Method for determining a penguin population, device and computer readable medium therefor

Patent metadata

Field	Value
Publication number	US-12430941-B2
Application number	US-202318136280-A
Country	US
Kind code	B2
Filing date	Apr 18, 2023
Priority date	Apr 19, 2022
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

The disclosure provides a method, a device and a computer readable medium for determining the penguin population relating to the technical field of image processing. The method of one embodiment of the disclosure comprises the following steps: firstly acquiring the penguin habitat image detected by the unmanned airborne sensor; and acquiring an interest region with penguins distributing, and a gray value of the interest region from the penguin habitat image; then for any one of gray value: determining a penguin state according to the gray value; finally determining the penguin population according to the penguin state.

First claim

What is claimed is:

1. A method for determining a penguin population, comprising:
acquiring a penguin habitat image detected by an unmanned airborne sensor;
acquiring an interest region with penguin distributing, and a plurality of gray values of the interest region from the penguin habitat image;
for any one of the gray values: determining a penguin state according to the gray value;
determining the penguin population, according to the penguin state, wherein the penguin population is configured for revealing a variation of the Antarctic penguin population and analyzing natural and social factors in the Antarctic penguin population distribution, determining a penguin state according to the gray value comprises:
if the gray value meets a first preset condition, determining the gray value corresponding to an adult penguin, and acquiring a raster data corresponding to the gray value from the penguin habitat image;
converting the raster data into a vector data, and determining a circumference property parameter of the adult penguin according to the vector data;
determining the adult penguin being in a standing state if the circumference property parameter meets a third preset condition;
determining the adult penguin being in a lying face down state if the circumference property parameter meets a fourth preset condition.

2. The method as recited in claim 1 , wherein
the determining a penguin state according to the gray value includes:
determining the gray value as a baby penguin if the gray value meets a second preset condition, and acquiring the raster data corresponding to the gray value from the penguin habitat image;
converting the raster data into a vector data, and determining an area property parameter of the baby penguin according to the vector data;
determining the baby penguin as an individual state if the area property parameter meets a fifth preset condition;
identifying the baby penguin as a daycare state if the area property parameter meets a sixth preset condition.

3. The method as recited in claim 2 , wherein
determining the gray value corresponding to at least one of the combinations of the adult penguin and the baby penguin, based on an object-oriented classification method.

4. The method as recited in claim 2 , wherein
the penguin is divided into the adult penguin and the baby penguin; and
the determining the penguin population according to the penguin state includes:
determining an adult penguin population according to an adult penguin state;
determining a baby penguin population according to a baby penguin state;
determining a total penguin population according to the adult penguin population and the baby penguin population.

5. The method as recited in claim 4 , wherein
the determining the baby penguin population according to the baby penguin state includes:
counting baby penguin corresponding to the individual state, to acquire a first baby penguin population;
counting baby penguin corresponding to the daycare state, to acquire a second baby penguin population;
determining the baby penguin population according to the first baby penguin population and the second baby penguin population.

6. The method as recited in claim 4 , wherein
determining the gray value corresponding to at least one of the combinations of the adult penguin and the baby penguin based on an object-oriented classification method.

7. The method as recited in claim 1 , wherein
the penguin is divided into the adult penguin and the baby penguin; and
the determining the penguin population according to the penguin state includes:
determining an adult penguin population according to an adult penguin state;
determining a baby penguin population according to a baby penguin state;
determining a total penguin population according to the adult penguin population and the baby penguin population.

8. The method as recited in claim 7 , wherein
the determining the baby penguin population according to the baby penguin state includes:
counting baby penguin corresponding to the individual state, to acquire a first baby penguin population;
counting baby penguin corresponding to the daycare state, to acquire a second baby penguin population;
determining the baby penguin population according to the first baby penguin population and the second baby penguin population.

9. The method as recited in claim 8 , wherein
determining the gray value corresponding to at least one of the combinations of the adult penguin and the baby penguin based on an object-oriented classification method.

10. The method as recited in claim 7 , wherein
determining the gray value corresponding to at least one of the combinations of the adult penguin and the baby penguin based on an object-oriented classification method.

11. A computer readable medium storing a computer program, wherein the computer program implements the method according to claim 1 executed by a processor.

12. The method as recited in claim 1 , wherein
the determining a penguin state according to the gray value includes:
determining the gray value as a baby penguin if the gray value meets a second preset condition, and acquiring the raster data corresponding to the gray value from the penguin habitat image;
converting the raster data into a vector data, and determining an area property parameter of the baby penguin according to the vector data;
determining the baby penguin as an individual state if the area property parameter meets a fifth preset condition;
identifying the baby penguin as a daycare state if the area property parameter meets a sixth preset condition.

13. The method as recited in claim 12 , wherein
determining the gray value corresponding to at least one of the combinations of the adult penguin and the baby penguin based on an object-oriented classification method.

14. The method as recited in claim 1 , wherein
the penguin is divided into the adult penguin and the baby penguin; and
the determining the penguin population according to the penguin state includes:
determining an adult penguin population according to an adult penguin state;
determining a baby penguin population according to a baby penguin state;
determining a total penguin population according to the adult penguin population and the baby penguin population.

15. The method as recited in claim 14 , wherein
the determining the baby penguin population according to the baby penguin state includes:
counting baby penguin corresponding to the individual state, to acquire a first baby penguin population;
counting baby penguin corresponding to the daycare state, to acquire a second baby penguin population;
determining the baby penguin population according to the first baby penguin population and the second baby penguin population.

16. The method as recited in claim 14 , wherein
determining the gray value corresponding to at least one of the combinations of the adult penguin and the baby penguin based on an object-oriented classification method.

17. A device for determining a penguin population, comprising:
a first acquisition module configured to acquire a penguin habitat image detected by an unmanned airborne sensor;
a second acquisition module configured to acquire an interest region with penguin distributing, and a plurality of gray values of the interest region of from the penguin habitat image;
a first determination module configured to determine a penguin state according to any one of gray value;
a second determination module configured to determine the penguin population according to the penguin state; wherei

Assignees

• Univ Hainan
• Sanya Research Institute Of Hainan Univ

Inventors

• Zhao Peng
• Liu Hao
• Deng Yufei
• Liu Pengjia
• Yan Jinmeng
• Cui Zhenhua
• Ge Song

Classifications

• G06T2207/30242

  Counting objects in image · CPC title

• G06T2207/10032

  Satellite or aerial image; Remote sensing · CPC title

• G06V10/56 Primary

  relating to colour · CPC title

• G06V20/17

  taken from planes or by drones · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title