Boundary-Guided Dual-Perspective Cross-Modal Fusion Network for RGB-IR Object Detection.
Saved in:
| Title: | Boundary-Guided Dual-Perspective Cross-Modal Fusion Network for RGB-IR Object Detection. |
|---|---|
| Authors: | Lin, Huachen1 (AUTHOR), Fu, Zhiwei1 (AUTHOR), Chen, Xiumei1 (AUTHOR), Feng, Guirong1 (AUTHOR) guirfeng@fzu.edu.cn |
| Source: | Remote Sensing. Sep2026, Vol. 18 Issue 18, p3175. 21p. |
| Subjects: | Multimodal user interfaces |
| Abstract: | Highlights: What are the main findings? Scene-level modality contributions driven by global illumination often diverge from local spatial reliability in RGB-IR scenes. This inconsistency can be effectively resolved by decoupling global modality weighting and local cross-modal rectification. Standard backbone downsampling progressively attenuates shallow boundary cues essential for target localization. Embedding explicit Sobel gradient priors into shallow dual-modal features successfully preserves these key geometric details. What are the implications of the main findings? The results demonstrate that the proposed boundary-guided dual-perspective fusion network significantly improves RGB-IR object detection accuracy while operating with substantially fewer parameters. BDPNet provides a robust and highly efficient paradigm for multimodal feature fusion, particularly suited for dynamic illumination conditions and thermally cluttered backgrounds. Visible-infrared (RGB-IR) object detection leverages multimodal information to ensure reliable perception in complex environments. However, dynamic scenes pose significant challenges due to the frequent inconsistency between scene-level modality contributions and local spatial reliability. Furthermore, standard feature extraction progressively attenuates boundary-sensitive structural cues, and unified fusion strategies often fail to capture spatially varying cross-modal complementarity. To overcome these limitations, we propose a Boundary-Guided Dual-Perspective Cross-Modal Fusion Network (BDPNet) to explicitly preserve shallow geometric structures and decouple deep semantic fusion into macroscopic and microscopic perspectives. Specifically, a Geometric Boundary Enhancement Module (GBEM) embeds Sobel-based high-frequency priors into shallow dual-modal features via residual spatial modulation, preventing the loss of crucial localization cues during downsampling. In the deep semantic space, a Hybrid Dual-Perspective Adaptive Fusion Module (HDAM) employs an illumination-aware branch for global modality weighting and a spatial confidence-driven branch for local cross-modal rectification. A spatial gating mechanism then dynamically reconciles these macro-environmental and micro-signal features. Extensive experiments on M3FD, LLVIP, and DroneVehicle demonstrate the effectiveness of BDPNet. Compared with state-of-the-art methods, BDPNet improves mAP50–95 by 0.8% and 1.0% on M3FD and LLVIP, respectively, and improves mAP50 by 0.6% on DroneVehicle, while using substantially fewer parameters and lower computational cost. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
