US 12,189,037 B2
Three-dimensional point cloud generation method, position estimation method, three-dimensional point cloud generation device, and position estimation device
Pongsak Lasang, Singapore (SG); Chi Wang, Singapore (SG); Zheng Wu, Singapore (SG); Sheng Mei Shen, Singapore (SG); Toshiyasu Sugio, Osaka (JP); and Tatsuya Koyama, Kyoto (JP)
Assigned to PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA, Torrance, CA (US)
Filed by Panasonic Intellectual Property Corporation of America, Torrance, CA (US)
Filed on May 19, 2020, as Appl. No. 16/877,835.
Application 16/877,835 is a continuation of application No. PCT/JP2018/042423, filed on Nov. 16, 2018.
Claims priority of provisional application 62/588,596, filed on Nov. 20, 2017.
Prior Publication US 2020/0278450 A1, Sep. 3, 2020
Int. Cl. G01S 17/894 (2020.01); G06T 7/521 (2017.01); G06T 7/73 (2017.01)
CPC G01S 17/894 (2020.01) [G06T 7/521 (2017.01); G06T 7/73 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A three-dimensional point cloud data processing method for processing, using a processor, three-dimensional point cloud data, the three-dimensional point cloud data processing method comprising:
obtaining (i) a two-dimensional image obtained using a camera and (ii) a first three-dimensional point cloud obtained using a distance sensor;
detecting, from the two-dimensional image obtained in the obtaining, a feature value of the two-dimensional image, the feature value being associated with a two-dimensional coordinate value in a two-dimensional image and one of a plurality of first three-dimensional points included in the first three-dimensional point cloud;
generating first three-dimensional point cloud data that includes a plurality of first three-dimensional point data items associated one to one with the plurality of first three-dimensional points included in the first three-dimensional point cloud, the plurality of first three-dimensional point data items each being a combination of (i) a three-dimensional coordinate value of an associated first three-dimensional point out of the plurality of first three-dimensional points, (ii) the feature value of the associated first three-dimensional point, and (iii) a confidence value of the three-dimensional coordinate value of the associated first three-dimensional point, each of the plurality of first three-dimensional point data items being associated with each of the plurality of first three-dimensional points included in the first three-dimensional point cloud; and
selecting, based on the confidence value, a first three-dimensional point from among the plurality of first three-dimensional point cloud to output a first three-dimensional point data item associated to the selected first three-dimensional point,
wherein the confidence value indicates certainty of a coordinate position of the first three-dimensional point, and
wherein the confidence value is calculated based on a total number of two-dimensional images in which the associated three-dimensional point is observed, the confidence value increasing as the total number of two-dimensional images in which the associated three-dimensional point is observed increases.