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.

【Stereo Depth】 RTS2Net : AnyNetをSemantic Segmentationで精度UP

Last updated at Posted at 2020-12-15

Real-Time Semantic Stereo Matching

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/534f2eaa-3c5b-dd6c-87f0-c31061ec594f.png) AnyNetにSemantic Segmentationを追加してさらに物体に対してのSmoothingを行うネットワーク。 AnyNetと基本的なSemantic Segmentationが分かれば難しい事はなかったので、結果だけを見たいと思う。

結果

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/76fe9cec-afbb-4c7b-e581-41b65c93270d.png) すべてのstageに置いてRTS2の方がAnytimeより精度がよくなってる。速度が遅くなるのは仕方ないか。 ちなみに約10Hzの所に赤字になっているのを比べるとRTS2Netの方が同じ速度で精度が良いという事を主張したいらしい。

image.png
RealTime System(10Hz)の中では一番精度が良い。

結論

・Semantic Segmentationを使用する事でStereo Depthの精度が上がる事がわかった。

参考文献

Real-Time Semantic Stereo Matching https://arxiv.org/pdf/1910.00541.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?