Target detection method, terminal device, and medium

Patent metadata

Field	Value
Publication number	US-2022301277-A1
Application number	US-202217837192-A
Country	US
Kind code	A1
Filing date	Jun 10, 2022
Priority date	Dec 12, 2019
Publication date	Sep 22, 2022
Grant date	—

Abstract

The present disclosure provides a target detection method. The method includes: acquiring a first scene image captured by a camera; acquiring current position and pose information of the camera; adjusting the first scene image based on the current position and pose information of the camera to obtain a second scene image; and performing a target detection on the second scene image. In addition, The present disclosure also provides a terminal device, and a medium.

First claim

What is claimed is:

1 . A target detection method, comprising:
acquiring a first scene image captured by a camera; acquiring current position and pose information of the camera; adjusting the first scene image based on the current position and pose information of the camera to obtain a second scene image; and performing a target detection on the second scene image.

2 . The target detection method according to claim 1 , wherein acquiring the current position and pose information of the camera, comprises:
acquiring the current position and pose information of the camera by a simultaneous localization and mapping (SLAM) system.

3 . The target detection method according to claim 1 , wherein adjusting the first scene image based on the current position and pose information of the camera, comprises:
determining a rotation angle of the first scene image based on the current position and pose information of the camera; and rotating the first scene image based on the rotation angle.

4 . The target detection method according to claim 3 , further comprising:
determining, based on the current position and pose information of the camera, that the first scene image meets an adjustment requirement; wherein the adjustment requirement refers to that the rotation angle of the first scene image is greater than 0 degree.

5 . The target detection method according to claim 2 , wherein performing the target detection on the second scene image, comprises:
dividing the second scene image to form a plurality of region proposals; and performing the target detection on the plurality of region proposals respectively.

6 . The target detection method according to claim 5 , further comprising:
scanning a scene corresponding to the first scene image by the SLAM system to generate a three-dimensional point cloud corresponding to the scene; and adjusting the three-dimensional point cloud based on the current position and pose information of the camera, so as to make the three-dimensional point cloud correspond to a direction of the second scene image; or scanning a scene corresponding to the second scene image by the SLAM system to generate a three-dimensional point cloud corresponding to the scene.

7 . The target detection method according to claim 6 , wherein scanning the scene comprises:
calibrating the camera to determine internal parameters of the camera; and scanning the scene using the calibrated camera to generate the three-dimensional point cloud corresponding to the scene through the SLAM system.

8 . The target detection method according to claim 6 , wherein dividing the second scene image to form the plurality of region proposals comprises:
dividing the second scene image based on the three-dimensional point cloud to form the plurality of region proposals.

9 . The target detection method according to claim 8 , wherein dividing the second scene image based on the three-dimensional point cloud to form the plurality of region proposals, comprises:
dividing the three-dimensional point cloud to form a plurality of three-dimensional regions; and projecting the plurality of three-dimensional regions to the second scene image to form the plurality of region proposals.

10 . The target detection method according to claim 9 , wherein dividing the three-dimensional point cloud to form the plurality of three-dimensional regions, comprises:
merging three-dimensional points in the adjusted three-dimensional point cloud by a clustering algorithm to obtain a merged three-dimensional point cloud; and dividing the merged three-dimensional point cloud to form the plurality of three-dimensional regions.

11 . The target detection method according to claim 9 , wherein dividing the three-dimensional point cloud to form the plurality of three-dimensional regions, comprises:
fitting three-dimensional points in the adjusted three-dimensional point cloud with a plurality of preset models to divide the three-dimensional point cloud into the plurality of three-dimensional regions respectively to the plurality of preset models.

12 . The target detection method according to claim 5 , wherein performing the target detection on the plurality of region proposals respectively, comprises:
identifying a category of each object in a region proposal using a classification algorithm; and determining a size of the object by performing a bounding box regression for the object to realizing the target detection on the region proposal.

13 . A terminal device, comprising: a memory, a processor, and computer programs stored in the memory and executable by the processor, wherein when the processor executes the computer programs, the processor is caused to implement a target detection method, comprising:
acquiring a first scene image captured by a camera; acquiring current position and pose information of the camera; adjusting the first scene image based on the current position and pose information of the camera to obtain a second scene image; and performing a target detection on the second scene image.

14 . The terminal device according to claim 13 , wherein acquiring the current position and pose information of the camera, comprises:
acquiring the current position and pose information of the camera by a simultaneous localization and mapping (SLAM) system.

15 . The terminal device according to claim 13 , wherein adjusting the first scene image based on the current position and pose information of the camera, comprises:
determining a rotation angle of the first scene image based on the current position and pose information of the camera; and rotating the first scene image based on the rotation angle.

16 . The terminal device according to claim 14 , wherein performing the target detection on the second scene image, comprises:
dividing the second scene image to form a plurality of region proposals; and performing the target detection on the plurality of region proposals respectively.

17 . The terminal device according to claim 16 , wherein the target detection method further comprises:
scanning a scene corresponding to the first scene image by the SLAM system to generate a three-dimensional point cloud corresponding to the scene; and adjusting the three-dimensional point cloud based on the current position and pose information of the camera, so as to make the three-dimensional point cloud correspond to a direction of the second scene image; or scanning a scene corresponding to the second scene image by the SLAM system to generate a three-dimensional point cloud corresponding to the scene.

18 . The terminal device according to claim 17 , wherein dividing the second scene image to form the plurality of region proposals comprises:
dividing the second scene image based on the three-dimensional point cloud to form the plurality of region proposals.

19 . The terminal device according to claim 18 , wherein dividing the second scene image based on the three-dimensional point cloud to form the plurality of region proposals, comprises:
dividing the three-dimensional point cloud to form a plurality of three-dimensional regions; and projecting the plurality of three-dimensional regions to the second scene image to form the plurality of region proposals.

20 . A non-transitory computer readable storage medium, storing computer programs therein, wherein when the computer programs are executed by a processor, the processor is caused to implement a target detection method, comprising:
acquiring a first

Assignees

• Guangdong Oppo Mobile Telecommunications Corp Ltd

Inventors

• Xu Yi

Classifications

• G06V20/10

  Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) · CPC title

• G06V10/255

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06T7/73 Primary

  using feature-based methods · CPC title

• G06T7/80

  Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration · CPC title

• G06T2207/30208

  Marker matrix · CPC title