• Home
  • Search
  • Pedestrian attribute recognition in elevator
  • Cite Icon2
  • https://doi.org/10.1109/icaica54878.2022.9844591Copy DOI Icon

Pedestrian attribute recognition in elevator

  • Jun 24, 2022
  • Pengyuan Zhang +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recognizing pedestrian attributes in elevator video surveillance plays a critical role in community safety and business decision. Existing methods have paid little attention to such scenarios, in which the essential facial information usually cannot be obtained and used for recognizing pedestrian attributes. Considering that low-level attributes have strong correlations with high-level attributes, e.g., gender can be predicted with the combination of hair length and dressing style, in this paper, we constructed a large multi-label dataset for pedestrian attribute recognition in elevator and proposed an end-to-end multi-label model to improve attribute recognition. This model consists of 1) channel attention mechanism, which was used to ignore the irrelevant background information, 2) local feature blocks extraction which can fully extract the local feature of the image, 3) multiple classifiers which can accelerate the speed of reasoning by avoiding repeated computation of features in the shared layer. In the inference stage, we used FPN and feature map dimensionality reduction to predict attributes. Compared with the baseline model, the performances on our dataset and the other two large-scale pedestrian attribute datasets, i.e., PETA and MarKet1501, demonstrate the effectiveness of the proposed method.

Similar Papers
  • Book Chapter
  • Citations5

Research on Pedestrian Attribute Recognition Based on Semantic Segmentation in Natural Scene

  • Jan 01, 2019
  • Xin Feng +3
  • PDF
  • Research Article
  • Citations36

Attention Based CNN-ConvLSTM for Pedestrian Attribute Recognition.

  • Feb 03, 2020
  • Sensors (Basel, Switzerland)
  • Yang Li +3
  • Research Article
  • Citations10

A novel self-boosting dual-branch model for pedestrian attribute recognition

  • Apr 14, 2023
  • Signal Processing: Image Communication
  • Yilu Cao +5
  • Conference Article
  • Citations322

Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios

  • Nov 01, 2015
  • Dangwei Li +2
  • Research Article
  • Citations4

Attribute-Guided Global and Part-Level Identity Network for Person Re-Identification

  • May 12, 2022
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Shaoming Pan +2
  • Conference Article
  • Citations61

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

  • Jan 01, 2017
  • Yang Zhou +5
  • Research Article
  • Citations1

Person Re-identification Based on Attribute Hierarchy Recognition

  • Sep 10, 2019
  • 电子与信息学报
  • Hongchang Chen +3
  • Conference Article
  • Citations23

Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations

  • Jan 01, 2018
  • Yiqiang Chen +4
  • Conference Article
  • Citations173

Attribute Recognition by Joint Recurrent Learning of Context and Correlation

  • Oct 01, 2017
  • Jingya Wang +3
  • Research Article
  • Citations11

Pedestrian re‐identification based on attribute mining and reasoning

  • Apr 26, 2021
  • IET Image Processing
  • Chao Li +5
  • Conference Article
  • Citations154

Pose Guided Deep Model for Pedestrian Attribute Recognition in Surveillance Scenarios

  • Jul 01, 2018
  • Dangwei Li +3
  • Conference Article
  • Citations11

Robust pedestrian attribute recognition for an unbalanced dataset using mini-batch training with rarity rate

  • Jun 01, 2016
  • Hiroshi Fukui +4
  • Conference Article
  • Citations8

Hierarchical pedestrian attribute recognition based on adaptive region localization

  • Jul 01, 2017
  • Chunfeng Yao +3
  • PDF
  • Research Article
  • Citations10

Pedestrian Attribute Analysis Using Agent-Based Modeling

  • Jul 16, 2020
  • Applied Sciences
  • Khaled Shaaban +1
  • Research Article
  • Citations32

Pedestrian attribute recognition based on multiple time steps attention

  • Jul 13, 2020
  • Pattern Recognition Letters
  • Zhong Ji +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.