Deep Multi-Task Network for Learning Person Identity and Attributes

Ahmed

2021

SN COMPUT. SCI.

Video surveillance is ubiquitous. In addition to understanding various scene objects, extracting human visual attributes from the scene has attracted tremendous traction over the past many years. This is a challenging problem even for human observers. This is a multi-label problem, i.e., a subject in a scene can have multiple attributes that we are hoping to recognize, such as shoes types, clothing type, wearing some accessory, or carrying some object or not, etc. Solutions have been presented over the years and many researchers have employed convolutional neural networks (CNNs). In this work, we propose using Depthwise Separable Convolution Neural Network (DS-CNN) to solve the pedestrian attribute recognition problem. The network employs depthwise separable convolution layers (DSCL), instead of the regular 2D convolution layers. DS-CNN performs extremely well, especially with smaller datasets. In addition, with a compact network, DS-CNN reduces the number of trainable parameters while making learning efficient. We evaluated our method on two benchmark pedestrian datasets and results show improvements over the state of the art.

Section: Related Workmentioning

confidence: 99%

Depthwise Separable Convolutional Neural Networks for Pedestrian Attribute Recognition

Ahmed

2021

SN COMPUT. SCI.

“…They learn pose invariant deep person re-identification features using synthesized images. A deep CNN based method to learn partial descriptive features for efficient person feature representation is presented in [37]. They employed a pyramid spatial pooling module and reported an improvement of 2.71% on the PETA dataset over [25].…”

Section: Related Workmentioning

confidence: 99%

Pedestrian attribute recognition using two-branch trainable Gabor wavelets network

2021

PLoS ONE

Keeping an eye on pedestrians as they navigate through a scene, surveillance cameras are everywhere. 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 multi-label problem is extremely challenging even for human observers and has rightly garnered attention from the computer vision community. Towards a solution to this problem, in this paper, we adopt trainable Gabor wavelets (TGW) layers and cascade them 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 two-branch neural network where mixed layers, a combination of the TGW and convolutional layers, make up the building block of our deep neural network. We test our method on twoo challenging publicly available datasets and compare our results with state of the art.

“…They learn pose invariant deep person re-identification features using synthesized images. A deep CNN based method to learn partial descriptive features for efficient person feature representation is presented in [41] . They employed a pyramid spatial pooling module and reported an improvement of 2.71% on the PETA dataset over [29] .…”

Section: Related Workmentioning

confidence: 99%

Pedestrian attribute recognition using trainable Gabor wavelets

Ahmed

Lataifeh

2021

Heliyon

Surveillance cameras are everywhere keeping an eye on pedestrians or people as they navigate through the scene. Within this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails the extraction of different attributes such as age-group, clothing style, accessories, footwear style etc. This is a multi-label problem with a host of challenges even for human observers. As such, the topic has rightly attracted attention recently. In this work, we integrate trainable Gabor wavelet (TGW) layers inside a convolution neural network (CNN). Whereas other researchers have used fixed Gabor filters with the CNN, the proposed layers are learnable and adapt to the dataset for a better recognition. We test our method on publicly available challenging datasets and demonstrate considerable improvements over state of the art approaches.