基于Boosted Cascade的快速对象检测机器学习算法
需积分: 49 124 浏览量
更新于2024-09-08
收藏 955KB PDF 举报
"Rapid Object Detection using a Boosted Cascade of Simple Features"
本文档介绍了一种基于机器学习的快速对象检测方法，该方法能够快速处理图像并实现高检测率。本方法的三个主要贡献是：
1. 引入了一种新的图像表示方法，即“积分图像”（Integral Image），该方法使得检测器可以快速计算特征。
2. 提出了基于AdaBoost的学习算法，该算法可以从大量视觉特征中选择一个小的关键特征集，并生成非常高效的分类器。
3. 提出了一个级联分类器方法，该方法可以快速排除图像的背景区域，并将更多的计算资源分配给可能的对象区域。
积分图像（Integral Image）是一种快速计算图像特征的方法。该方法可以将图像转换为一个积分图像，然后使用积分图像计算特征。这使得检测器可以快速计算特征，从而提高检测速度。
基于AdaBoost的学习算法可以从大量视觉特征中选择一个小的关键特征集。该算法可以生成非常高效的分类器，从而提高检测速度。
级联分类器方法可以快速排除图像的背景区域，并将更多的计算资源分配给可能的对象区域。这使得检测器可以快速检测对象，从而提高检测速度。
本文档介绍了一种快速对象检测方法，该方法基于机器学习和图像处理技术，可以快速检测对象并实现高检测率。
知识点：
1. 积分图像（Integral Image）：一种快速计算图像特征的方法。
2. 基于AdaBoost的学习算法：一种可以从大量视觉特征中选择一个小的关键特征集的学习算法。
3. 级联分类器方法：一种可以快速排除图像的背景区域并将更多的计算资源分配给可能的对象区域的方法。
4. 机器学习在对象检测中的应用：机器学习可以用于对象检测，提高检测速度和检测率。
5. 图像处理技术在对象检测中的应用：图像处理技术可以用于对象检测，提高检测速度和检测率。
相关技术：
1. 对象检测（Object Detection）：一种计算机视觉技术，用于检测图像中的对象。
2. 机器学习（Machine Learning）：一种人工智能技术，用于训练机器学习模型，实现自动化检测。
3. 图像处理（Image Processing）：一种技术，用于处理和分析图像，提取图像特征。
4. 计算机视觉（Computer Vision）：一种技术，用于使机器能够看到和理解图像。
Rapid Object Detection using a Boosted Cascade
of
Simple
Features
Paul Viola
viola@merl.com
Mitsubishi Electric Research Labs
201
Broadway, 8th
FL
Cambridge,
MA
021
39
Michael Jones
michael.jones@compaq.com
Compaq Cambridge Research Lab
One
Cambridge Center
Cambridge,
MA
02142
Abstract
This paper describes a machine learning approach for vi-
sual object detection which is capable
of
processing images
extremely rapidly and achieving high detection rates. This
work is distinguished by three key contributions. The first
is
the introduction
of
a
new image representation called the
“Integral linage” which allows the features used by our de-
tector
to
be computed very quickly. The second is a learning
algorithm, based on AdaBoost, which selects a
small
num-
ber
of
critical visual features from a larger set and yields
extremely eflcient class@ers[5]. The third contribution is
a method for combining increasingly more complex classi-
jers in a “cascade” which allows background regions
of
the
image
to
be
quickly discarded while spending more compu-
tation on promising object-like regions. The cascade can be
viewed as an object specijic focus-of-attention mechanism
which unlike previous approaches provides statistical guar-
untees that discarded regions are unlikely to contain the ob-
ject of interest, In the domain
of
face detection the system
yields detection rates comparable to the best previous sys-
tems. Used in real-time applications, the detector runs at
15
frames per second without resorting to image differenc-
ing or skin color detection.
1.
Introduction
This paper brings together new algorithms and insights to
construct a framework for robust and extremely rapid object
detection. This framework is demonstrated on, and in part
motivated by, the task of face detection. Toward this end
we have constructed a frontal face detection system which
achieves detection and false positive rates which are equiv-
alent to the best published results
[
14, 11, 13,
10,
11.
This
face detection system is most clearly distinguished from
previous approaches in its ability to detect faces extremely
rapidly. Operating on 384 by
288
pixel images, faces are de-
tected at
I5
frames per second on a conventional
700
MHz
Intel Pentium 111. In other face detection systems, auxiliary
information, such as image differences in video sequences,
or pixel color
in
color images, have been used to achieve
high frame rates.
Our system achieves high frame rates
working only with the information present in a single grey
scale image. These alternative sources of information can
also be integrated with
our
system to achieve even higher
frame rates.
There are three main contributions of
our
object detec-
tion framework. We will introduce each of these ideas
briefly below and then describe them in detail in subsequent
sections.
The first contribution
of
this paper is a new image repre-
sentation called an
integral image
that allows for very fast
feature evaluation. Motivated
in
part by the work of Papa-
georgiou et al. our detection system does not work directly
with image intensities
[9].
Like these authors we use a set
of features which are reminiscent of Haar Basis functions
(though we will also use related filters which are more com-
plex than Haar filters). In order to compute these features
very rapidly at many scales we introduce the integral im-
age representation for images. The integral image can be
computed from an image using a few operations per pixel.
Once computed, any one of these Harr-like features can be
computed at any scale or location in
constant
time.
The second contribution of this paper is a method for
constructing a classifier by selecting a small number of im-
portant features using AdaBoost
[5].
Within any image sub-
window the total number of Harr-like features
is
very large,
far larger than the number
of
pixels. In order to ensure fast
classification, the learning process must exclude a large ma-
jority of the available features, and focus on a small set of
critical features. Motivated by the work
of
Tieu and Viola,
feature selection is achieved through a simple modification
of the Adal3oost procedure: the weak learner is constrained
so
that each weak classifier returned can depend on only a
single feature
[
151.
As a result each stage of the boosting
process, which selects a new weak classifier, can be viewed
as a feature selection process. Adal3oost provides an effec-
tive learning algorithm and strong bounds on generalization
performance [12,8,9].
The third major contribution of this paper is a method
for combining successively more complex classifiers in a
cascade structure which dramatically increases the speed of
0-7695-1272-0/01
$10.00
0
2001
EEE
1-5
11
下载后可阅读完整内容，剩余7页未读，立即下载
2013-10-28 上传
2013-06-14 上传
2009-03-27 上传
2021-06-11 上传
2021-06-16 上传
2024-11-07 上传
2024-11-07 上传
大姨妈V
- 粉丝: 858
- 资源: 16
我的内容管理
展开
最新资源
- 探索数据转换实验平台在设备装置中的应用
- 使用git-log-to-tikz.py将Git日志转换为TIKZ图形
- 小栗子源码2.9.3版本发布
- 使用Tinder-Hack-Client实现Tinder API交互
- Android Studio新模板：个性化Material Design导航抽屉
- React API分页模块：数据获取与页面管理
- C语言实现顺序表的动态分配方法
- 光催化分解水产氢固溶体催化剂制备技术揭秘
- VS2013环境下tinyxml库的32位与64位编译指南
- 网易云歌词情感分析系统实现与架构
- React应用展示GitHub用户详细信息及项目分析
- LayUI2.1.6帮助文档API功能详解
- 全栈开发实现的chatgpt应用可打包小程序/H5/App
- C++实现顺序表的动态内存分配技术
- Java制作水果格斗游戏：策略与随机性的结合
- 基于若依框架的后台管理系统开发实例解析
