Machine Vision Technology：Lecture10 Object Detection

计算机视觉（本科） 北京邮电大学 鲁鹏

• Introduction of object detection
• Face Detection
• Pedestrian Detection

object detection and challenges

Object Detection Design challenges：

• How to efficiently search for likely objects

  • Even simple models require searching hundreds of thousands of positions and scales.即使是简单的模型也需要搜索成千上万的位置和尺度。

• Feature design and scoring 特征设计和评分

  • How should appearance be modeled?
  • What features correspond to the object?

• How to deal with different viewpoints? 处理不同的视角差异

  • Often train different models for a few different viewpoints 经常为几个不同的视角训练不同的模型

Face Detection人脸检测

Challenges of face detection：

• Sliding window = tens of thousands of location/scale evaluations

  • 一个百万像素的图像有大约 $10^6$ 个像素，以及相当数量的候选人脸位置

• Faces are rare: 0–10 per image 人脸罕见：每张图片0-10哥人脸

  • For computational efficiency, spend as little time as possible on the non-face windows. 为了提高计算效率，在非人脸窗口上花费尽可能少的时间。
  • For 1 Mpix, to avoid having a false positive in every image, our false positive rate has to be less than $10^{-6}$ 1Mpix,避免假阳性在每一个图像,我们的假阳性率必须小于 $10^{-6}$

Sliding Window Face Detection with Viola-Jones 2001

Viola-Jones使用了机器学习的boosting算法，下面是boosting算法介绍：

• A simple algorithm for learning robust classifiers
• Provides efficient algorithm for sparse visual feature selection
• Easy to implement, not requires external optimization tools

1.找到正确率大于0.5的分类器 $h_i(x)$

2.把错误分类的权重放大

3.迭代1-2

通过几个分类器组合起来得到最终分类器。
$$h(x)={\alpha }_1{h}_1(x)+{\alpha }_2{h}_2(x)+{\alpha }_3{h}_3(x)+\cdots$$
其中 $h(x)$ 是 Strong classifier 强分类器，$h_i(x)$ 是Weak classifier，$x$ 是 Features vector，${\alpha }_i$ 是 Weight。

每个弱分类器：
$$h_j(x)=\{\begin{array}{rcl}1& & \text{if}{f}_j(x)>{\theta }_j\\ 0& & \text{otherwise}\end{array}$$
其中 $f_j(x)$ 是 value of rectangle feature，${\theta }_j$ 是threshold。如下图所示。

所以最终的 strong classfier：
$$h(x)=\{\begin{array}{rcl}1& & \sum _{t=1}^T{\alpha }_t{h}_t(x)>\frac{1}{2}\sum _{t=1}^T{\alpha }_t\\ 0& & \text{otherwise}\end{array}$$

Viola & Jones algorithm ：

• A “paradigmatic” method for real‐time object detection 实时目标检测的“范例”方法
• Training is slow, but detection is very fast
• Key ideas：
  • Integral images for fast feature evaluation 用于快速特征评估的积分图像（积分图）。
  • Boosting for feature selection
  • Attentional cascade for fast rejection of non‐face windows 注意力级联快速拒绝非人脸窗口。也就是对非人脸窗口处理用时更少。

详情看论文，没听太明白。。。就积分图有点像二维联合分布函数的矩形公式。

Pedestrian Detection行人检测

Histograms of oriented gradients for human detection 2005

HoG Feature.