Vehicle Pose Transform by Generative Adversarial Network for Re-Identification

碩士 === 國立中正大學 === 資訊工程研究所 === 107 === Vehicle Re-identification (Re-ID) is an major task that seeks a query vehicleimage from the gallery image dataset and it has the huge potential to contribute tothe intelligent video surveillance. However, the pose variation of vehicle images isone of the key ch...

Full description

Bibliographic Details
Main Authors:	HU, CHAN-SHUO, 胡展碩
Other Authors:	CHIANG, CHEN-KUO
Format:	Others
Language:	en_US
Published:	2019
Online Access:	http://ndltd.ncl.edu.tw/handle/ev7rhw

id	ndltd-TW-107CCU00392045
record_format	oai_dc
spelling	ndltd-TW-107CCU003920452019-11-01T05:28:37Z http://ndltd.ncl.edu.tw/handle/ev7rhw Vehicle Pose Transform by Generative Adversarial Network for Re-Identification 基於生成對抗網路之車輛面向轉換識別方法 HU, CHAN-SHUO 胡展碩碩士國立中正大學資訊工程研究所 107 Vehicle Re-identification (Re-ID) is an major task that seeks a query vehicleimage from the gallery image dataset and it has the huge potential to contribute tothe intelligent video surveillance. However, the pose variation of vehicle images isone of the key challenges. Same vehicle identities with different viewpoint usuallyhave large discrepancy. In this paper, we propose a method based on GenerativeAdversarial Networks (GANs) to generate fake images that have the same viewpointto solve the different pose problem. Our model first extracts identity-related andpose-unrelated representations from input images and then concatenates the repre-sentation with the pose information to generate the fake image with the assignedpose to deal with the pose variation problem. CHIANG, CHEN-KUO 江振國 2019 學位論文 ; thesis 30 en_US
collection	NDLTD
language	en_US
format	Others
sources	NDLTD
description	碩士 === 國立中正大學 === 資訊工程研究所 === 107 === Vehicle Re-identification (Re-ID) is an major task that seeks a query vehicleimage from the gallery image dataset and it has the huge potential to contribute tothe intelligent video surveillance. However, the pose variation of vehicle images isone of the key challenges. Same vehicle identities with different viewpoint usuallyhave large discrepancy. In this paper, we propose a method based on GenerativeAdversarial Networks (GANs) to generate fake images that have the same viewpointto solve the different pose problem. Our model first extracts identity-related andpose-unrelated representations from input images and then concatenates the repre-sentation with the pose information to generate the fake image with the assignedpose to deal with the pose variation problem.
author2	CHIANG, CHEN-KUO
author_facet	CHIANG, CHEN-KUO HU, CHAN-SHUO 胡展碩
author	HU, CHAN-SHUO 胡展碩
spellingShingle	HU, CHAN-SHUO 胡展碩 Vehicle Pose Transform by Generative Adversarial Network for Re-Identification
author_sort	HU, CHAN-SHUO
title	Vehicle Pose Transform by Generative Adversarial Network for Re-Identification
title_short	Vehicle Pose Transform by Generative Adversarial Network for Re-Identification
title_full	Vehicle Pose Transform by Generative Adversarial Network for Re-Identification
title_fullStr	Vehicle Pose Transform by Generative Adversarial Network for Re-Identification
title_full_unstemmed	Vehicle Pose Transform by Generative Adversarial Network for Re-Identification
title_sort	vehicle pose transform by generative adversarial network for re-identification
publishDate	2019
url	http://ndltd.ncl.edu.tw/handle/ev7rhw
work_keys_str_mv	AT huchanshuo vehicleposetransformbygenerativeadversarialnetworkforreidentification AT húzhǎnshuò vehicleposetransformbygenerativeadversarialnetworkforreidentification AT huchanshuo jīyúshēngchéngduìkàngwǎnglùzhīchēliàngmiànxiàngzhuǎnhuànshíbiéfāngfǎ AT húzhǎnshuò jīyúshēngchéngduìkàngwǎnglùzhīchēliàngmiànxiàngzhuǎnhuànshíbiéfāngfǎ
_version_	1719285069844054016

Vehicle Pose Transform by Generative Adversarial Network for Re-Identification

Similar Items