白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Techniques for determining settings for a content capture device

專利號
US11968456B2
公開日期
2024-04-23
申請人
Magic Leap, Inc.（US FL Plantation）
發(fā)明人
Brian Keith Smith; Ilya Tsunaev
IPC分類
H04N23/72; H04N5/222; H04N5/265; H04N23/63; H04N23/71; H04N23/73; H04N23/741; H04N23/743; H04N23/76
技術(shù)領域
luma,pixel,image,may,in,be,aec,examples,object,weight
地域： FL FL Plantation

摘要

A method for computing a total weight array includes receiving an image frame captured by a content capture device and identifying a plurality of objects in the image frame. Each object of the plurality of objects corresponds to one of a plurality of pixel groups. The method also includes providing a plurality of neural networks and calculating, for each object of the plurality of objects, an object weight using a corresponding neural network of the plurality of neural networks. The method further includes computing the total weight array by summing the object weight for each of the plurality of objects.

說明書

The single value may be applied to all of the pixel groups of the object (as shown in the total weight array 1080). To illustrate in an equation, a total weight array, wT, may be a summation of the outputs from each object's neural network, for example:

w T [ r , c ] = ∑ i = 0 N o w i [ r , c ]
where No is the number of objects.

After the total weight array 1080 is generated, the total weight array 1080 may be compared to a target as described above with reference to FIG. 1. In addition, using the weighted luma average equation described above in regards to FIG. 1, a specific weight may be disabled for the second weighting model by setting an array associated with the weight to zero.

FIG. 11 is a flowchart illustrating an embodiment of a process 1100 for automatic exposure control (AEC) using a second weighting model. In some aspects, the process 1100 may be performed by a computing device.

權(quán)利要求

1
微信群二維碼
意見反饋