US 12,067,790 B2
Method and system for identifying object
Maximilian Doemling, Landshut (DE); Qianshan Li, Shanghai (CN); and Wenxin Tian, Shanghai (CN)
Assigned to Bayerische Motoren Werke Aktiengesellschaft, Munich (DE)
Appl. No. 17/597,100
Filed by Bayerische Motoren Werke Aktiengesellschaft, Munich (DE)
PCT Filed Jun. 28, 2019, PCT No. PCT/CN2019/093596
§ 371(c)(1), (2) Date Dec. 27, 2021,
PCT Pub. No. WO2020/258222, PCT Pub. Date Dec. 30, 2020.
Prior Publication US 2022/0254140 A1, Aug. 11, 2022
Int. Cl. G06V 20/56 (2022.01); G06V 10/72 (2022.01); G06V 10/80 (2022.01)
CPC G06V 20/588 (2022.01) [G06V 10/72 (2022.01); G06V 10/803 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A method for identifying an object, comprising:
at a first time instant, acquiring raw data output by a camera installed on a vehicle, the output raw data comprises one of a continuous data output format for a continuous model or a discrete data output format for a discrete model;
feeding the raw data to a discrete statistic model to form discrete statistic model format data for the first time instant, the discrete statistic model format data includes a continuous part having the continuous data output format and a discrete part having the discrete data output format;
fusing the discrete statistic model format data for the first time instant with historical discrete statistic model format data to update the discrete statistic model format data for the first time instant; and
identifying the object from the updated discrete statistic model format data for the first time instant, wherein the object includes a lanemarking characterized by a curve.