相关实验视频
Updated: Apr 10, 2026
11:23
Lensless Fluorescent Microscopy on a Chip
Published on: August 17, 2011
18.4K
Squeeze-EnGAN:用于智能汽车的内存高效和无监督的低光图像增强
Haegyo In1, Juhum Kweon2, Changjoo Moon1
1Department of Smart Vehicle Engineering, Konkuk University, Seoul 05029, Republic of Korea.
Sensors (Basel, Switzerland)
|April 28, 2025
概括
这项研究介绍了Squeeze-EnGAN,这是一种新的深度学习方法,用于增强没有配对数据的低光图像. 该模型改进了智能汽车对象检测,提供实时性能和效率.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 智能运输系统 智能运输系统
背景情况:
- 自动驾驶汽车依赖于像RGB摄像头这样的传感器,这些传感器在低光下表现不佳.
- 现有的低光图像增强 (LLIE) 方法通常是昂贵的或与道路场景作斗争.
- 监督的LLIE方法需要配对的数据集,这对于驾驶场景来说很难获得.
研究的目的:
- 为智能汽车开发一种高效的,无监督的LLIE方法.
- 解决现有的LLIE模型在适应道路场景和缺少配对数据集方面的局限性.
主要方法:
- 提出Squeeze-EnGAN,一种基于生成对抗网络 (GAN) 的LLIE方法.
- 将消防模块纳入U-net架构,以减少参数和计算成本.
- 利用无监督学习方法,消除了对照低光和正常光数据集的需要.
主要成果:
- 与Enlighten.GAN相比,Squeeze-EnGAN显示出显著的内存效率,并减少了多重积累操作 (MAC).
- 在Jetson Xavier等嵌入式系统上实现实时性能.
- 来自Squeeze-EnGAN的增强图像提高了智能汽车对象检测的准确性.
结论:
- 在智能车辆中,Squeeze-EnGAN提供了一种有效和高效的解决方案,用于在低光下增强智能车辆的图像.
- 无监督方法克服了为驾驶场景获得配对数据集的挑战.
- 该模型提高对象检测的能力突出了其在增强自动驾驶系统方面的潜力.
相关概念视频
01:24Vision
52.2K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
52.2K
01:37Super-resolution Fluorescence Microscopy
6.7K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
6.7K