The Deeper, the Better: Analysis of Person Attributes Recognition

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 employed a pyramid spatial pooling module and reported an improvement of 2.71% on the PETA dataset over [25]. [38] improved over [25] by employing a deeper network based on a context sensitive framework. The proposed network improved generalization and classification accuracy by creating a richer feature sets using deeper residual networks (ResNet) and achieved the best in class results on attribute recognition datasets.…”

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 report an improvement of 2.71% on the PETA dataset over [24]. A context sensitive framework using a deeper network to improve classification accuracy and generalization is presented by [36]. They improve over [24] by creating a richer feature sets using deeper residual networks (ResNet) that could achieve the best in class results on attribute recognition datasets.…”

Section: Related Workmentioning

confidence: 99%

A multi-branch separable convolution neural network for pedestrian attribute recognition

Ahmed

2020

Heliyon

Video surveillance applications have made great strides in making the world a safer place. Extracting visual attributes from a scene, such as the type of shoes, the type of clothing, carrying any object or not, or wearing any accessory etc., is a challenging problem and an efficient solution holds the key to a great number of applications. In this paper, we present a multi-branch convolutional neural network that uses depthwise separable convolution (DSC) layers to solve the pedestrian attribute recognition problem. Researchers have proposed various solutions over the years making use of convolutional neural networks (CNN), however, we introduce DSC layers to the CNN for the problem of pedestrian attribute recognition. In addition, we make a novel use of the different color spaces and create a 3-branch CNN, denoted as 3bCNN, that is efficient, especially with smaller datasets. We experiment on two benchmark datasets and show results with improvement over the state of the art.