当前位置：网站首页>An example of shadow detection in image processing bdrar

An example of shadow detection in image processing bdrar

2022-07-20 17:27:00 【Between mountains and rivers 2018】

paper :Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection

github:BDRAR

Preparation

  1. Set the path of pretrained ResNeXt model in resnext/config.py
  2. Set the path of SBU dataset in config.py

The pretrained ResNeXt model is ported from the official torch version, using the convertor provided by clcarwin. You can directly download the pretrained model ported by me.

 

 

Effect display ：

On the left below is true shadow mask, The picture on the right is predict mask, Here is GT

good:

 

not good :

1. Black objects that are similar to shadows themselves are misjudged as shadows , Of course, this may be related to the effect of my training model

 

2. Missed parts ：

 

Overall, , The effect is still broad .

 

 

 

 

 

 

 

原网站

版权声明
本文为[Between mountains and rivers 2018]所创，转载请带上原文链接，感谢
https://yzsam.com/2022/201/202207191446175015.html

边栏推荐

猜你喜欢

随机推荐