Zhang et al. (2026) Enhanced Deep Recurrent Optical Flow With Efficient Feature Encoding and Channel Attention for River Surface Velocimetry

Identification

• Journal: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: Minghu Zhang, Jinjun Guo, Yingying Chen, Enzhan Zhang, Rui Jin, Xiaowei Nie, X. Li
• DOI: 10.1109/jstars.2026.3656354

Research Groups

[Information not available in the provided text]

Short Summary

This paper introduces an enhanced deep recurrent optical flow method, incorporating efficient feature encoding and channel attention, for improved river surface velocimetry.

Objective

• To develop and evaluate an enhanced deep recurrent optical flow algorithm with efficient feature encoding and channel attention for accurate and efficient river surface velocity measurement.

Study Configuration

• Spatial Scale: River surface (specific dimensions not provided).
• Temporal Scale: Not specified, but relates to video frame rates for optical flow analysis.

Methodology and Data

• Models used: Deep Recurrent Optical Flow, enhanced with efficient feature encoding and channel attention mechanisms.
• Data sources: Not explicitly stated, but typically involves video footage or image sequences of river surfaces.

Main Results

[Information not available in the provided text]

Contributions

[Information not available in the provided text]

Funding

[Information not available in the provided text]

Citation

@article{Zhang2026Enhanced,
  author = {Zhang, Minghu and Guo, Jinjun and Chen, Yingying and Zhang, Enzhan and Jin, Rui and Nie, Xiaowei and Li, X.},
  title = {Enhanced Deep Recurrent Optical Flow With Efficient Feature Encoding and Channel Attention for River Surface Velocimetry},
  journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  year = {2026},
  doi = {10.1109/jstars.2026.3656354},
  url = {https://doi.org/10.1109/jstars.2026.3656354}
}