Liang-zhi Li

Visiting PhD Candidate
Liangzhi Li

l38li@uwaterloo.ca

Research Interests

The combined use of multimodal earth observation (EO) imagery can provide a more comprehensive understanding of the target area. Although EO images can be coarsely corrected using orbital parameters and strict geometric positioning models to remove geometric distortions between images (e.g., rotation and scaling), there will still be position shifts of a few pixels to tens of pixels between images. Therefore, a matching process should be implemented for these multimodal EO images. My current research focuses on the establishment of multimodal EO image matching based on deep neural networks.

Education

  • Ph.D., Information Engineering, School of Electrical and Information Engineering, Chang'an University, Xi'an, China, Sept 2019 - present
  • M.Sc., Geomatics Engineering, School of Geology Engineering and Geomatics, Chang'an University, Xi'an, China, Sept 2017 – June 2019
  • B.Eng., Geomatics Engineering, Shandong Jiaotong University, Jinan, China, Sept 2013 – June 2017

Publications

  • Li L, Liu M, Ma L, et al. 2022. Cross-Modal feature description for remote sensing image matching. International Journal of Applied Earth Observation and Geoinformation, 112, 102964.
  • Li L, L. Han, H. Cao and H. Hu, 2022. Joint self-attention for remote sensing image matching, IEEE Geoscience and Remote Sensing Letters, doi: 10.1109/LGRS.2022.3191364.
  • Li L, Han L, Ye Y, 2022. Self-supervised keypoint detection and cross-fusion matching networks for multimodal remote sensing image registration. Remote Sensing, 14(15), 3599.
  • Li L, Han L, Ming T, et al. 2021. A deep learning semantic template matching framework for remote sensing image registration. ISPRS Journal of Photogrammetry and Remote Sensing, 181, 205-217.
  • Li L, Han L, Ming T, et al., 2020. Remote sensing image registration based on deep learning regression model. IEEE Geoscience and Remote Sensing Letter, doi.10.1109/LGRS.2020.3032439.
  • Li L, Han L, Hu H, et al. 2020. Standardized object-based dual CNNs for very high-resolution remote sensing image classification and standardization combination effect analysis. International Journal of Remote Sensing, 41(17), 6635-6663.