自動運転に向けた地図情報精緻化におけるデータ駆動型AIの課題

元 政現; 金丸 和樹; 我妻 広明

doi:10.14864/fss.34.0_330

34th Fuzzy System Symposium

Session ID : MH3-3

DOI https://doi.org/10.14864/fss.34.0_330

Conference information

Host: Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT)

Name : 34th Fuzzy System Symposium

Number : 34

Location : [in Japanese]

Date : September 03, 2018 - September 05, 2018

proceeding

An Application of Pix2Pix Approach from Aerial Photos to Vector Representation in the Digital Map and its Limitation

*JungHyun WON, Kazuki KANAMARU, Hiroaki WAGATSUMA

Author information

Keywords: Generative Adversarial Network, pix2pix, Aerial Photo, Digital Map

CONFERENCE PROCEEDINGS FREE ACCESS

Details

Abstract

As a deep learning algorithm, software tools based on Generative Adversarial Network (GAN) are released in the form of pix2pix. In the present study, we report a preliminary study of the application of pix2pix to the automatic conversion from aerial photos to vector representation in the digital map and discuss its limitation.

Corresponding author

Conference information

Register with J-STAGE for free!