Caffe可以直接对图像的像素进行分类吗？ [英] Can Caffe classify pixels of an image directly?

问题描述

我想将图片的像素归类为「is street」或「is not street」。我有一些来自 KITTI数据集的培训数据，我看到Caffe有一个 IMAGE_DATA 图层类型。

I would like to classify pixels of an image to "is street" or "is not street". I have some training data from the KITTI dataset and I have seen that Caffe has an IMAGE_DATA layer type. The labels are there in form of images of the same size as the input image.

除了Caffe，我的第一个想法是解决这个问题是通过给图像应该分类的像素周围的补丁（例如，20像素到顶部/左/右/底部，导致每个像素41×41 = 1681个特征我想分类。

然而，如果我能告诉caffe如何使用标签，而不必手动创建这些图像修补程序（和图层类型 IMAGE_DATA 似乎建议这是可能的）我更喜欢。

Besides Caffe, my first idea to solve this problem was by giving image patches around the pixel which should get classified (e.g. 20 pixels to the top / left / right / bottom, resulting in 41×41=1681 features per pixel I want to classify.
However, if I could tell caffe how to use the labels without having to create those image patches manually (and the layer type IMAGE_DATA seems to suggest that it is possible) I would prefer that.

Caffe可以直接对图像的像素进行分类吗？这样的prototxt网络定义怎么样？我如何给Caffe关于标签的信息？

Can Caffe classify pixels of an image directly? How would such a prototxt network definition look like? How do I give Caffe the information about the labels?

我想输入图层会像

layers {
  name: "data"
  type: IMAGE_DATA
  top: "data"
  top: "label"
  image_data_param {
    source: "path/to/file_list.txt"
    mean_file: "path/to/imagenet_mean.binaryproto"
    batch_size: 4
    crop_size: 41
    mirror: false
    new_height: 256
    new_width: 256
  }
}

但是，我不确定 crop_size 正好是。它真的居中吗？ caffe如何处理角落像素？ new_height 和 new_width 有什么好处？

However, I am not sure what crop_size exactly means. Is it really centered? How does caffe deal with the corner pixels? What is new_height and new_width good for?

推荐答案

似乎可以尝试完全卷积网络进行语义分段

Caffe在本文中被引用： https://github.com/BVLC/caffe/wiki/Publications

Caffe was cited in this paper: https://github.com/BVLC/caffe/wiki/Publications

这里也是模型：
https://github.com/BVLC/caffe / wiki / Model-Zoo＃fully-convolutional-semantic-segmentation-models-fcn-xs

此演示文稿也可以是有用的：
http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-pixels.pdf

Also this presentation can be helpfull: http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-pixels.pdf

这篇关于Caffe可以直接对图像的像素进行分类吗？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！