基于跨模式信息瓶和最小冗余转换的红外可见聚变多式物体检测算法的研究
Weiyan Tan1, Bing Geng2, XiuGuang Bai2
1Guangdong Provincial Veterans Service Center, GuangDong, China. weiyantan2025@outlook.com.
Scientific reports
|March 11, 2026
概括
这项研究引入了一种新的多式物体检测框架,通过减少红外和可见光传感器之间的冗余信息,提高在具有挑战性的环境中的性能. 该方法增强了跨模式的一致性和边界检测,以实现更强大的对象识别.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 传感器融合式传感器
背景情况:
- 多模式物体检测对于在复杂的环境中导航至关重要.
- 现有的方法在模态冗余性和特征不对齐方面扎.
研究的目的:
- 开发一种新的多式联通融合检测框架.
- 解决模式冗余性抑制和特征对齐方面的局限性.
主要方法:
- 提出了一个整合跨模式信息瓶 (CIB) 和最小冗余转换 (MRT) 的框架.
- 对于共享的语义,CIB使用了压缩-分解-重建路径.
- MRT应用稀疏的转换来减少冗余并增强边界意识.
- 实施了双阶段培训策略 (模式隔离和融合).
主要成果:
- 在KAIST夜间场景上,mAP的改进从42.8%提高到44.1%.
- 在LLVIP低光条件下实现了80.0%AP@75,超过了最先进的2.4%.
- 证明了对阻塞和照明变化的稳定性.
结论:
- 拟议的框架有效地抑制了模式冗余性,并调整了特征.
- 这种方法显示出在不利条件下可靠的多式联运感知有很大的潜力.
相关概念视频
01:03IR Frequency Region: Fingerprint Region
2.2K
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
2.2K
01:09Infrared (IR) Spectroscopy: Overview
6.4K
When electromagnetic radiation passes through a material, atoms or molecules transition from a lower to a higher energy state by absorbing radiation corresponding to the energy difference between the two states. The absorption of infrared (IR) radiation causes transitions between vibrational energy levels in a molecule. Therefore, IR spectroscopy is a useful analytical tool for determining the molecular structure of molecules.
Different compounds display unique properties due to their...
Different compounds display unique properties due to their...
6.4K