Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

修改aircv特征点筛选的计算方法 #1049

Open
wants to merge 7 commits into
base: master
Choose a base branch
from

Conversation

hakaboom
Copy link
Contributor

@hakaboom hakaboom commented May 17, 2022

这个pr的目的在于提高特征匹配的准确率
增加特征点识别的find_all_results方法

@Da-Capo
Copy link
Member

Da-Capo commented Jun 10, 2022

hello hakaboom!非常感谢❤您的pr,我们对您提供的代码进行了基准测试,测试的结果如下。
1 以下代码段在部分情况会报错
https://github.com/hakaboom/Airtest/blob/d5d632ebfbb5b6131505b3cf763ee6acb8ced8e7/airtest/aircv/keypoint_base.py#L204
https://github.com/hakaboom/Airtest/blob/d5d632ebfbb5b6131505b3cf763ee6acb8ced8e7/airtest/aircv/keypoint_base.py#L214
2 在我们的测试数据中表现,相比当前sfit算法 漏检减少、误检增多,可能导致用户现有脚本的表现异常。
测试样本量总数 8372,以下为测试结果
正确 4260 + 2719 检测错位 344 漏检 801 虚警 247
正确 4187 + 2535 检测错位 634 漏检 694 虚警 320
下面列出部分检测有问题的图(红色是正确的框,蓝色是sift的识别结果 绿色pr sift的识别结果)
result_560311_tpl1481082239753
result_560402_tpl1464535754810
result_561527_tpl1598925325189
result_560005_tpl1586942359447

@Da-Capo
Copy link
Member

Da-Capo commented Jun 10, 2022

这些是测试的原始图像 方便您进行问题排查
screen_560005_tpl1586942359447
screen_560311_tpl1481082239753
screen_560402_tpl1464535754810
screen_561527_tpl1598925325189
tmpl_560005_tpl1586942359447
tmpl_560311_tpl1481082239753
tmpl_560402_tpl1464535754810
tmpl_561527_tpl1598925325189

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants