1
1

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 5 years have passed since last update.

【物体検出】Window Base物体検出

1
Last updated at Posted at 2020-09-22

window baseのobject detectionに関してwindowをスライドするのか〜ぐらいにしか理解していなかったので、まとめてみた。

処理手順

1. 様々なサイズや縦横比(aspect ratio)のwindowを定義する
  1. 1で定義したwindowをそれぞれ画像の左端から右端まで少しずつスライドさせていく

image.png
3. windowでくり抜いた画像をfixしたサイズにresizeする
image.png
4. 画像分類器を用いて物体が何であるかを推定すれば、車や人などwindow内の物体が何であるか判別出来る。
画像分類器に関しては良ければ参考に
https://qiita.com/minh33/items/a8b77d7fb809385632ea

image.png
=> CARってClassifyされば正解!

プログラムで書くとわかりやすい

image.png

参考文献

What do we learn from region based object detectors (Faster R-CNN, R-FCN, FPN)? https://medium.com/@jonathan_hui/what-do-we-learn-from-region-based-object-detectors-faster-r-cnn-r-fcn-fpn-7e354377a7c9 Window Based Object Detection https://www.youtube.com/watch?v=jgACj-1zbQw C4W3L03 Object Detection https://www.youtube.com/watch?v=5e5pjeojznk
1
1
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
1
1

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?