具有事件摄像头的低延迟汽车视觉
Daniel Gehrig1, Davide Scaramuzza2
1Robotics and Perception Group, University of Zurich, Zurich, Switzerland. dgehrig@ifi.uzh.ch.
Nature
|May 29, 2024
概括
本研究引入使用事件和RGB摄像头的混合物探测器. 这种方法可以显著降低高级驾驶辅助系统的延迟和带宽,而不会损害准确性.
科学领域:
- 计算机视觉
- 机器人技术
- 传感器融合
背景情况:
- 目前的高级驾驶辅助系统 (ADAS) 依赖于RGB摄像头,面临带宽延迟权衡.
- 事件摄像机提供高时间分辨率和稀疏性,减少带宽和延迟.
- 现有的事件摄像机算法难以与基于图像的系统相匹配,
研究的目的:
- 开发一个混合物体检测系统, 结合事件和基于的摄像头.
- 克服当前事件摄像机算法的准确性-效率权衡.
- 利用事件和RGB摄像机的优势来改善ADAS感知.
主要方法:
- 提出了一个混合物探测器,集成事件和RGB摄像头数据.
- 利用高时间分辨率和事件数据的稀疏性.
- 使用标准图像中的丰富,低时间分辨率的信息.
主要成果:
- 通过降低感知和计算延迟实现了高速物体检测.
- 证明一个20fps的RGB摄像头加上一个事件摄像头匹配5000fps的摄像头延迟.
- 保持与具有显著较低带宽 (45 fps) 的高率系统可比的精度.
结论:
- 混合方法有效地结合了事件和基于框架的视觉的好处.
- 这种方法为ADAS的感知提供了高效和强大的解决方案.
- 释放事件摄像机的潜力,提供实时,高性能的驾驶辅助.
相关概念视频
01:24Vision
48.6K
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.
48.6K
02:16Light Acquisition
8.0K
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.
8.0K
01:10Torque
18.5K
Torque is an important quantity for describing the dynamics of a rotating rigid body. We see the application of torque in many ways in the world, such as when pressing the accelerator in a car, which causes the engine to apply additional torque on the drivetrain. Here, we define torque and provide a framework to create an equation to calculate torque for a rigid body with fixed-axis rotation.
Torque can be considered as the rotational counterpart to force. Since forces change the translational...
Torque can be considered as the rotational counterpart to force. Since forces change the translational...
18.5K
01:15Depth Perception and Spatial Vision
2.7K
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.
2.7K