Object tracking method, object tracking apparatus, vehicle having the same, and computer-program product

Patent metadata

Field	Value
Publication number	US-11482013-B2
Application number	US-201816616962-A
Country	US
Kind code	B2
Filing date	May 23, 2018
Priority date	Sep 28, 2017
Publication date	Oct 25, 2022
Grant date	Oct 25, 2022

Abstract

The present application provides an object tracking method. The object tracking method includes obtaining an image of an area in front of a vehicle; dividing the image of the area in the front of the vehicle into a plurality of sub-images; determining a plurality of first sub-images that satisfy a plurality of threshold conditions out of the plurality of sub-images; selecting a plurality of target sub-images out of the plurality of first sub-images, at least one of the plurality of first sub-images is not selected as one of the plurality of target sub-images; and recognizing a target object in one of the plurality of target sub-images.

First claim

What is claimed is:

1. An object tracking method, comprising:
obtaining an image of an area in front of a vehicle;
dividing the image of the area in the front of the vehicle into a plurality of sub-images;
determining a plurality of first sub-images that satisfy a plurality of threshold conditions out of the plurality of sub-images;
selecting a plurality of target sub-images out of the plurality of first sub-images, at least one of the plurality of first sub-images is not selected as one of the plurality of target sub-images; and
recognizing a target object in one of the plurality of target sub-images;
wherein the plurality of threshold conditions comprise:
a real distance between the target object in a sub-image and the front of the vehicle is in a first threshold distance range;
a real height of the target object in the sub-image is in a threshold height range;
a real width of the target object in the sub-image is in a threshold width range; and
a real distance between a central point of the sub-image and one of two lateral sides of the vehicle closer to the central point of the sub-image is in a second threshold distance range;
wherein the real distance between the target object in a sub-image and the front of the vehicle is determined according to Equation (1):

D
=

f
v

⁢

h
c

+

h
c

⁡

(

c
v

-

v

t
⁢

⁢
2

)

⁢

tan
⁡

(
φ
)

v

t
⁢

⁢
2

-

v
0

;

(
1
)

wherein D is the real distance between the target object in a sub-image and the front of the vehicle; f v is a focal length of a camera configured to obtain the image of the area in the front of the vehicle; h c is a height of the camera relative to ground; c v is a position of camera optical center; V t2 is a vertical coordinate of a middle point of a base of the sub-image; v 0 is a vertical coordinate of a vanishing point of the image of the area in the front of the vehicle.

2. The object tracking method of claim 1 , further comprising:
calculating the real distance between the target object in the sub-image and the front of the vehicle;
calculating the real height of the target object in the sub-image;
calculating the real width of the target object in the sub-image; and
calculating the real distance between the central point of the sub-image and the one of two lateral sides of the vehicle closer to the central point of the sub-image.

3. The object tracking method of claim 1 , wherein the image of the area in the front of the vehicle is obtained using a monocular camera on center top of the vehicle.

4. The object tracking method of claim 1 , wherein the vertical coordinate of the vanishing point of the image of the area in the front of the vehicle is determined by:
detecting edge image of the image of the area in the front of the vehicle using an edge detection algorithm;
detecting a plurality of adjacent straight lines, extension directions of which converging with each other at a point of convergence;
assigning the plurality of adjacent straight lines as a road lane;
assigning the point of convergence of the extension directions of the plurality of adjacent straight lines as the vanishing point of the image of the area in the front of the vehicle; and
determining the vertical coordinate of the vanishing point of the image of the area in the front of the vehicle.

5. The object tracking method of claim 1 , wherein the real height of the target object in the sub-image is determined according to Equation (2):

H
=

h
t

⁡

(

D
+

h
c

⁢

tan
⁡

(
φ
)

)

f
v

+

Assignees

• Boe Technology Group Co Ltd
• Beijing Boe Technology Dev Co Ltd

Inventors

• Ding Hongli
• Tang Xiaojun

Classifications

• G06V20/58 Primary

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V20/584 Primary

  of vehicle lights or traffic lights · CPC title

• G06F18/285

  Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title