Misaligned visible-thermal object detection: A drone-based benchmark and baseline

Multispectral object detection has achieved remarkable results due to its ability to fuse information from visible and thermal modalities in recent years. However, the existing visible-thermal datasets are constructed based on manually aligned image pairs, which cannot fully represent the challenges...

Full description

Saved in:
Bibliographic Details
Main Authors: Kechen Song, Xiaotong Xue, Hongwei Wen, Yingying Ji, Yunhui Yan, Qinggang Meng
Format: Default Article
Published: 2024
Subjects:
Automotive engineering
Control engineering, mechatronics and robotics
Computer vision and multimedia computation
Multispectral object detection
Visible-thermal dataset
Cross-modal alignment
Feature alignment
Online Access:https://hdl.handle.net/2134/26060668.v1
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://hdl.handle.net/2134/26060668.v1

Similar Items