US 11,928,802 B2
Apparatus for acquiring depth image, method for fusing depth images, and terminal device
Xiage Qin, Shenzhen (CN)
Assigned to SHENZHEN GOODIX TECHNOLOGY CO., LTD., Shenzhen (CN)
Filed by SHENZHEN GOODIX TECHNOLOGY CO., LTD., Shenzhen (CN)
Filed on Jul. 8, 2022, as Appl. No. 17/860,579.
Application 17/860,579 is a continuation of application No. PCT/CN2021/111293, filed on Aug. 6, 2021.
Prior Publication US 2023/0042846 A1, Feb. 9, 2023
Int. Cl. G06T 5/50 (2006.01); G01S 17/48 (2006.01); G01S 17/86 (2020.01); G01S 17/894 (2020.01); G06T 7/30 (2017.01); G06T 7/521 (2017.01); H04N 23/56 (2023.01)
CPC G06T 5/50 (2013.01) [G01S 17/48 (2013.01); G01S 17/86 (2020.01); G01S 17/894 (2020.01); G06T 7/30 (2017.01); G06T 7/521 (2017.01); H04N 23/56 (2023.01); G06T 2207/10024 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20221 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus for acquiring a depth image, comprising:
an emitting module configured to emit a speckle array to an object, wherein the speckle array comprises p number of mutually spaced apart speckles;
a receiving module comprising an image sensor, the image sensor comprising a sensor array, the sensor array comprising m*n pixel units, wherein each of the pixel units comprises a Complementary Metal Oxide Semiconductor (CMOS) photodiode and a photoelectric signal reading circuit, the photodiode is configured to receive the speckle array reflected by the object, and generate a corresponding photocurrent signal based on the speckle array, a current intensity indicated by the photocurrent signal is positively correlated with a light intensity of light beam irradiation received by the photodiode, and the photoelectric signal reading circuit is configured to read the photocurrent signal and output a corresponding pixel signal; and
a processing unit configured to receive the pixel signal and generate a sparse depth image based on the pixel signal, the p speckles indicating a resolution of the sparse depth image, wherein the processing unit is further configured to align an RGB image having a resolution of a*b with the sparse depth image, and fuse the aligned sparse depth image with the RGB image using a pre-trained image fusion model to obtain a dense depth image, wherein the RGB image is a two-dimensional image acquired by an RGB camera with a and b being numbers of pixels in the two dimensions of the RGB image respectively, and the dense depth image has a resolution of a*b.