TY - JOUR
T1 - COXNet
T2 - Cross-Layer Fusion With Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
AU - Peng, Peiran
AU - Xu, Tingfa
AU - Song, Liqiang
AU - Zhu, Mengqi
AU - Fang, Yuqiang
AU - Li, Jianan
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2026/1
Y1 - 2026/1
N2 - 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.
AB - 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.
KW - RGBT imagery
KW - multimodal fusion
KW - spatial misalignment correction
KW - tiny object detection
UR - https://www.scopus.com/pages/publications/105013057407
U2 - 10.1109/TCSVT.2025.3595147
DO - 10.1109/TCSVT.2025.3595147
M3 - Article
AN - SCOPUS:105013057407
SN - 1051-8215
VL - 36
SP - 596
EP - 608
JO - IEEE Transactions on Circuits and Systems for Video Technology
JF - IEEE Transactions on Circuits and Systems for Video Technology
IS - 1
ER -