US 11,843,858 B1
Machine learning for phase detection autofocus
Wen-Chun Feng, New Taipei (TW); Jian-Jia Su, Changhua (TW); and Hui Shan Kao, New Taipei (TW)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on May 19, 2022, as Appl. No. 17/664,142.
Int. Cl. H04N 23/67 (2023.01); H04N 23/45 (2023.01); H04N 23/60 (2023.01)
CPC H04N 23/672 (2023.01) [H04N 23/45 (2023.01); H04N 23/64 (2023.01)] 23 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving first image data of a first scene from a first image sensor of a first camera, the first image data comprising phase shift information and a representation of the first scene;
determining a characteristic of the first scene based on the first image data, wherein the characteristic of the first scene comprises at least one of a repeating pattern scene, a multi-depth scene, or a low-light scene;
determining a first focal distance for the first scene based on a machine learning algorithm by inputting the phase shift information to the machine learning algorithm;
configuring the machine learning algorithm based on the characteristic of the first scene, wherein the configuring comprises loading a plurality of weights based on the characteristic of the first scene; and
controlling a focal position of the first camera based on the first focal distance.