R-CNN, Fast R-CNN, Faster R-CNN, YOLO：目标检测算法总结

Question

如题所述

Answer 1

参考链接

以下是文中涉及的算法的最原始的文章：

一个最直接的解决办法是从图中取不同的感兴趣区域，然后对这些区域用CNN进行分类，检测这些区域中是否有物体的存在。
但是待检测物体可能存在于图片的不同位置而且有不同的长宽比例。所以以上方法需要选取量非常大的区域并需要非常大的计算量。

因此，R-CNN, Fast R-CNN, Faster R-CNN, YOLO被开发去又快又准地找物体。

为了解决上述提到的有大量区域被选择的问题， Ross Girshick et al 提出了一种方法：用了选择性搜索从图片提取了2000个区域，这些区域被称为”region proposals“。

用这种办法，我们不需要去分类巨大数量的区域了，我们只需要去处理2000个区域。这2000个区域是用如下的选择性搜索算法（selective search algorithm）来找到的：

这篇文章 介绍了更多关于选择性搜索算法(selective search algorithm)的内容。

RCNN步骤：

R-CNN存在的问题：

Fast R-CNN的几个改进：
The same author of the previous paper(R-CNN) solved some of the drawbacks of R-CNN to build a faster object detection algorithm and it was called Fast R-CNN. The approach is similar to the R-CNN algorithm.

Fast R-CNN更快的原因是：

Fast R-CNN更快：
From the above graphs, you can infer that Fast R-CNN is significantly faster in training and testing sessions over R-CNN. When you look at the performance of Fast R-CNN during testing time, including region proposals slows down the algorithm significantly when compared to not using region proposals. Therefore, region proposals become bottlenecks in Fast R-CNN algorithm affecting its performance.

上面两个算法的缺点：
selective search耗时
Both of the above algorithms(R-CNN & Fast R-CNN) uses selective search to find out the region proposals . Selective search is a slow and time-consuming process affecting the performance of the network.

Faster R-CNN的改进：
不用selective search去找region proposals；
用network去找region proposals；
Therefore, Shaoqing Ren et al . came up with an object detection algorithm that eliminates the selective search algorithm and lets the network learn the region proposals .

Faster R-CNN的步骤：

时间上的对比：
Faster R-CNN最快并且能用作实时目标检测

之前几种算法的缺点：
产生region的时候没有纵览整幅图。其实图的某些部分有更高的可能性包含物体。
All of the previous object detection algorithms use regions to localize the object within the image. The network does not look at the complete image. Instead, parts of the image which have high probabilities of containing the object .

YOLO的思想：
用一个单独的网络去预测bounding boxes和bounding boxes中存在物体的概率
YOLO or You Only Look Once is an object detection algorithm much different from the region based algorithms seen above.
In YOLO, a single convolutional network predicts (1) the bounding boxes and (2)the class probabilities for these boxes.

YOLO的具体步骤：
How YOLO works is that:

YOLO的优缺点：