转载请注明出处
Apple原文地址: https://developer.apple.com/documentation/arkit/understanding_augmented_reality

Article

Understanding Augmented Reality

• Discover concepts, features, and best practices for building great AR experiences.

• 探索 AR 的概念、特性，以及了解构建优秀 AR 场景的最佳实践。

Overview

image.png

• The basic requirement for any AR experience—and the defining feature of ARKit—is the ability to create and track a correspondence between the real-world space the user inhabits and a virtual space where you can model visual content. When your app displays that content together with a live camera image, the user experiences augmented reality: the illusion that your virtual content is part of the real world.

• 对于所有的 AR 场景而言，最基本要求是：创建并追踪现实空间和虚拟空间之间的关系，其中，现实空间是用户所处的世界，虚拟空间是可对可视化内容进行建模的世界，这同时也是 ARKit 的基本特征。当您的应用将这些虚拟内容与实时视频结合，并一起显示的时候，用户就可以体验到所谓的「增强现实」：您的虚拟内容成为了真实世界的一部分，尽管这只是「错觉」而已。

How World Tracking Works

• To create a correspondence between real and virtual spaces, ARKit uses a technique called visual-inertial odometry. This process combines information from the iOS device’s motion sensing hardware with computer vision analysis of the scene visible to the device’s camera. ARKit recognizes notable features in the scene image, tracks differences in the positions of those features across video frames, and compares that information with motion sensing data. The result is a high-precision model of the device’s position and motion.

• 为了在现实世界和虚拟世界之间建立对应关系，ARKit 使用了一种被称为视觉惯性里程计的技术。这项技术会将 iOS 设备的动作感测硬件信息，加上对可见场景的计算机视觉分析功能，然后与设备的摄像头相结合。ARKit 将会去识别场景图像当中的显著特征，然后在视频帧中追踪这些特征位置的距离，然后再将这些信息与动作感测数据进行比较。从而生成具备设备位置和动作特征的高精度模型。

• World tracking also analyzes and understands the contents of a scene. Use hit-testing methods (see the ARHitTestResult
  class) to find real-world surfaces corresponding to a point in the camera image. If you enable the planeDetection
  setting in your session configuration, ARKit detects flat surfaces in the camera image and reports their position and sizes. You can use hit-test results or detected planes to place or interact with virtual content in your scene.

• 全局追踪 (World Tracking) 同样也可以分析和识别场景当中的内容。通过使用点击测试 (hit-testing) 方法（参见 ARHitTestResult类），从而找到与相机图像中的某个点所对应的真实世界面。如果您在 Session (会话) 配置当中启用了 planeDetection配置的话，那么 ARKit 就会去检测相机图像当中的水平面，并报告其位置和大小。您可以使用点击测试所生成的结果，或者使用所检测到的水平面，从而就可以在场景当中放置虚拟内容，或者与之进行交互。

Best Practices and Limitations

• World tracking is an inexact science. This process can often produce impressive accuracy, leading to realistic AR experiences. However, it relies on details of the device’s physical environment that are not always consistent or are difficult to measure in real time without some degree of error. To build high-quality AR experiences, be aware of these caveats and tips.

• 全局追踪是一项不精确的科学 (inexact science)。尽管在这个过程当中，经常会产生可观的准确度，从而让 AR 的体验更加真实。然而，它严重依赖于设备物理环境的相关细节，而这些细节并不总是一致，有些时候也难以实时测量，这也就导致这些物理细节往往都会存在某种程度的错误。要建立高品质的 AR 体验，那么请注意下述这些注意事项和提示：

• **Design AR experiences for predictable lighting conditions. **World tracking involves image analysis, which requires a clear image. Tracking quality is reduced when the camera can’t see details, such as when the camera is pointed at a blank wall or the scene is too dark.

• 基于可见的照明条件来设计 AR 场景。全局追踪涉及到了图像分析的相关内容，因此就需要我们提供清晰的图像。如果摄像头没有办法看到相关的物理细节，比如说摄像头拍到的是一面空空如也的墙壁，或者场景的光线实在太暗的话，那么全局追踪的质量就会大大降低。

• Use tracking quality information to provide user feedback World tracking correlates image analysis with device motion. ARKit develops a better understanding of the scene if the device is moving, even if the device moves only subtly. Excessive motion—too far, too fast, or shaking too vigorously—results in a blurred image or too much distance for tracking features between video frames, reducing tracking quality. The ARCamera
  class provides tracking state reason information, which you can use to develop UI that tells a user how to resolve low-quality tracking situations.
• 根据追踪质量的相关信息来给用户进行反馈提示。全局追踪会将图像分析与设备的动作模式关联起来。如果设备正在移动的话，那么 ARKit 就可以更好地对场景进行建模，这样即便设备只是略微晃动，也不会影响追踪质量。但是一旦用户的动作过多、过快或者晃动过于激烈，就会导致图像变得模糊，或者导致视频帧中要追踪的特征之间的距离过大，从而致使追踪质量的降低。ARCamera类能够提供追踪状态，此外还能提供导致该状态出现的相关原因，您可以在 UI 上展示这些信息，告诉用户如何解决追踪质量低这个问题。

• Allow time for plane detection to produce clear results, and disable plane detection when you have the results you need. Plane detection results vary over time—when a plane is first detected, its position and extent may be inaccurate. As the plane remains in the scene over time, ARKit refines its estimate of position and extent. When a large flat surface is in the scene, ARKit may continue changing the plane anchor’s position, extent, and transform after you’ve already used the plane to place content.
• 给水平面检测预留点时间来生成清晰的结果，一旦您获得所需的结果后，就禁用水平面检测。一开始对水平面进行检测的时候，所检测到的水平面位置和范围很可能不准确。不过随着时间的推移，只要水平面仍然保持在场景当中，那么 ARKit 就能够较为精确地估计水平面的位置和范围。当场景中有一个比较大的平坦表面的话，就算您已经使用过这个水平面来放置内容，那么ARKit 可能还会继续对水平面的锚点位置、范围和变换点进行修正。