Water surface detection method and apparatus, unmanned aerial vehicle landing method and apparatus and unmanned aerial vehicle

Patent metadata

Field	Value
Publication number	US-10577101-B2
Application number	US-201715850555-A
Country	US
Kind code	B2
Filing date	Dec 21, 2017
Priority date	Dec 21, 2017
Publication date	Mar 3, 2020
Grant date	Mar 3, 2020

Abstract

Embodiments of the present disclosure disclose a water surface detection method, an unmanned aerial vehicle landing method and an unmanned aerial vehicle. The detection method includes: controlling the unmanned aerial vehicle to generate an airflow, where the airflow is used to generate a water surface ripple; obtaining an image of a landing area of the unmanned aerial vehicle and a flight parameter of the unmanned aerial vehicle; and processing the image, and determining, with reference to the flight parameter, whether the landing area has the water surface ripple. Damage caused by erroneous landing of the unmanned aerial vehicle on a water surface can be alleviated by determining whether the landing area has the water surface.

First claim

What is claimed is:

1. A water surface detection method, applied to an unmanned aerial vehicle, wherein the detection method comprises:
controlling the unmanned aerial vehicle to generate an airflow, wherein the airflow is used to generate a water surface ripple;
obtaining an image of a landing area of the unmanned aerial vehicle and a flight parameter of the unmanned aerial vehicle; and
processing the image, and determining, with reference to the flight parameter, whether the landing area has the water surface ripple;
wherein the processing the image, and determining, with reference to the flight parameter, whether the landing area has the water surface ripple comprises:
performing edge detection on the image to obtain a first sub-image;
obtaining a wavelength range of the water surface ripple according to the flight parameter;
filtering the first sub-image according to the wavelength range to obtain a ripple corresponding to the wavelength range;
calculating reliability of the ripple according to a vision algorithm and determining whether the reliability is greater than a preset threshold; and
if the reliability is greater than the preset threshold, determining that the landing area is a water surface.

2. The water surface detection method according to claim 1 , wherein the water surface detection method further comprises:
determining whether a flight altitude of the unmanned aerial vehicle is less than a specified altitude; and
if the flight altitude of the unmanned aerial vehicle is not less than the specified altitude, controlling the unmanned aerial vehicle to descend until the flight altitude of the unmanned aerial vehicle is less than the specified altitude, so as to ensure that the unmanned aerial vehicle can generate the water surface ripple.

3. The water surface detection method according to any of claim 1 , wherein the airflow is generated by an airflow generating apparatus of the unmanned aerial vehicle.

4. The water surface detection method according to claim 3 , wherein the airflow generating apparatus comprises a rotor of the unmanned aerial vehicle.

5. The water surface detection method according to any of claim 1 , wherein the flight parameter comprises a flight attitude parameter of the unmanned aerial vehicle and an altitude parameter of the unmanned aerial vehicle.

6. The water surface detection method according to claim 1 , further comprising:
if the landing area has the water surface ripple, controlling the unmanned aerial vehicle to suspend landing and/or controlling the unmanned aerial vehicle to fly away from the landing area.

7. An unmanned aerial vehicle, comprising a body and an image collection apparatus connected to the body, wherein the unmanned aerial vehicle further comprises:
an airflow generating apparatus, configured to generate an airflow, wherein the airflow is used to generate a water surface ripple;
a flight control chip, wherein the flight control chip is configured to obtain an image that is of a landing area of the unmanned aerial vehicle and collected by the image collection apparatus and a flight parameter of the unmanned aerial vehicle; and
a vision chip, configured to: perform image processing on the image that is of the landing area and collected by the image collection apparatus, and determine, with reference to the flight parameter obtained by the flight control chip, whether the landing area has the water surface ripple;
wherein the vision chip is specifically configured to:
perform edge detection on the image to obtain a first sub-image;
obtain a wavelength range of the water surface ripple according to the flight parameter;
filter the first sub-image according to the wavelength range to obtain a ripple corresponding to the wavelength range;
calculate reliability of the ripple according to a vision algorithm, and determine whether the reliability is greater than a preset threshold; and
if the reliability is greater than the preset threshold, determine that the landing area is a water surface.

8. The unmanned aerial vehicle according to claim 7 , wherein the flight control chip is further configured to:
determine whether a flight altitude of the unmanned aerial vehicle is less than a specified altitude; and
if the flight altitude of the unmanned aerial vehicle is not less than the specified altitude, control the unmanned aerial vehicle to descend until the flight altitude of the unmanned aerial vehicle is less than the specified altitude, so as to ensure that the unmanned aerial vehicle can generate the water surface ripple.

9. The unmanned aerial vehicle according to any of claim 7 , wherein the airflow is generated by the airflow generating apparatus of the unmanned aerial vehicle.

10. The unmanned aerial vehicle according to claim 9 , wherein the airflow generating apparatus comprises a rotor of the unmanned aerial vehicle.

11. The unmanned aerial vehicle according to any of claim 7 , wherein the flight parameter comprises a flight attitude parameter of the unmanned aerial vehicle and an altitude parameter of the unmanned aerial vehicle.

Assignees

• Autel Robotics Co Ltd

Inventors

• Wang Xu
• Cui Xipeng
• Jia Ning
• Song Yu

Classifications

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06V20/17 Primary

  taken from planes or by drones · CPC title

• G06V20/13

  Satellite images · CPC title

• G06T7/529

  from texture · CPC title

• G06T2207/20061

  Hough transform · CPC title