A Human Pose Estimated Method Based on a Deep Convolutional Neural Network

A Human Pose Estimated Method Based on a Deep Convolutional Neural Network

碩士 === 國立臺灣科技大學 === 電子工程系 === 104 === The human pose estimation is an emerging research topic in the area of computer vision, which has many particular applications including automated surveillance systems, interactive human machine interfaces, and video-based pose recognitions. The human pose estim...

Full description

Bibliographic Details
Main Authors: Hui-Chuan Chang, 張惠娟
Other Authors: Shanq-Jang Ruan
Format: Others
Language:en_US
Published: 2016
Online Access:http://ndltd.ncl.edu.tw/handle/87060509825002077664
id ndltd-TW-104NTUS5428141
record_format oai_dc
spelling ndltd-TW-104NTUS54281412017-09-24T04:40:50Z http://ndltd.ncl.edu.tw/handle/87060509825002077664 A Human Pose Estimated Method Based on a Deep Convolutional Neural Network 基於卷積類神經網路之人體骨架預測方法 Hui-Chuan Chang 張惠娟 碩士 國立臺灣科技大學 電子工程系 104 The human pose estimation is an emerging research topic in the area of computer vision, which has many particular applications including automated surveillance systems, interactive human machine interfaces, and video-based pose recognitions. The human pose estimation is an advanced localization technique, of which implementation is beyond the object detection because of the possibility of articulated human body and various occlusions. We inherent the structure the Convol-utional Pose Machine.In order to get the accurate localization of the human joints, this study implements a convolution neural network to model the features in human pose training images by operating different-sized kernels to acquire the optimum features. Then, the trained model is utilized to localize the human joints within the test images after segmenting the foreground through the ViBe technique. Shanq-Jang Ruan 阮聖彰 2016 學位論文 ; thesis 49 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立臺灣科技大學 === 電子工程系 === 104 === The human pose estimation is an emerging research topic in the area of computer vision, which has many particular applications including automated surveillance systems, interactive human machine interfaces, and video-based pose recognitions. The human pose estimation is an advanced localization technique, of which implementation is beyond the object detection because of the possibility of articulated human body and various occlusions. We inherent the structure the Convol-utional Pose Machine.In order to get the accurate localization of the human joints, this study implements a convolution neural network to model the features in human pose training images by operating different-sized kernels to acquire the optimum features. Then, the trained model is utilized to localize the human joints within the test images after segmenting the foreground through the ViBe technique.
author2 Shanq-Jang Ruan
author_facet Shanq-Jang Ruan
Hui-Chuan Chang
張惠娟
author Hui-Chuan Chang
張惠娟
spellingShingle Hui-Chuan Chang
張惠娟
A Human Pose Estimated Method Based on a Deep Convolutional Neural Network
author_sort Hui-Chuan Chang
title A Human Pose Estimated Method Based on a Deep Convolutional Neural Network
title_short A Human Pose Estimated Method Based on a Deep Convolutional Neural Network
title_full A Human Pose Estimated Method Based on a Deep Convolutional Neural Network
title_fullStr A Human Pose Estimated Method Based on a Deep Convolutional Neural Network
title_full_unstemmed A Human Pose Estimated Method Based on a Deep Convolutional Neural Network
title_sort human pose estimated method based on a deep convolutional neural network
publishDate 2016
url http://ndltd.ncl.edu.tw/handle/87060509825002077664
work_keys_str_mv AT huichuanchang ahumanposeestimatedmethodbasedonadeepconvolutionalneuralnetwork
AT zhānghuìjuān ahumanposeestimatedmethodbasedonadeepconvolutionalneuralnetwork
AT huichuanchang jīyújuǎnjīlèishénjīngwǎnglùzhīréntǐgǔjiàyùcèfāngfǎ
AT zhānghuìjuān jīyújuǎnjīlèishénjīngwǎnglùzhīréntǐgǔjiàyùcèfāngfǎ
AT huichuanchang humanposeestimatedmethodbasedonadeepconvolutionalneuralnetwork
AT zhānghuìjuān humanposeestimatedmethodbasedonadeepconvolutionalneuralnetwork
_version_ 1718540292084203520

Similar Items