Article searching method combined with depth information

The invention belongs to the technical field of intelligent article searching and positioning, and relates to an article searching method combining depth information. The method comprises the following process steps: S1, training an article detection model by adopting an article detection algorithm, then positioning a target area in a video image, and predicting a corresponding category; S2, performing video image acquisition by using a binocular camera; obtaining depth map information of a target in the video through a binocular camera, and determining a real distance between the target and the camera; s3, performing image acquisition according to a planned path when the object is searched, processing the acquired image to predict the category of the target, calculating the real distancebetween the target and the camera, and informing a user of the specific position of the target in a voice broadcast mode after verifying that the category of the target is consistent. According to themethod, background interf