ShiqiYu / ShiqiYu/libfacedetection
在树莓4B上检测人脸，检测精度与距离的关系
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 12.8k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
于老师您好，我在树莓派4B上使用libfacedetection检测人脸的时候，发现当摄像机与人脸的距离变化时，在某一个特定距离检测出来的置信度变化很大，只要不是这个距离都可以得到很好的检测效果，但是一旦摄像机距离人脸大约35~40cm距离的时候，将检测到的人脸的置信度非常低（demo中的confidence），我使用的是项目自带的模型代码，请问这是模型的问题还是算法的问题？由于我需要被测人脸与摄像头的距离不断变化，请问这个问题应该怎么解决？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the bundled libfacedetection demo on a Raspberry Pi 4B, recording confidence as the camera-to-face distance changes, especially around 35–40 cm. Compare the observed results with the project’s supplied model and determine whether the behavior is caused by the model or algorithm; done means identifying the cause and documenting a reliable solution for changing distances.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, raspberry-pi
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100