Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition
Surveillance cameras are everywhere, keeping an eye on pedestrians as they navigate through a scene. With this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails recognizing attributes such as age-group, clothing style, accessories, footwear styl...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9360746/ |
| _version_ | 1818663170609250304 |
|---|---|
| author | Imran N. Junejo |
| author_facet | Imran N. Junejo |
| author_sort | Imran N. Junejo |
| collection | DOAJ |
| description | Surveillance cameras are everywhere, keeping an eye on pedestrians as they navigate through a scene. With this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails recognizing attributes such as age-group, clothing style, accessories, footwear style etc. This is a multi-label problem and challenging even for human observers. The problem has rightly attracted attention recently from the computer vision community. In this paper, we adopt trainable Gabor wavelets (TGW) layers and use it with a convolution neural network (CNN). Whereas other researchers are using fixed Gabor filters with the CNN, the proposed layers are learnable and adapt to the dataset for a better recognition. We propose a multi-branch neural network where mixed-layers, a combination of the TGW and convolutional layer, make up the building block of our 3-branch deep neural network. We test our method on publicly available challenging datasets and compare our results with state of the art. |
| first_indexed | 2024-12-17T05:12:35Z |
| format | Article |
| id | doaj.art-6f3ece79127249e4b9b906f94b67c09c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T05:12:35Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6f3ece79127249e4b9b906f94b67c09c2022-12-21T22:02:12ZengIEEEIEEE Access2169-35362021-01-019400194002610.1109/ACCESS.2021.30615389360746Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute RecognitionImran N. Junejo0https://orcid.org/0000-0002-7745-7952Zayed University, Dubai, United Arab EmiratesSurveillance cameras are everywhere, keeping an eye on pedestrians as they navigate through a scene. With this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails recognizing attributes such as age-group, clothing style, accessories, footwear style etc. This is a multi-label problem and challenging even for human observers. The problem has rightly attracted attention recently from the computer vision community. In this paper, we adopt trainable Gabor wavelets (TGW) layers and use it with a convolution neural network (CNN). Whereas other researchers are using fixed Gabor filters with the CNN, the proposed layers are learnable and adapt to the dataset for a better recognition. We propose a multi-branch neural network where mixed-layers, a combination of the TGW and convolutional layer, make up the building block of our 3-branch deep neural network. We test our method on publicly available challenging datasets and compare our results with state of the art.https://ieeexplore.ieee.org/document/9360746/Computer visionpedestrian attribute recognitiondeep learning |
| spellingShingle | Imran N. Junejo Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition IEEE Access Computer vision pedestrian attribute recognition deep learning |
| title | Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition |
| title_full | Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition |
| title_fullStr | Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition |
| title_full_unstemmed | Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition |
| title_short | Multi-Branch Gabor Wavelet Layers for Pedestrian Attribute Recognition |
| title_sort | multi branch gabor wavelet layers for pedestrian attribute recognition |
| topic | Computer vision pedestrian attribute recognition deep learning |
| url | https://ieeexplore.ieee.org/document/9360746/ |
| work_keys_str_mv | AT imrannjunejo multibranchgaborwaveletlayersforpedestrianattributerecognition |