LMDENet:一种轻量级的RGB-IR物体检测网络,用于低光远程传感图像
1School of Computer Science and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China.
Sensors (Basel, Switzerland)
|February 27, 2026
概括
这项研究引入了一个用于RGB红外物体检测的轻量级网络,通过解决跨模态差异来改善在具有挑战性的条件下的感知. 拟议的方法提高了准确性,同时保持了效率.
科学领域:
- 计算机视觉 计算机视觉
- 遥感 遥感 遥感 遥感
- 机器学习 机器学习
背景情况:
- RGB红外 (RGB-IR) 对象检测增强了感知,特别是在不利的条件下,如低照明和雾.
- 现有的方法面临着内部模式和跨模式差异的挑战,导致复杂的架构和低于最佳的融合.
- 双分支网络中的静态融合范式难以表征模式差异,阻碍了互补信息挖掘.
研究的目的:
- 开发一个轻量级的RGB-IR多模式检测网络 (LMDENet),有效地解决跨模式差异.
- 改进RGB和IR模式之间的互补信息的挖掘,以增强对象检测.
- 为了在检测准确度和计算效率之间取得有利的平衡.
主要方法:
- 引入了以照明为导向的标签选择 (IGLS) 以实现一致的RGB和IR标签集成.
- 提出了一个异质的骨干网络 (HBN),用于模式特定的表示学习,具有差异化的分支.
- 开发了一个差异补充增强模块 (DCEM) 来分解和选择性增强跨模式特征.
主要成果:
- 在无人机车辆数据集上,LMDENet实现了78.9%的mAP@0.5,在LLVIP数据集上实现了93.6%的mAP@0.5.
- 该模型在不同场景中表现出强大的概括能力.
- LMDENet仅用3.3M个参数和8.7G个FLOP实现了这些结果.
结论:
- 拟议的LMDENet有效地克服了现有的RGB-IR物体检测方法的局限性.
- 该网络实现了卓越的准确性-效率平衡,使其适合于现实世界的应用.
- 该研究强调了明确不一致性表征和选择性增强对多式联的重要性.
相关概念视频
02:16Light Acquisition
9.7K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.7K
01:09Infrared (IR) Spectroscopy: Overview
5.6K
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...
5.6K
01:05Difference from Background: Limit of Detection
8.6K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.6K
01:25IR Spectrometers
2.8K
There are two main infrared (IR) spectrophotometers: dispersive IR spectrometers and Fourier transform infrared (FTIR) spectrometers. In a dispersive IR spectrometer, a beam of infrared radiation produced by a hot wire is divided into two parallel equal-intensity beams using mirrors. One beam passes through the sample, while another is a reference beam. The beams then move through the monochromator, which separates the radiations into a continuous spectrum of different frequencies. The...
2.8K