Title:
VISUAL FEATURE EXTRACTION NEURAL NETWORK MODEL TRAINING METHOD AND SYSTEM
Document Type and Number:
WIPO Patent Application WO/2024/085630
Kind Code:
A1
Abstract:
The present disclosure relates to a visual feature extraction neural network model training method performed by at least one processor. The visual feature extraction neural network model training method comprises the steps of: receiving a first street view image captured on the ground; converting the first street view image into a first distorted top view image; converting the first street view image into a second distorted top view image; obtaining a first positional correspondence relationship between pixels in the first distorted top view image and pixels in the second distorted top view image; and training a visual feature extraction neural network model by using the first distorted top view image, the second distorted top view image, and the first positional correspondence relationship, wherein the first distorted top view image and the second distorted top view image are different from each other.
More Like This:
Inventors:
LEE DONGKYU (KR)
Application Number:
PCT/KR2023/016102
Publication Date:
April 25, 2024
Filing Date:
October 18, 2023
Export Citation:
Assignee:
NAVER LABS CORP (KR)
International Classes:
G06N3/08; G06T3/00
Foreign References:
| KR102206834B1 | 2021-01-25 | |||
| CN115082450A | 2022-09-20 | |||
| KR20190124113A | 2019-11-04 | |||
| KR101583797B1 | 2016-01-08 | |||
| KR20220096162A | 2022-07-07 |
Attorney, Agent or Firm:
AHN, Je Sung et al. (KR)
Download PDF: