Object tracking method and device

摘要

Disclosed is an object tracking method. The method includes steps of obtaining a first boundary region of a waiting-for-recognition object in the disparity map related to the current frame; calculating a probability of each valid pixel in the first boundary region so as to get a pixel probability map of the waiting-for-recognition object; obtaining historic tracking data of each tracked object, which includes identifier information of the tracked object and a pixel probability map related to each of one or more prior frame related disparity maps prior to the disparity map related to the current frame; determining identifier information of the waiting-for-recognition object, and updating the pixel probability map of the waiting-for-recognition object; and updating, based on the updated pixel probability map of the waiting-for-recognition object, the first boundary region of the waiting-for-recognition object, so as to get a second boundary region of the waiting-for-recognition object.

主权项

1. A method of tracking plural some-type objects based on continuous disparity maps, comprising:
a step of obtaining a first boundary region of a waiting-for-recognition object, which is detected from a disparity map related to current frame, in the disparity map related to the current frame; a step of calculating a probability of each valid pixel in the first boundary region of the waiting-for-recognition object belonging to a pixel for forming the waiting-for-recognition object, so as to obtain a pixel probability map of the waiting-for-recognition object; a step of obtaining historic tracking data of each tracked object, which includes identifier information of the tracked object and a pixel probability map related to each of one or more prior frame related disparity maps prior to the disparity map related to the current frame; a step of determining, based on matching of the pixel probability map of the waiting-for-recognition object and each of one or more pixel probability maps of each tracked object, identifier information of the waiting-for-recognition object, and updating the pixel probability map of the waiting-for-recognition object; and a step of updating, based on the updated pixel probability map of the waiting-for-recognition object, the first boundary region of the waiting-for-recognition object, so as to obtain a second boundary region of the waiting-for-recognition object.