0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

【2D OD】RCNN : 2D Object Detectionの基礎編

Last updated at Posted at 2020-09-25

Rich feature hierarchies for accurate object detection and semantic segmentation

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/0b1aeb5e-0cae-f84c-d017-791ba41f8fe0.png) 2014年に発案された2D Object Detectionの基礎と言えるRCNNを見ていこう

アルゴリズム

1. Input Image 2. Extract Region Proposal 3. Compute CNN Feature 4. Classify regions

Extract region proposal

[selective search](https://qiita.com/minh33/items/1cb765861dcb8a98b4f5)により物体がありそうな所を提示する

warped region

selective searchによって得られたwindow sizeを固定のサイズ(任意)に変換する。 *物体の大きさや縦横比による影響を抑えるため

classify regions

Fully Connected Layerを用いてclass分類を行い。 softmaxにてclassの確率合計が1になるように正規化する。

参考文献

Rich feature hierarchies for accurate object detection and semantic segmentation https://arxiv.org/pdf/1311.2524.pdf
0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?