A5034059316- Remote-Sensing Image Classification
- Land Use and Ecosystem Services
- Impact of Light on Environment and Health
- Automated Road and Building Extraction
- Remote Sensing and Land Use
- Urbanization and City Planning
- Remote Sensing in Agriculture
- Urban Heat Island Mitigation
- Advanced Image and Video Retrieval Techniques
- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
- Urban Transport and Accessibility
- Image Retrieval and Classification Techniques
- Housing Market and Economics
- Data Stream Mining Techniques
State Forestry and Grassland Administration
2024
Beijing Forestry University
2024
University at Buffalo, State University of New York
2018-2022
PLA Information Engineering University
2019
The vacant house is an essential phenomenon of urban decay and population loss. Exploration the correlations between housing vacancy some socio-environmental factors conducive to understanding mechanism shrinking revitalization. In recent years, rapidly developing night-time remote sensing, which has ability detect artificial lights, been widely applied in applications associated with human activities. Current sensing studies on rates are limited by coarse spatial resolution data. launch...
(1) Background: Public sidewalk GIS data are essential for smart city development. We developed an automated street-level detection method with image-processing Google Street View data. (2) Methods: view images were processed to produce graph-based segmentations. Image segment regions manually labeled and a random forest classifier was established. used multiple aggregation steps determine presence. (3) Results: In total, 2438 GSV street 78,255 segmented image examined. The image-level had...
The formation and demolition of vacant houses are the most visible sign city shrinking revitalization. Timely detection has become an inevitable task to aid "Smart City" initiative. Two pressing problems exist for houses, however: (1) No publicly accessible information is available at individual house level (2) decennial census survey does not catch up with rapidly changing status houses. To this end, remote sensing provides a low-cost avenue detecting Traditionally, was accredited its...
Abandoned houses (AH) present an utmost challenge confronting the urban environment in contemporary U.S. shrinking cities. Data accessibility is a major hurdle that prevents acquisition of large-scale AH information at individual property level. To this end, latest revolution open-access remote sensing platforms has witnessed plethora multi-source, multi-perspective fine-spatial-resolution data for environments, among which very-high-resolution (VHR) top-down view images and...
Night-Time light imagery has become a very popular data source for monitoring the intensity of human activity in urban environments. Subpixel information is required many applications, however, widely used low-spatial-resolution night-time suffers from mixed-pixel problem. In this paper, using Visible Infrared Imaging Radiometer Suite (VIIRS) data, we presented first spectral mixture analysis (SMA) on imagery. Specifically, proposed to define two endmembers (light and dark) endmember...
Building change detection (BCD) from remote sensing images is an essential field for urban studies. In this well-developed field, Convolutional Neural Networks (CNNs) and Transformer have been leveraged to empower BCD models in handling multi-scale information. However, it still challenging accurately detect subtle changes using current models, which has the main bottleneck improving accuracy. paper, a differential feature self-attention network (MDFA-Net) proposed effectively integrate CNN...
Abstract In order to solve the problem of insufficient use sequence information and low detection efficiency traditional anomaly methods, this paper introduces Markov chain into user behaviour detection, proposes a description based on support vector data field ( SVDD) User Behaviour Sequence Detection Method (ASDMS), which first uses accurately quantify sequence, then constructs user’s normal model model, identifies behaviour. The experimental results show that ASDMS method has better...