Abstract: Multimodal object detection plays a crucial role in all-weather and multi-scene applications of aerial imagery. Existing studies mainly focus on multimodal fusion and inter-level feature ...
Official Code for Misaligned RGB-Infrared Object Detection via Adaptive Dual-discrepancy Calibration. @Article{rs15194887, AUTHOR = {He, Mingzhou and Wu, Qingbo and Ngan, King Ngi and Jiang, Feng and ...
Abstract: Thermal infrared object detection has been widely used in autonomous driving and safety monitoring, and modern deep learning techniques together with the availability of massive labeled data ...
DMFusion is a YOLOv8-based dual-branch object detection architecture for infrared–visible imagery that performs progressive, difference-aware fusion via a Feature Complementary Mapping Module (FCM) ...