What question did this study set out to answer?

To improve radar target recognition performance in complex environments with low signal-to-noise ratios.

July 26, 2026Remote Sensing0 citationsOpen Access

Improved Ship Target Recognition Using Dual-Path Cooperative Fusion Mechanism

An Improved Recognition Technique for Ship Targets Based on Dual-Path Cooperative Fusion Mechanism

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates enhanced radar target recognition in complex environments, indicating superior accuracy of the proposed method.

To improve radar target recognition performance in complex environments with low signal-to-noise ratios.
Developed a recognition technique using heterogeneous multi-modal feature fusion.
Constructed a three-channel parallel encoding network incorporating ConvLSTM, Conv1D-GRU, and GRU.
Designed a dual-path cooperative fusion mechanism with a cross-attention module and an adaptive weight fusion layer.
Achieved 99.42% average recognition accuracy under co-polarization and 98.15% under cross-polarization.
Improved recognition accuracy from 90.01% to 99.42% in co-polarization and from 81.14% to 98.15% in cross-polarization compared to traditional methods.

Su et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

July 26, 2026Remote Sensing0 citationsOpen Access

An Improved Recognition Technique for Ship Targets Based on Dual-Path Cooperative Fusion Mechanism

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates enhanced radar target recognition in complex environments, indicating superior accuracy of the proposed method.

To improve radar target recognition performance in complex environments with low signal-to-noise ratios.
Developed a recognition technique using heterogeneous multi-modal feature fusion.
Constructed a three-channel parallel encoding network incorporating ConvLSTM, Conv1D-GRU, and GRU.
Designed a dual-path cooperative fusion mechanism with a cross-attention module and an adaptive weight fusion layer.
Achieved 99.42% average recognition accuracy under co-polarization and 98.15% under cross-polarization.
Improved recognition accuracy from 90.01% to 99.42% in co-polarization and from 81.14% to 98.15% in cross-polarization compared to traditional methods.

Su et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark