Automatic tracking shopping cart

Patent metadata

Field	Value
Publication number	US-10394247-B2
Application number	US-201715552158-A
Country	US
Kind code	B2
Filing date	Apr 5, 2017
Priority date	Nov 17, 2016
Publication date	Aug 27, 2019
Grant date	Aug 27, 2019

Abstract

The present disclosure provides an automatic tracking shopping cart. The automatic tracking shopping cart comprises an automatic tracking device. The automatic tracking device is fixed to a body of the shopping cart, operative to control movement of the shopping cart for tracking a target object. The automatic tracking device comprises: an image collection unit configured to collect a color image and a depth image of a field of image; a processing unit configured to identify the target object based on the collected color image and depth image, and determine a motion parameter of the shopping cart based on a position and/or movement of the target object; and a shopping cart driving unit configured to drive the shopping cart to move based on the determined motion parameter. A method for automatically controlling movement of a shopping cart to track a target object is also provided.

First claim

We claim:

1. An automatic tracking shopping cart, comprising:
an automatic tracking device fixed to a body of the shopping cart, and operative to control movement of the shopping cart for tracking a target object, the automatic tracking device comprising:
an image collection unit configured to collect a color image and a depth image of a field of view;
a processing unit configured to identify the target object based on the collected color image and depth image, and determine a motion parameter of the shopping cart based on a position and/or movement of the target object; and
a shopping cart driving unit configured to drive the shopping cart to move based on the determined motion parameter,
wherein the processing unit comprises:
a target determination module configured to determine target characteristics of the target object in the color image and a target depth of the target object in the depth image based on the collected color image and depth image;
an image analysis module configured to determine a current depth of the target object from a color image and a depth image of a current frame based on target characteristics and a target depth determined in a previous frame; and
a driving calculation module configured to determine the movement parameter of the shopping cart based on the calculated current depth.

2. The automatic tracking shopping cart according to claim 1 , wherein the automatic tracking shopping cart further comprises a console configured to receive an instruction input by a user, and
the target determination module is configured to determine a human target in the collected color image which is closest to the shopping cart as the target object based on the instruction received by the console indicating that a new target object needs to be determined.

3. The automatic tracking shopping cart according to claim 1 , wherein the target determination module is configured to take the current depth as a target depth for a next frame, when the image analysis module successfully determines the current depth of the target object from the color image and the depth image of the current frame.

4. The automatic tracking shopping cart according to claim 1 , wherein the target determination module is configured to re-determine a human target in the collected color image which has target characteristics best matching the target characteristics determined in the previous frame as the target object, when the image analysis module fails to determine the current depth of the target object from the color image and the depth image of the current frame.

5. The automatic tracking shopping cart according to claim 4 , wherein the target determination module is configured to
calculate a histogram of respective human targets in the currently collected color image;
match the histogram of the respective human targets with a histogram of a target object determined in the previous frame to determine matching values for the respective human targets; and
re-determine the human target which has the highest matching value higher than a reference matching value as the target object.

6. The automatic tracking shopping cart according to claim 1 , wherein the image analysis module is configured to:
calculate a background projection image based on the color image and the depth image of the current frame;
cut an image with a predetermined depth range out of the calculated background projection image based on the target depth;
perform expansion and average filtering processing on the image with the predetermined depth range; and
determine the current depth of the target object.

7. The automatic tracking shopping cart according to claim 1 , wherein the driving calculation module is configured to determine a current distance between the target object and the shopping cart based on the calculated current depth, and trigger the shopping cart driving unit to drive the shopping cart when the current distance is larger than a reference distance.

8. The automatic tracking shopping cart according to claim 1 , wherein the motion parameter comprises an average velocity v of the shopping cart in a next time period, the average velocity v being determined based on

v
=

Δ
⁢

⁢

l
2

-

Δ
⁢

⁢

l
1

+
L

T

,

wherein T is a duration of a time period, Δl 1 is a distance between the shopping cart and the target object at a start of a current time period, Δl 2 is a distance between the shopping cart and the target object at an end of the current time period, and L is a distance of the shopping cart moving within the current time period.

9. The automatic tracking shopping cart according to claim 1 , wherein the automatic tracking device further comprises a memory for storing the color image, the depth image, the target characteristics and/or the target depth.

10. An automatic tracking shopping cart, comprising:
an automatic tracking device fixed to a body of the shopping cart, and operative to control movement of the shopping cart for tracking a target object, the automatic tracking device comprising:
an image collection unit configured to collect a color image and a depth image of a field of view;
a processing unit configured to identify the target object based on the collected color image and depth image, and determine a motion parameter of the shopping cart based on a position and/or movement of the target object; and
a shopping cart driving unit configured to drive the shopping cart to move based on the determined motion parameter,
wherein the processing unit is configured to adjust a collection direction of the image collection unit if the processing unit fails to identify the target object, and the image collection unit re-collects the color image and the depth image.

11. The automatic tracking shopping cart according to claim 10 , wherein the automatic tracking device further comprises an alarming unit, and the target determination module is further configured to trigger the alarming unit, if the human target which has the matching value higher than the reference matching value cannot be determined from the re-collected color image and depth image.

12. A method for automatically controlling movement of a shopping cart to track a target object, comprising
Collecting a color image and a depth image of a field of view;
identifying the target object based on the collected color image and depth image, and determining a motion parameter of the shopping cart based on a position and/or movement of the target object; and
driving the shopping cart to move based on the determined motion parameter,
wherein the determining a motion parameter of the shopping cart based on a position and/or movement of the target object comprises:
determining target characteristics of the target object in the color image an

Assignees

• Boe Technology Group Co Ltd

Inventors

• Ding Hongli
• GU Yu
• Li Yue
• Zhang Ying
• Zhao Kai
• Zhang Yifei

Classifications

• G06V10/758

  Involving statistics of pixels or of feature values, e.g. histogram matching · CPC title

• B62B3/14

  characterised by provisions for nesting or stacking, e.g. shopping trolleys {(collapsible shopping trolleys B62B3/027)} · CPC title

• G06T2207/30196

  Human being; Person · CPC title

• B62B5/0069

  Control · CPC title

• G06T7/194

  involving foreground-background segmentation · CPC title