US 12,094,226 B2
Simultaneous localization and mapping method, device, system and storage medium
Qingquan Li, Shenzhen (CN); Weicheng Xiong, Shenzhen (CN); Liang Zhang, Shenzhen (CN); Shuang Yang, Shenzhen (CN); and Xuewan Li, Shenzhen (CN)
Assigned to SHENZHEN INTELLIGENCE ALLY TECHNOLOGY CO., LTD., Shenzhen (CN)
Appl. No. 17/624,317
Filed by SHENZHEN INTELLIGENCE ALLY TECHNOLOGY CO., LTD., Shenzhen (CN)
PCT Filed Apr. 15, 2021, PCT No. PCT/CN2021/087531
§ 371(c)(1), (2) Date Dec. 31, 2021,
PCT Pub. No. WO2021/233029, PCT Pub. Date Nov. 25, 2021.
Claims priority of application No. 202010416829.5 (CN), filed on May 18, 2020.
Prior Publication US 2023/0260151 A1, Aug. 17, 2023
Int. Cl. G06V 20/64 (2022.01); G06T 7/13 (2017.01); G06T 7/246 (2017.01); G06T 7/73 (2017.01); G06V 10/44 (2022.01); G06V 10/46 (2022.01); G06V 10/75 (2022.01); G06V 20/10 (2022.01)
CPC G06V 20/64 (2022.01) [G06T 7/13 (2017.01); G06T 7/248 (2017.01); G06T 7/74 (2017.01); G06V 10/457 (2022.01); G06V 10/462 (2022.01); G06V 10/757 (2022.01); G06V 20/10 (2022.01); G06T 2207/10028 (2013.01); G06T 2207/20221 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method for simultaneous localization and mapping (SLAM), comprising:
acquiring a local binocular vision image and a local three-dimensional laser point cloud image that can be collected at present;
preprocessing the local binocular vision image and the local three-dimensional laser point cloud image, respectively;
acquiring a position and an attitude of a local binocular vision map according to the preprocessed local binocular vision image;
fusing the position and the attitude of the local binocular vision map with the preprocessed local three-dimensional laser point cloud image to obtain a local fusion map; and
performing a global consistency optimization on a global map according to the local fusion map to obtain a dense point cloud map and output a current position information and a current attitude information in real time so as to complete the simultaneous localization and mapping (SLAM), wherein the global map is constructed according to a global three-dimensional laser point cloud image;
wherein the preprocessing the local binocular vision image comprises:
extracting features of the local binocular vision image to obtain feature points of the local binocular vision image;
selecting a specific feature point meeting a preset condition from the feature points of the local binocular vision image;
calculating a feature descriptor of the specific feature point; and
performing a feature matching for the binocular visual image according to the feature descriptor, so as to construct a local map according to the local binocular visual image obtained after the feature matching; and
wherein the acquiring a position and an attitude of a local binocular vision map according to the preprocessed local binocular vision image comprises:
performing local map tracking according to the preprocessed local binocular vision image; and
optimizing a currently obtained local map during map tracking to obtain the position and the attitude of the local binocular vision map.