HOG特征：人像检测的强大工具

5星 · 超过95%的资源需积分: 45 90 浏览量更新于2024-09-16 收藏 445KB PDF 举报

在"Histograms of Oriented Gradients for Human Detection"（HOG：梯度方向直方图的人体检测）一文中，作者Navneet Dalal和Bill Triggs探讨了在视觉对象识别任务中，特别是人体检测方面，特征集选择的重要性。他们选择基于线性支持向量机（SVM）的人体检测作为实验案例，对现有基于边缘和梯度的描述符进行了深入评估。论文首先回顾了当时的边缘检测和梯度描述符技术，发现这些方法在人体检测中的性能有限。他们随后提出了一种创新的特征表示方法——HOG，即通过将图像划分为小的局部区域，计算每个区域内像素梯度的方向直方图。HOG的优势在于它能捕捉到物体在不同方向上的纹理模式，即使在光照变化或物体姿态不同时也能保持一定的稳健性。在论文中，作者详细研究了HOG计算过程中的各个步骤对性能的影响。他们强调了以下几个关键环节的重要性： 1. **精细尺度的梯度信息**：HOG依赖于高分辨率图像上的梯度，这有助于捕捉细节特征，增强对目标物体的识别能力。 2. **精细的取向归一化**：通过将梯度方向细分为多个区间，HOG可以更精确地描述物体表面的纹理方向分布。 3. **相对粗粒度的空间划分**：虽然HOG关注细节，但空间上的粗略划分有助于减少计算复杂度，提高检测速度。 4. **高质量的局部对比度归一化**：通过对相邻描述符块进行对比，HOG能够抑制背景噪声，突出目标物体的特性。通过实验，HOG在原始的MIT行人数据库上表现出接近完美的识别性能。为了进一步验证其泛化能力，作者还引入了一个更具挑战性的数据集，包含超过1800张标注的人体图像，涵盖了更广泛的姿势变化和背景环境。这个新数据集的引入展示了HOG在实际复杂场景下依然保持强大性能的特点。总结来说，"Histograms of Oriented Gradients for Human Detection"是一篇开创性的研究，它不仅介绍了HOG作为一种高效的人体检测特征表示方法，而且深入分析了其背后的理论与实践细节，为后续的计算机视觉领域尤其是目标检测领域的研究者提供了宝贵的参考。HOG的出现极大地推动了实时、鲁棒的人体检测技术的发展，并且成为了众多现代物体检测算法的基础组件。

Histograms of Oriented Gradients for Human Detection

Navneet Dalal and Bill Triggs

INRIA Rhˆone-Alps, 655 avenue de l’Europe, Montbonnot 38334, France

{Navneet.Dalal,Bill.Triggs}@inrialpes.fr, http://lear.inrialpes.fr

Abstract

We study the question of feature sets for robust visual ob-

ject recognition, adopting linear SVM based human detec-

tion as a test case. After reviewing existing edge and gra-

dient based descriptors, we show experimentally that grids

of Histograms of Oriented Gradient (HOG) descriptors sig-

niﬁcantly outperform existing feature sets for human detec-

tion. We study the inﬂuence of each stage of the computation

on performance, concluding that ﬁne-scale gradients, ﬁne

orientation binning, relatively coarse spatial binning, and

high-quality local contrast normalization in overlapping de-

scriptor blocks are all important for good results. The new

approach gives near-perfect separation on the original MIT

pedestrian database, so we introduce a more challenging

dataset containing over 1800 annotated human images with

a large range of pose variations and backgrounds.

1 Introduction

Detecting humans in images is a challenging task owing

to their variable appearance and the wide range of poses that

they can adopt. The ﬁrst need is a robust feature set that

allows the human form to be discriminated cleanly, even in

cluttered backgrounds under difﬁcult illumination. We study

the issue of feature sets for human detection, showing that lo-

cally normalized Histogram of Oriented Gradient (HOG) de-

scriptors provide excellent performance relative to other ex-

isting feature sets including wavelets [17,22]. The proposed

descriptors are reminiscent of edge orientation histograms

[4,5], SIFT descriptors [12] and shape contexts [1], but they

are computed on a dense grid of uniformly spaced cells and

they use overlapping local contrast normalizations for im-

proved performance. We make a detailed study of the effects

of various implementation choices on detector performance,

taking “pedestrian detection” (the detection of mostly visible

people in more or less upright poses) as a test case. For sim-

plicity and speed, we use linear SVM as a baseline classiﬁer

throughout the study. The new detectors give essentially per-

fect results on the MIT pedestrian test set [18,17], so we have

created a more challenging set containing over 1800 pedes-

trian images with a large range of poses and backgrounds.

Ongoing work suggests that our feature set performs equally

well for other shape-based object classes.

We brieﬂy discuss previous work on human detection in

§2, give an overview of our method §3, describe our data

sets in §4 and give a detailed description and experimental

evaluation of each stage of the process in §5–6. The main

conclusions are summarized in §7.

2 Previous Work

There is an extensive literature on object detection, but

here we mention just a few relevant papers on human detec-

tion [18,17,22,16,20]. See [6] for a survey. Papageorgiou et

al [18] describe a pedestrian detector based on a polynomial

SVM using rectiﬁed Haar wavelets as input descriptors, with

a parts (subwindow) based variant in [17]. Depoortere et al

give an optimized version of this [2]. Gavrila & Philomen

[8] take a more direct approach, extracting edge images and

matching them to a set of learned exemplars using chamfer

distance. This has been used in a practical real-time pedes-

trian detection system [7]. Viola et al [22] build an efﬁcient

moving person detector, using AdaBoost to train a chain of

progressively more complex region rejection rules based on

Haar-like wavelets and space-time differences. Ronfard et

al [19] build an articulated body detector by incorporating

SVM based limb classiﬁers over 1

and 2

order Gaussian

ﬁlters in a dynamic programming framework similar to those

of Felzenszwalb & Huttenlocher [3] and Ioffe & Forsyth

[9]. Mikolajczyk et al [16] use combinations of orientation-

position histograms with binary-thresholded gradient magni-

tudes to build a parts based method containing detectors for

faces, heads, and front and side proﬁles of upper and lower

body parts. In contrast, our detector uses a simpler archi-

tecture with a single detection window, but appears to give

signiﬁcantly higher performance on pedestrian images.

3 Overview of the Method

This section gives an overview of our feature extraction

chain, which is summarized in ﬁg. 1. Implementation details

are postponed until §6. The method is based on evaluating

well-normalized local histograms of image gradient orienta-

tions in a dense grid. Similar features have seen increasing

use over the past decade [4,5,12,15]. The basic idea is that

local object appearance and shape can often be characterized

rather well by the distribution of local intensity gradients or

下载后可阅读完整内容，剩余7页未读，立即下载

天天向上的金牛

粉丝: 57
资源: 2

HOG特征：人像检测的强大工具

论文解读《Histograms of Oriented Gradients for Human Detection》.pdf

Histograms of Oriented Gradients for Human Detection论文

计算方向梯度直方图，基于经典论文Histograms of Oriented Gradients for Human Detection

HOG--Histograms of Oriented Gradients for Human Detection.

[2005 CVPR] Histograms of Oriented Gradients for Human Detection

人体检测梯度方向直方图 Histograms of Oriented Gradients for Human Detection

hogsvmmatlab代码-objective-detection-source:目标检测源

histogramofgradients-120212033438-phpapp02.rar_hog_human

基于java的化妆品配方及工艺管理系统的开题报告.docx

vue chrome 扩展模板.zip

最新资源