Pedestrian tracking method and device, computer equipment and storage medium

[0025] Example 1

[0026] figure 1 This is a flowchart of a pedestrian tracking method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation where the indoor navigation robot actively follows in real time. The method of this embodiment may be executed by a pedestrian tracking device, and the device may be implemented by means of software and / or hardware, and the device may be configured in a server.

[0027] Correspondingly, the method specifically includes the following steps:

[0028] S110. If it is determined that the indoor navigation robot and the target pedestrian have established a following navigation relationship, each time the tracking time point is reached, a detection and collection image is acquired through an indoor environment camera.

[0029] The following navigation relationship may be an initial image of the target pedestrian collected by the indoor navigation robot, and a task relationship is established with the

[0055] Embodiment 2

[0056] Figure 2a This is a flowchart of another indoor robot navigation control method provided in Embodiment 2 of the present invention. This embodiment is refined on the basis of the above-mentioned embodiments, and calculates the first fusion comparison feature corresponding to each detection target and the corresponding navigation route according to the pedestrian image collected by the indoor navigation robot for the target pedestrian and the set following navigation route. Track the second fusion comparison feature corresponding to the predicted target for further refinement, refer to Figure 2a , the method specifically includes the following steps:

[0057] S210. If it is determined that the indoor navigation robot and the target pedestrian have established a following navigation relationship, each time the tracking time point is reached, an indoor environment camera is used to acquire a detection and acquisition image.

[0058] S220: Identify at

[0078] Embodiment 3

[0079] image 3 This is a flowchart of another indoor robot navigation control method provided in Embodiment 3 of the present invention. This embodiment is refined on the basis of the above-mentioned embodiments, and further refines the identification of the target pedestrian in the detection target according to the similarity between the first fusion comparison feature and the second fusion comparison feature. Refer to image 3 , the method specifically includes the following steps:

[0080] S310. If it is determined that the indoor navigation robot and the target pedestrian have established a following navigation relationship, each time the tracking time point is reached, a detection and acquisition image is acquired through an indoor environment camera.

[0081] S320: Identify at least one detection target in the detection and acquisition image, and identify a tracking prediction target for the target pedestrian in the detection and acquisition image.