US 12,249,131 B2
Model generating apparatus and model generating method
Yasutaka Okada, Kobe (JP); Ryusuke Seki, Kobe (JP); Yuki Katayama, Kobe (JP); Rei Hiromi, Kobe (JP); and Aoi Ogishima, Kobe (JP)
Assigned to DENSO TEN Limited, Kobe (JP)
Appl. No. 17/639,836
Filed by DENSO TEN Limited, Kobe (JP)
PCT Filed Sep. 23, 2020, PCT No. PCT/JP2020/035861
§ 371(c)(1), (2) Date Mar. 2, 2022,
PCT Pub. No. WO2022/064575, PCT Pub. Date Mar. 31, 2022.
Prior Publication US 2022/0415032 A1, Dec. 29, 2022
Int. Cl. G06V 10/82 (2022.01); G06V 10/77 (2022.01); G06V 10/778 (2022.01)
CPC G06V 10/82 (2022.01) [G06V 10/7715 (2022.01); G06V 10/778 (2022.01)] 5 Claims
OG exemplary drawing
 
1. A model generating apparatus comprising:
a processor configured to:
measure sizes of a plurality of objects identified in an image included in data set;
calculate a distribution of the sizes for the plurality of objects;
select fewer number of layers among a plurality of layers for extracting features in a Convolutional Neural Network (CNN), based on the distribution; and
connect the fewer number of layers to a detector for detecting the plurality of objects.