基于深度学习的红外望远镜的对抗性强大和可普遍化的立体声匹配
Bowen Liu1, Jiawei Ji1, Cancan Tao1
1School of Automation Science and Electrical Engineering, Beihang University, 37 Xueyuan Road, Haidian District, Beijing 100191, China.
Journal of imaging
|November 26, 2024
概括
这项研究引入了一种新的深度学习方法,用于使用红外和可见光图像进行立体匹配. 这种方法提高了稳定性和通用性,而不需要大型数据集,在具有挑战性的条件下提高了准确性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 机器人技术 机器人技术 机器人技术
背景情况:
- 深度学习在立体匹配方面表现出色,但在概括性和稳定性方面扎,特别是在红外 (IR) 纹理和遮方面.
- 现有的方法通常需要大量的红外数据集,并且缺乏适应不同红外摄像机的适应性.
研究的目的:
- 开发一种基于深度学习的新型深度优化方法,用于立体匹配.
- 为了提高各种成像条件和数据集的稳定性和通用性.
- 调查红外纹理在深度学习立体相匹配中的实用性.
主要方法:
- 使用多尺度人口普查转换计算匹配成本量.
- 在立体声匹配任务中使用堆叠的沙漏子网络.
- 在没有大型数据集的情况下,适应红外和标准双眼镜图像的方法.
主要成果:
- 在保持精度的同时,在对抗性强度方面取得了实质性的改进.
- 与自动驾驶数据集的最先进方法相比,减少了近一半的终点误差 (EPE).
- 从模拟到现实世界数据集的优越泛化证明,没有微调.
结论:
- 拟议的方法为立体声匹配提供了强大而适应性的解决方案,在各种条件和成像类型中有效.
- 红外纹理对于深度学习框架中的立体匹配仍然很有价值,即使在具有挑战性的照明环境中也是如此.
- 这种方法显著提升了对自动驾驶等应用的立体声匹配能力.
相关概念视频
Depth Perception and Spatial Vision
568
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
568
Deconvolution
132
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
132


