New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Contextually guided very-high-resolution imagery classification with semantic segments #5

Open

KenichiSasaki opened this issue Oct 10, 2019 · 0 comments

Labels

CNN Segmentation Statistical Method

Collaborator

KenichiSasaki commented Oct 10, 2019 •

edited

概要

Algorithm論文 (Link)
Semantic-free segments (Semantic segments: 建物，木，道など) を持つVHR画像に対してのSegmentation論文

Algorithm

CNNで識別，ここではFCNではなくObject検出(FCNはVHRの表現量に向かない)
Contour情報を識別結果に追加しCRFで後処理
輪郭エッジを保存したSegmentationを実現

実装

3枚の画像使用，中国とドイツの画像(解像度9㎝のArial Image)
EMPなどより精度大幅に向上

所感

CNNと後処理の工夫を加えて精度向上を示した
2017年の発表だが，CNNの初歩的な導入がようやく登場
CNNを用いた研究はいろいろ余地ありそう，
- FCN，転移学習への応用，
- 筆者も言及しているが，VHRは表現量が多くFCNは困難らしい

KenichiSasaki added the CNN label

Shaw0202 added ComputerVision Segmentation labels

KenichiSasaki added Statistical Method and removed ComputerVision labels

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment