Jointly human semantic parsing and attribute recognition with feature pyramid structure in EfficientNets
Authors:
Open Access
- 1 April 2021
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 15 (10) , 2281-2291
Abstract
Pedestrian attributes recognition is an important issue in computer vision and has a special role in the field of video surveillance. The previous methods presented to solve this issue are mainly based on multi‐label end‐to‐end deep neural networks. These methods neglect to apply attributes for defining local feature areas and they suffer from the problems of the bounding box presence. A new framework for jointly human semantic parsing and pedestrian attribute recognition to achieve effective attribute recognition is proposed. By extracting human parts via semantic parsing, both semantic and spatial information can be explored with eliminating of background. The framework also uses multi‐scale features to employ rich details and contextual information through proposed attribute recognition‐bidirectional feature pyramid network. For baseline network that has a significant impact on the performance, EfficientNet‐B3 is selected as a baseline network from The EfficientNet family which provides an appropriate trade‐off between the three factors of CNNs scaling (depth/width/resolution). Finally, the proposed framework is tested on datasets PETA, RAP and PA‐100k. Experimental results show that our method has superior performance in both mean accuracy and instance‐based metrics compared to state‐of‐the‐art results.Keywords
This publication has 29 references indexed in Scilit:
- Joint Multi-person Pose Estimation and Semantic Part Segmentation2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns2016
- Person Attribute Recognition with a Jointly-Trained Holistic CNN Model2015
- Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios2015
- Multi-Task CNN Model for Attribute PredictionIEEE Transactions on Multimedia, 2015
- Multi-label CNN based pedestrian attribute learning for soft biometrics2015
- Pedestrian Attribute Recognition At Far Distance2014
- Edge Boxes: Locating Object Proposals from Edges2014
- Pedestrian Attribute Classification in Surveillance: Database and Evaluation2013