IAF-RTDETR: Illumination Evaluation-Driven Multimodal Object Detection Network for Infrared–Visible Dual-Source Fusion

计算机科学 稳健性(进化) 融合 人工智能 RGB颜色模型 推论 计算机视觉 可视化 目标检测 模式识别(心理学) 图像融合 特征(语言学) 传感器融合 管道(软件) 融合机制 分割 估计员 特征提取 一致性(知识库) 人工神经网络 深度学习 融合规则 曲线波变换
作者
Qi Hu,Haiyan Yu,Zhiquan Zhou,Siqi Li
出处
期刊:Electronics [Multidisciplinary Digital Publishing Institute]
卷期号:15 (6): 1332-1332
标识
DOI:10.3390/electronics15061332
摘要

Infrared–visible multimodal object detection has attracted increasing attention for its robustness under challenging conditions such as low illumination, occlusion, and complex backgrounds. However, existing fusion methods often suffer from coarse illumination modeling and insufficient cross-modal semantic alignment, leading to performance degradation in scenes with strong illumination variations or modality imbalance. To address these issues, this paper proposes IAF-RTDETR (Illumination-Aware Fusion RT-DETR), an illumination-aware fusion real-time detection network built upon the RT-DETR framework. The proposed method introduces a progressive fusion pipeline composed of four key modules: (1) a Modality-Specific Feature Enhancer to recalibrate modality-dependent representations and suppress low-quality feature interference; (2) a lightweight Global Light Estimator that learns a continuous illumination score via self-supervised proxy supervision derived from RGB image statistics; (3) a Light-Aware Fusion module that dynamically adjusts multi-scale fusion weights of infrared and visible features according to the estimated illumination; and (4) a Cross-Layer Dual-Branch Interaction Module that alleviates cross-modal semantic shift through bidirectional attention-guided interaction and channel reweighting. Extensive experiments on the M3FD dataset demonstrate that the proposed method achieves consistent performance improvements under diverse lighting conditions, outperforming RGB-only and IR-only baselines by 7.4% and 16.1% in mAP@50, respectively, while maintaining real-time inference speed (≈17.3 ms). Further evaluations on the LLVIP dataset validate the robustness and generalization ability of IAF-RTDETR in real low-illumination scenarios. Moreover, compared with representative multimodal fusion methods such as TFDet and TarDAL, the proposed method achieves superior detection accuracy. Visualization and quantitative semantic consistency analyses further confirm the effectiveness of the proposed illumination-aware fusion and cross-layer interaction mechanisms. These results indicate that IAF-RTDETR provides an effective and practical solution for real-time infrared–visible object detection under complex lighting environments.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
热爱胃肠的小赖完成签到,获得积分10
1秒前
慕青的应助被nwy采纳,获得10
1秒前
Zhang完成签到,获得积分10
1秒前
Hu完成签到,获得积分10
3秒前
3秒前
369ninja发布了新的文献求助10
4秒前
4秒前
小小牛马完成签到 ,获得积分10
4秒前
拂晓倩影发布了新的文献求助30
4秒前
小狗不能吃巧克力完成签到,获得积分10
5秒前
kmkk关注了科研通微信公众号
5秒前
6秒前
秋风的应助被苗英采纳,获得10
6秒前
zhang完成签到,获得积分10
6秒前
6秒前
_xiepang发布了新的文献求助10
6秒前
秋风的应助被明亮的迎松采纳,获得10
8秒前
8秒前
9秒前
9秒前
公爵发布了新的文献求助10
9秒前
Yuan88发布了新的文献求助10
10秒前
沉舟发布了新的文献求助10
10秒前
小蘑菇的应助被不晓得先生采纳,获得10
10秒前
霜风款冬发布了新的文献求助10
12秒前
是why耶完成签到 ,获得积分10
12秒前
隐形曼青的应助被风吹麦浪采纳,获得10
13秒前
Maestro_S的应助被风吹麦浪采纳,获得20
13秒前
13秒前
13秒前
自觉千凝发布了新的文献求助10
14秒前
Akim的应助被yjt采纳,获得10
14秒前
ding的应助被山海不远采纳,获得10
14秒前
14秒前
14秒前
15秒前
斯文败类的应助被sun采纳,获得10
16秒前
16秒前
17秒前
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184220
求助须知:如何正确求助?哪些是违规求助? 9573266
关于积分的说明 21830447
捐赠科研通 7781246
什么是DOI,文献DOI怎么找? 3434248
关于科研通互助平台的介绍 2558373
邀请新用户注册赠送积分活动 2480784