用于视频和全息投影的深度键合成

• Format: Patent
• Language: Chinese
• Published: 20.08.2019
• Subjects: ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PICTORIAL COMMUNICATION, e.g. TELEVISION

根据本文的实施例，深度键合成是利用基于深度的数学函数检测数字图像中的特定所需部分/对象的过程，以便于将这些特定部分/对象分隔用于进一步处理。在一个具体实施例中，从视频捕捉设备捕捉数字视觉图像，并且确定该数字视觉图像内的一个或多个对象，这些对象在视频捕捉设备的特定深度范围内。由此，可以将一个或多个对象从不在特定深度范围内的数字视觉图像的部分分离开来，并且处理该一个或多个被分离的对象以脱离数字视觉图像的、不在特定深度范围内的部分进行视觉显示。并且，在某些实施例中，数字图像的被检测的部分(被分离的部分)可以与另一图像层叠，例如用于电影制作，或者被用于全息投影。 According to embodiments herein, depth key compositing is the process of detecting specific desired portions/objects of a digital image using mathematical functions based on depth, in order to separate those specific portions/objects for further processing. In one particular embodiment, a digital visual image is captured from a video capture device, and one or more objects are determined within the digital visual image that are within a particular depth range of the video capture device. From there, the one or more objects may be isolated from portions of the digital visual image not within the particular depth range, and the isolated objects are processed for visual display apart from the portions of the digital visual image not wit