Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios
Pedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. I...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-11-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/11/11/245 |
| _version_ | 1818945604509761536 |
|---|---|
| author | Xiangpeng Song Hongbin Yang Congcong Zhou |
| author_facet | Xiangpeng Song Hongbin Yang Congcong Zhou |
| author_sort | Xiangpeng Song |
| collection | DOAJ |
| description | Pedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. It is desirable to model the label dependencies between different attributes to improve the recognition performance as each pedestrian normally possesses many attributes. In this paper, we treat pedestrian attribute recognition as multi-label classification and propose a novel model based on the graph convolutional network (GCN). The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian feature, which is a normal operation processing image in deep learning, then we transfer attribute labels to word embedding and construct a correlation matrix between labels to help GCN propagate information between nodes. This paper applies the object classifiers learned by GCN to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable. Experiments on pedestrian attribute recognition dataset show that the approach obviously outperforms other existing state-of-the-art methods. |
| first_indexed | 2024-12-20T08:01:45Z |
| format | Article |
| id | doaj.art-e10f892659be49688f878b3ed2f46335 |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-12-20T08:01:45Z |
| publishDate | 2019-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-e10f892659be49688f878b3ed2f463352022-12-21T19:47:30ZengMDPI AGFuture Internet1999-59032019-11-01111124510.3390/fi11110245fi11110245Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance ScenariosXiangpeng Song0Hongbin Yang1Congcong Zhou2School of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaPedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. It is desirable to model the label dependencies between different attributes to improve the recognition performance as each pedestrian normally possesses many attributes. In this paper, we treat pedestrian attribute recognition as multi-label classification and propose a novel model based on the graph convolutional network (GCN). The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian feature, which is a normal operation processing image in deep learning, then we transfer attribute labels to word embedding and construct a correlation matrix between labels to help GCN propagate information between nodes. This paper applies the object classifiers learned by GCN to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable. Experiments on pedestrian attribute recognition dataset show that the approach obviously outperforms other existing state-of-the-art methods.https://www.mdpi.com/1999-5903/11/11/245pedestrian attribute recognitiongraph convolutional networkmulti-label learning |
| spellingShingle | Xiangpeng Song Hongbin Yang Congcong Zhou Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios Future Internet pedestrian attribute recognition graph convolutional network multi-label learning |
| title | Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios |
| title_full | Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios |
| title_fullStr | Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios |
| title_full_unstemmed | Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios |
| title_short | Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios |
| title_sort | pedestrian attribute recognition with graph convolutional network in surveillance scenarios |
| topic | pedestrian attribute recognition graph convolutional network multi-label learning |
| url | https://www.mdpi.com/1999-5903/11/11/245 |
| work_keys_str_mv | AT xiangpengsong pedestrianattributerecognitionwithgraphconvolutionalnetworkinsurveillancescenarios AT hongbinyang pedestrianattributerecognitionwithgraphconvolutionalnetworkinsurveillancescenarios AT congcongzhou pedestrianattributerecognitionwithgraphconvolutionalnetworkinsurveillancescenarios |