Human detection in video sequences using stereo vision

碩士 === 國立中興大學 === 電機工程學系所 === 96 === In this thesis, we focus on the detection of human bodies using two cameras. We can roughly divide this research into two steps. The first one is to obtain the stereo disparity images, which includes the calibration of cameras as preprocessing. The second step is...

Full description

Bibliographic Details
Main Authors: Lu-Wei Huang, 黃祿倭
Other Authors: 陶金旭
Format: Others
Language:zh-TW
Published: 2008
Online Access:http://ndltd.ncl.edu.tw/handle/40410211235117260528
id ndltd-TW-096NCHU5441054
record_format oai_dc
spelling ndltd-TW-096NCHU54410542016-05-09T04:13:42Z http://ndltd.ncl.edu.tw/handle/40410211235117260528 Human detection in video sequences using stereo vision 立體視覺於視訊人體偵測之應用 Lu-Wei Huang 黃祿倭 碩士 國立中興大學 電機工程學系所 96 In this thesis, we focus on the detection of human bodies using two cameras. We can roughly divide this research into two steps. The first one is to obtain the stereo disparity images, which includes the calibration of cameras as preprocessing. The second step is to detect the human regions accurately and efficiently. We extract the human regions in the images by using the fuzzy 2D histogram on the X-D plane. Then we used a scale-adaptive filter to enhance the area with an average scale for human bodies. According to the experiment results, our method can produce a segmentation region of the human shape which contains a human object in the image. And we had tracked the movements of human objects in the video sequences. 陶金旭 2008 學位論文 ; thesis 54 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立中興大學 === 電機工程學系所 === 96 === In this thesis, we focus on the detection of human bodies using two cameras. We can roughly divide this research into two steps. The first one is to obtain the stereo disparity images, which includes the calibration of cameras as preprocessing. The second step is to detect the human regions accurately and efficiently. We extract the human regions in the images by using the fuzzy 2D histogram on the X-D plane. Then we used a scale-adaptive filter to enhance the area with an average scale for human bodies. According to the experiment results, our method can produce a segmentation region of the human shape which contains a human object in the image. And we had tracked the movements of human objects in the video sequences.
author2 陶金旭
author_facet 陶金旭
Lu-Wei Huang
黃祿倭
author Lu-Wei Huang
黃祿倭
spellingShingle Lu-Wei Huang
黃祿倭
Human detection in video sequences using stereo vision
author_sort Lu-Wei Huang
title Human detection in video sequences using stereo vision
title_short Human detection in video sequences using stereo vision
title_full Human detection in video sequences using stereo vision
title_fullStr Human detection in video sequences using stereo vision
title_full_unstemmed Human detection in video sequences using stereo vision
title_sort human detection in video sequences using stereo vision
publishDate 2008
url http://ndltd.ncl.edu.tw/handle/40410211235117260528
work_keys_str_mv AT luweihuang humandetectioninvideosequencesusingstereovision
AT huánglùwō humandetectioninvideosequencesusingstereovision
AT luweihuang lìtǐshìjuéyúshìxùnréntǐzhēncèzhīyīngyòng
AT huánglùwō lìtǐshìjuéyúshìxùnréntǐzhēncèzhīyīngyòng
_version_ 1718262954571333632