isLouisHsu / isLouisHsu/isLouisHsu.github.io

NMS & soft-NMS | LOUIS' BLOG

Open
#23 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

e4f5fe5cf915df4f5bd4281a6b6be091 Gitalk
Dominant language
HTML
Stars
4
Forks
1
PR merge metrics
No merged PRs in 30d

Description

https://louishsu.xyz/2019/05/26/NMS-softer-NMS/

前言在目标检测中,若多个回归框(Bounding Box)重叠内容较多,则可以保留其中几个,删除其余冗余的框,非极大值抑制(Non-Maximum Suppression, NMS)算法可实现该功能。 那么用什么指标评价两个回归框重叠过多呢,以下介绍图像的交并比IoU(Intersection over Union)。 IoU原理IoU的思路非常简单,即计算两个回归框交集部分面积与并集面积的比值,

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the linked NMS and soft-NMS article and the Chinese text in the issue body. The issue does not identify a file, requested change, or acceptance criteria, so the scope and definition of done need clarification before work can begin.

Written by the indexing model from the issue text.

Assessment

Domain
content, documentation
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.