COXNet: Cross-Layer Fusion With Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
IEEE Transactions on Circuits and Systems for Video Technology · 2026-01 · 36 (1) · 596-608
DOI: 10.1109/tcsvt.2025.3595147 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-01. Verfasst von Peiran Peng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Natural Science Foundation of Chongqing Municipality.
Abstract (Originalsprache)
Detecting tiny objects in multimodal Red-Green-Blue-Thermal (RGBT) imagery is a critical challenge in computer vision, particularly in surveillance, search and rescue, and autonomous navigation. Drone-based scenarios exacerbate these challenges due to spatial misalignment, low-light conditions, occlusion, and cluttered backgrounds. Current methods struggle to leverage the complementary information between visible and thermal modalities effectively. We propose COXNet, a novel framework for RGBT tiny object detection, addressing these issues through three core innovations: i) the Cross-Layer Fusion Module, fusing high-level visible and low-level thermal features for enhanced semantic and spatial accuracy; ii) the Dynamic Alignment and Scale Refinement module, correcting cross-modal spatial misalignments and preserving multi-scale features; and iii) an optimized label assignment strategy using the GeoShape Similarity Measure for better localization. COXNet achieves a 3.32% mAP50 improvement on the RGBTDronePerson dataset over state-of-the-art methods, demonstrating its effectiveness for robust detection in complex environments.
Förderung
- Natural Science Foundation of Chongqing Municipality
Zitieren
APA
Peng, P., Xu, T., Song, L., Zhu, M., Fang, Y., & Li, J. (2026). COXNet: Cross-Layer Fusion With Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(1), 596-608. https://doi.org/10.1109/tcsvt.2025.3595147
Vancouver
Peng P, Xu T, Song L, Zhu M, Fang Y, Li J. COXNet: Cross-Layer Fusion With Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(1):596-608. doi:10.1109/tcsvt.2025.3595147
BibTeX
@article{Peng2026,
author = {Peng, Peiran and Xu, Tingfa and Song, Liqiang and Zhu, Mengqi and Fang, Yuqiang and Li, Jianan},
title = {COXNet: Cross-Layer Fusion With Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {1},
pages = {596--608},
doi = {10.1109/tcsvt.2025.3595147}
}
EUVIMED