Summary of Pedestrian Traffic Statistics Research
Authors:
- 9 November 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 43-47
Abstract
As an important research direction in the field of computer vision and intelligent security, pedestrian traffic statistics have received more and more attention from the industry. This paper reviews the research on the important aspects of pedestrian flow statistics technology: feature extraction, target detection and pedestrian counting. Firstly, the typical methods of feature extraction are classified and compared according to the characteristics, and then the research on target detection and recognition is carried out. After summarizing, the pedestrian target count is introduced from the traditional method and the deep learning method respectively, and finally the future development is expected.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 11 references indexed in Scilit:
- End-to-End Representation Learning for Correlation Filter Based Tracking2017
- ECO: Efficient Convolution Operators for Tracking2017
- Multi-task Correlation Particle Filter for Robust Object Tracking2017
- Spatially supervised recurrent convolutional neural networks for visual object tracking2017
- Learning Multi-domain Convolutional Neural Networks for Visual Tracking2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Recurrently Target-Attending Tracking2016
- Visual Tracking with Fully Convolutional Networks2015
- Fast R-CNN2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014