Home Chang Liu

Chang Liu

Building Damage Estimation After Natural Disaster Using Multi Satellite Source Data Based on Machine Learning

University New South Wales Sydney

Chang Liu is currently completing a post doctorate at MIT Senseable City Lab, USA. Chang completed her PhD at the University of New South Wales (UNSW) Sydney in Australia. Her research focuses on the application of artificial intelligence (AI) in geospatial engineering and remote sensing for urban-related research, and have been keeping up to date with the development of state-of-the-art technologies in the discipline. Her interests include earth observation, remote sensing, Lidar, semantic segmentation, urban analysis, and natural disaster analysis.

Publications

- Journal Article
19/02/2024
Demystifying the Influencing Factors of Construction 4.0 Technology Implementation from a Sustainability Starting Point: Current Trends and Future Research Roadmap
- Journal Article
01/12/2023
Channel Attention and Normal-Based Local Feature Aggregation Network (CNLNet): A Deep Learning Method for Predisaster Large-Scale Outdoor Lidar Semantic Segmentation
- Conference Presentation
20/10/2023
The Influence of Changing Features on the Accuracy of Deep Learning-Based Large-Scale Outdoor Lidar Semantic Segmentation
- PhD Thesis
01/09/2023
Large-Scale Building Footprint Extraction and Damage Level Classification: Deep Learning Approaches with Satellite Imagery and LiDAR Data
- Conference Presentation
16/07/2023
An Improved Luminance Contrast Saliency Map for Burned Area Mapping Based INSAR Coherence Difference Image
- Conference Presentation
16/07/2023
Flood Assessment and Mapping Based on SAR and QUAV Vertical Remote Sensing Framework: A Case Study of 2022 Australia Moama Floods
- Journal Article
31/03/2023
Dielectric Fluctuation and Random Motion over Ground Model (DF-RMoG): An Unsupervised Three-Stage Method of Forest Height Estimation Considering Dielectric Property Changes
- Journal Article
01/11/2022
Bibliometric Analysis of Interferometric Synthetic Aperture Radar (InSAR) Application in Land Subsidence from 2000 to 2021
- Journal Article
29/04/2022
A Novel Attention-based Deep Learning Method for Post-disaster Building Damage Classification

Chang Liu

Building Damage Estimation After Natural Disaster Using Multi Satellite Source Data Based on Machine Learning

Publications

Demystifying the Influencing Factors of Construction 4.0 Technology Implementation from a Sustainability Starting Point: Current Trends and Future Research Roadmap

Channel Attention and Normal-Based Local Feature Aggregation Network (CNLNet): A Deep Learning Method for Predisaster Large-Scale Outdoor Lidar Semantic Segmentation

The Influence of Changing Features on the Accuracy of Deep Learning-Based Large-Scale Outdoor Lidar Semantic Segmentation

Large-Scale Building Footprint Extraction and Damage Level Classification: Deep Learning Approaches with Satellite Imagery and LiDAR Data

An Improved Luminance Contrast Saliency Map for Burned Area Mapping Based INSAR Coherence Difference Image

Flood Assessment and Mapping Based on SAR and QUAV Vertical Remote Sensing Framework: A Case Study of 2022 Australia Moama Floods

Dielectric Fluctuation and Random Motion over Ground Model (DF-RMoG): An Unsupervised Three-Stage Method of Forest Height Estimation Considering Dielectric Property Changes

Bibliometric Analysis of Interferometric Synthetic Aperture Radar (InSAR) Application in Land Subsidence from 2000 to 2021

A Novel Attention-based Deep Learning Method for Post-disaster Building Damage Classification