| CPC H04N 25/47 (2023.01) [G06T 7/248 (2017.01); G06T 7/579 (2017.01); H04N 23/695 (2023.01); G06T 2207/10028 (2013.01); G06T 2207/10152 (2013.01); G06T 2207/30204 (2013.01); G06T 2207/30241 (2013.01)] | 15 Claims |

|
1. A method for generating a depth image, comprising:
acquiring multiple event images of a target object captured by an event camera driven by an actuator during a motion cycle, each event image is provided with at least one first event point;
marking multiple target pixel points in a background image that have same positional information as each of the at least one first event point in the multiple event images, to obtain multiple second event points in the background image, the background image is pre-stored;
determining at least one event trajectory in the background image based on each of the multiple second event points;
calculating a depth value of each of the multiple second event points based on a motion range of the event camera during the motion cycle and a length of the at least one event trajectory to which each the second event point belongs; and
determining a pixel value of each of the multiple target pixel points based on the depth value of each of the multiple second event points in the background image, to generate a depth image of the target object.
|