Human Detection by Combining Histograms of Oriented Gradients with Global Feature
碩士 === 國立高雄第一科技大學 === 電腦與通訊工程所 === 97 === In this work, we propose an algorithm of combining Histograms of Oriented Gradients(HOG) with global feature for human detection from a non-static camera. We use AdaBoost algorithm to learn local characteristics of human based on HOG by giving massive traini...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2009
|
Online Access: | http://ndltd.ncl.edu.tw/handle/31908168846492052200 |
id |
ndltd-TW-097NKIT5650031 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-097NKIT56500312015-11-13T04:15:08Z http://ndltd.ncl.edu.tw/handle/31908168846492052200 Human Detection by Combining Histograms of Oriented Gradients with Global Feature 整合全域特徵於梯度方向直方圖之行人偵測 Hsin-Ming Tsai 蔡欣明 碩士 國立高雄第一科技大學 電腦與通訊工程所 97 In this work, we propose an algorithm of combining Histograms of Oriented Gradients(HOG) with global feature for human detection from a non-static camera. We use AdaBoost algorithm to learn local characteristics of human based on HOG by giving massive training samples. The human detector is represented by a set of selected discriminative HOG features. Since local feature is easily affected by complex backgrounds and noise, the idea of this work is to incorporate the global feature for improving the detection accuracy. Here, we adopt the head contour as the global feature. The score for evaluating the existence of the head contour is through the Chamfer distance. Furthermore, the score distributions of the pedestrian and non-pedestrian are modeled by Gaussian and Anova distributions, respectively. The combination of the human detector based on local features and head contour is achieved through the adjustment of the hyperplane of support vector machine. In the experiments, we exhibit that our proposed human detection method not only has higher detection rate but also lower false positive rate in comparison with the state-of-the-art human detector. Shih-Shinh Huang 黃世勳 2009 學位論文 ; thesis 86 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立高雄第一科技大學 === 電腦與通訊工程所 === 97 === In this work, we propose an algorithm of combining Histograms of Oriented Gradients(HOG) with global feature for human detection from a non-static camera. We use AdaBoost algorithm to learn local characteristics of human based on HOG by giving massive training samples. The human detector is represented by a set of selected discriminative HOG features. Since local feature is easily affected by complex backgrounds and noise, the idea of this work is to incorporate the global feature for improving the detection accuracy. Here, we adopt the head contour as the global feature. The score for evaluating the existence of the head contour is through the Chamfer distance. Furthermore, the score distributions of the pedestrian and non-pedestrian are modeled by Gaussian and Anova distributions, respectively. The combination of the human detector based on local features and head contour is achieved through the adjustment of the hyperplane of support vector machine. In the experiments, we exhibit that our proposed human detection method not only has higher detection rate but also lower false positive rate in comparison with the state-of-the-art human detector.
|
author2 |
Shih-Shinh Huang |
author_facet |
Shih-Shinh Huang Hsin-Ming Tsai 蔡欣明 |
author |
Hsin-Ming Tsai 蔡欣明 |
spellingShingle |
Hsin-Ming Tsai 蔡欣明 Human Detection by Combining Histograms of Oriented Gradients with Global Feature |
author_sort |
Hsin-Ming Tsai |
title |
Human Detection by Combining Histograms of Oriented Gradients with Global Feature |
title_short |
Human Detection by Combining Histograms of Oriented Gradients with Global Feature |
title_full |
Human Detection by Combining Histograms of Oriented Gradients with Global Feature |
title_fullStr |
Human Detection by Combining Histograms of Oriented Gradients with Global Feature |
title_full_unstemmed |
Human Detection by Combining Histograms of Oriented Gradients with Global Feature |
title_sort |
human detection by combining histograms of oriented gradients with global feature |
publishDate |
2009 |
url |
http://ndltd.ncl.edu.tw/handle/31908168846492052200 |
work_keys_str_mv |
AT hsinmingtsai humandetectionbycombininghistogramsoforientedgradientswithglobalfeature AT càixīnmíng humandetectionbycombininghistogramsoforientedgradientswithglobalfeature AT hsinmingtsai zhěnghéquányùtèzhēngyútīdùfāngxiàngzhífāngtúzhīxíngrénzhēncè AT càixīnmíng zhěnghéquányùtèzhēngyútīdùfāngxiàngzhífāngtúzhīxíngrénzhēncè |
_version_ |
1718130597223727104 |