
Preprint
Full-text available
Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embeddin...
Article
Traffic violations have become one of the major threats to urban transportation systems, undermining human safety and causing economic losses. To alleviate this problem, crowd-based patrol forces including traffic police and voluntary participants have been employed in many cities. To adaptively optimize patrol routes with limited manpower, it is e...
Article
Point cloud completion aims to reconstruct complete point clouds from partial point clouds, which is widely used in various fields such as autonomous driving and robotics. Most existing methods are sparse point cloud completion, where the number of point clouds after completion is relatively small and the details are insufficient. This article prop...
Article
Full-text available
In this paper, we introduce the 2020 Gaofen Challenge and relevant scientific outcomes. The 2020 Gaofen Challenge is an international competition, which is organized by the China High-Resolution Earth Observation Conference Committee and the Aerospace Information Research Institute, Chinese Academy of Sciences and technically co-sponsored by the IE...
Article
Full-text available
Nowadays, a large number of sensors are equipped on mobile or stationary platforms, which continuously generate geo-tagged and time-stamped readings (i.e., geo-sensory data) that contain rich information about the surrounding environment. These data have irregular space and time coordinates. To represent geo-sensory data, there have been extensive...
Article
Full-text available
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 o...
Preprint
Full-text available
Gulangyu Island is a special case of social development and changes since modern China. In the past, Chinese and foreign people lived together and Chinese and Western cultures coexisted, resulting in an international community with outstanding cultural diversity and modern quality of life. As a functional carrier, space is of great reference signif...
Article
Full-text available
Road extraction from optical remote sensing images has many important application scenarios, such as navigation, automatic driving and road network planning, etc. Current deep learning based models have achieved great successes in road extraction. Most deep learning models improve abilities rely on using deeper layers, resulting to the obese of the...
Article
To recover relative camera motion accurately and robustly, establishing a set of point-to-point correspondences in the pixel space is an essential yet challenging task in computer vision. Even though multi-scale design philosophy has been used with significant success in computer vision tasks, such as object detection and semantic segmentation, lea...
Conference Paper
This paper proposes the first tracklet proposal network, named PC-TCNN, for Multi-Object Tracking (MOT) on point clouds. Our pipeline first generates tracklet proposals, then refines these tracklets and associates them to generate long trajectories. Specifically, object proposal generation and motion regression are first performed on a point cloud...
Article
Full-text available
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 segmenta...
Article
The surging data traffic and dynamic user mobility in 5G networks have posed significant demands for mobile operators to increase data processing capacity and ensure user handover quality. Specifically, a cost-effective and quality-aware radio access network (RAN) is in great necessity. With the emergence of fog-computing-based RAN architecture (Fo...
Article
Recently, a lot of attention is given to deep learning on raw 3D point clouds. Existing approaches, however, either exploit the global shape feature without paying attention to the local features or hierarchically exploit local features with little attention to the global shape feature. In this paper, we proposed Fused Feature Point Network (FFPoin...
Article
Full-text available
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 t...
Article
Urban villages refer to the residential areas lagging behind the rapid urbanization process in many developing countries. These areas are usually with overcrowded buildings, high population density, and low living standards, bringing potential risks of public safety and hindering the urban development. Therefore, it is crucial for urban authorities...
Article
Full-text available
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 d...
Article
Frequency-domain dynamic load identification methods based on neural network (NN) models construct models independently at each frequency, but are inaccurate and inefficient to train. To address these problems, a deep regression adaptation network (DRAN) with model-transfer learning is proposed for identifying dynamic loads in the frequency domain....
Preprint
Semantic segmentation of building facade is significant in various applications, such as urban building reconstruction and damage assessment. As there is a lack of 3D point clouds datasets related to the fine-grained building facade, we construct the first large-scale building facade point clouds benchmark dataset for semantic segmentation. The exi...
Article
Point clouds and models with semantic information facilitate various indoor automation, ranging from indoor robotics to emergency responses. Studies are currently being conducted on semantic labeling and modeling based on offline mapped point clouds, in which, the performance is strongly limited by the mapping process. To address this issue, we pro...
Article
3D human trajectory reconstruction in an indoor scene is critical in various applications, such as indoor navigation and human activity recognition. This task is challenging due to occlusion and clutters of indoor scenes, flexible human body joints, and severe lack of relevant datasets. Although several methods have been proposed to reconstruct a 3...
Article
Full-text available
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,...
Conference Paper
Full-text available
Fairness has emerged as a critical problem in feder- ated learning (FL). In this work, we identify a cause of unfairness in FL – conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradien...
Article
Organoid, an in vitro 3D culture, has extremely high similarity with its source organ or tissue, which creates a model in vitro that simulates the in vivo environment. Organoids have been extensively studied in cell biology, precision medicine, drug toxicity, efficacy tests, etc., which have been proven to have high research value. Periodic observa...
Preprint
Full-text available
Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- \emph{conflicting} gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their g...
Preprint
This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing little computational cost during the inference stage. Another design that makes this framework different from many...
Article
Full-text available
High-Accuracy and high-efficiency 3-D sensing and associated data processing techniques are urgently needed for today’s roadway inventory, infrastructure health monitoring, autonomous driving, connected vehicles, urban modeling, and smart cities. 3D geospatial data acquired by digital photogrammetry or laser scanning or LiDAR systems have become on...
Article
Full-text available
Due to the wide distribution of crosswalks over the road nets, the finding of impaired crosswalk marks is usually long-time delayed, which may put crosswalk pedestrians into danger. To reduce the repairing cost and improve the finding speed of damaged crosswalks, this paper uses remote sensing images to automatically detect crosswalks. The detectio...
Article
Full-text available
Automatic building extraction from remote sensing imagery is crucial to urban construction and management. To address the main challenges of diverse building scale and appearance, this letter proposes an automatic building instance extraction method based on an improved hybrid task cascade (HTC). Our method consists of three components by obtaining...