Obstacle detection method, mobile platform, and computer readable storage medium

Patent metadata

Field	Value
Publication number	US-2020349727-A1
Application number	US-202016935790-A
Country	US
Kind code	A1
Filing date	Jul 22, 2020
Priority date	Jan 23, 2018
Publication date	Nov 5, 2020
Grant date	—

Abstract

The present disclosure provides an obstacle detection method. The method includes acquiring a first type of grid including obstacle indication information; determining a corresponding project position of the first type of grid in a first depth image; acquiring a first distance between a mobile platform and the corresponding projection position and a second distance between the mobile platform and an obstacle, the obstacle being the obstacle detected based on the first depth image; and updating the obstacle indication information of the first type of grid based on the first distance and the second distance.

First claim

What is claimed is:

1 . An obstacle detection method, comprising:
acquiring a first type of grid including obstacle indication information; determining a corresponding project position of the first type of grid in a first depth image; acquiring a first distance between a mobile platform and the corresponding projection position and a second distance between the mobile platform and an obstacle, the obstacle being the obstacle detected based on the first depth image; and updating the obstacle indication information of the first type of grid based on the first distance and the second distance.

2 . The method of claim 1 , wherein before acquiring the first type of grid including the obstacle indication information further includes:
dividing a three-dimensional (3D) space under a navigation coordinate system at a first time into a plurality of grids; and determining the first type of grid including the obstacle from the plurality of grids.

3 . The method of claim 2 , wherein after determining the first type of grid including the obstacle from the plurality of grids further includes:
storing a correspondence between the first type of grid and the obstacle indication information of the first type of grid in a first memory block; and acquiring the first type of grid including the obstacle indication information includes acquiring the first type of grid including the obstacle indication information from the first memory block.

4 . The method of claim 3 , further comprising:
dividing the first memory block into a plurality of memory units, each memory unit corresponds to an area of the first type of grid.

5 . The method of claim 3 , wherein the number of memory units included in the first memory block is determined based on a distance between the first type of grid and the mobile platform.

6 . The method of claim 2 , wherein determining the first type of grid including the obstacle from the plurality of grids includes:
acquiring a second depth image at the first time and converting the second depth image into a first 3D point cloud; determining a grid corresponding to each feature point in the first 3D point cloud; and determining the first type of grid including the obstacle based on feature point information of each grid.

7 . The method of claim 1 , wherein determining the corresponding projection position of the first type of grid in the first depth image includes:
acquiring the first depth image at a second time; and determining the corresponding projection position of the first type of grid in the first depth image based on position information of the first type of grid.

8 . The method of claim 1 , wherein acquiring the second distance between the mobile platform and the obstacle includes:
acquiring the first depth image at the second time and converting the first depth image into a second 3D point cloud; determining the position of the obstacle at the second time based on the second 3D point cloud; and acquiring the second distance between the mobile platform and the obstacle.

9 . The method of claim 8 , wherein after determining the position of the obstacle at the second time based on the second 3D point cloud further includes:
dividing the 3D space under the navigation coordinate system at the second time into a plurality of grids; determining a second type of grid corresponding to the position of the obstacle from the plurality of grids; and storing the correspondence between the second type of grid and the obstacle indication information of the second type of grid in a second memory block.

10 . The method of claim 9 , further comprising:
dividing the second memory block into a plurality of memory units, each memory unit corresponds to an area of the second type of grid.

11 . The method of claim 10 , wherein the number of memory units included in the second memory block is determined based on a distance between the second type of grid and the mobile platform.

12 . The method of claim 1 , wherein updating the obstacle indication information of the first type of grid based on the first distance and the second distance includes:
determining the first type of grid does not include the obstacle and updating the obstacle indication information based on a determination result of an absence of the obstacle in response to a difference between the first distance and the second distance being greater than a first threshold.

13 . The method of claim 12 , wherein:
the obstacle indication information includes a probability of a presence of the obstacle; and updating the obstacle indication information based on the determination result of the absence of the obstacle includes reducing the probability of the presence of the obstacle of the first type of grid.

14 . The method of claim 13 , wherein after reducing the probability of the presence of the obstacle in the first type of grid further includes:
releasing a memory block for storing the first type of grid and the probability of the presence of the obstacle in the first type of grid in response to the reduced probability of the presence of the obstacle being less than a second threshold.

15 . The method of claim 1 , wherein updating the obstacle indication information of the first type of grid based on the first distance and the second distance includes:
determining the first type of grid includes the obstacle and updating the obstacle indication information based on the determination result of the presence of the obstacle in response to the difference between the first distance and the second distance being less than or equal to the first threshold.

16 . The method of claim 15 , wherein:
the obstacle indication information includes the probability of the presence of the obstacle; and updating the obstacle indication information based on the determination result of the presence of the obstacle includes increasing the probability of the presence of the obstacle of the first type of grid.

17 . The method of claim 2 , wherein dividing the 3D space under the navigation coordinate system into a plurality of grids includes:
setting a corresponding resolution for each grid based on the distance between each grid and the mobile platform.

18 . The method of claim 17 , wherein:
the corresponding resolution is higher when the distance between the grid and the mobile platform is shorter.

19 . The method of claim 3 , further comprising:
acquiring a first grid storage unit at the first time, the first grid storage unit includes a plurality of sub-grid storage units corresponding each grid at the first time; and storing address information of the first memory block corresponding to the first type of grid in the sub-grid storage unit corresponding to the first type of grid.

20 . A mobile platform, comprising:
a processor; and a memory storing one or more sets of instruction sets that, when executed by the processor, causes the processor to: acquire a first type of grid including obstacle indication information; determine a corresponding project position of the first type of grid in a first depth image; acquire a first distance between a mobile platform and the corresponding projection position and a second distance between the mobile platform and an obstacle, the obstacle is the obstacle detected based on the first depth image; and update the obstacle indication information of the first type of grid based on the first distance and the second distance.

Assignees

• Sz Dji Technology Co Ltd

Inventors

• Liu Ang
• Zhang Litian
• Ma Lu

Classifications

• B64U2201/10

  autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS] · CPC title

• B64U2101/30

  for imaging, photography or videography · CPC title

• B64U10/13

  Flying platforms · CPC title

• B64U60/50

  with landing legs · CPC title

• B64U20/87

  Mounting of imaging devices, e.g. mounting of gimbals · CPC title