deep-learn
/
ml
Archived
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

跟新目标检测图片链接

This commit is contained in:
zeek 2020-04-25 17:09:18 +08:00
parent 7e815697ce
commit 635ca681e1
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
targetDetection/README.md
View File

@ -7,10 +7,12 @@
3. 检测-Detection：解决“是什么？在哪里？”的问题，即定位出这个目标的的位置并且知道目标物是什么。
4. 分割-Segmentation：分为实例的分割（Instance-level）和场景分割（Scene-level），解决“每一个像素属于哪个目标物或场景”的问题。
![pic](http://index.zeekling.cn/gogsPics/ml/targetDection/1.png)
![pic](https://img.zeekling.cn/images/2020/04/25/63e746f0962e6215b5ed6a2587fe5af0.png)
## 目标检测算法分类
![pic](http://index.zeekling.cn/gogsPics/ml/targetDection/2.png)
![pic](https://img.zeekling.cn/images/2020/04/25/edfbb1a6466964df97d6bea080496c67.png)
### Two stage目标检测算法
先进行区域生成（region proposal，RP）（一个有可能包含待检物体的预选框），再通过卷积神经网络进行样本分类。