Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/154607
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, Pengyuen_US
dc.date.accessioned2022-01-03T05:53:50Z-
dc.date.available2022-01-03T05:53:50Z-
dc.date.issued2021-
dc.identifier.citationChen, P. (2021). Crowd counting for intelligent video surveillance. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/154607en_US
dc.identifier.urihttps://hdl.handle.net/10356/154607-
dc.description.abstractSurveillance plays an important role in maintaining public safety. Especially under the situation of COVID-19 recently, the flow of people needs to be monitored and strictly controlled at any time. However, this work usually costs plenty of time for humans to observe. Meanwhile, it is difficult to make an accurate estimation for crowds, especially in complex scenes. Fortunately, machine vision is an advanced technology that can help us complete this time-consuming task. With the rise of convolutional neural networks and deep learning, visual detectors can distinguish more types of objects, and they also have a wider range of applications. Meanwhile, the performance of these detectors has gradually improved, making it possible to use surveillance cameras to complete crowd detection tasks simultaneously. The video can be processed frame-by-frame as an image, and then the detector can automatically output prediction data, such as the total number of people, their faces’ locations and sizes, etc. In this dissertation, several object detection methods and the basic principles of the convolutional neural network are briefly introduced as fundamental knowledge. Besides, a simple and effective network with some modifications is discussed as the baseline of our method. Meanwhile, a self-training approach that enables the network to be trained using only point-level annotations is also introduced. Our method proposes to combine this training approach with the baseline to benefit from their powerful error correction and crowd analysis capabilities. Experimental results on the NWPU dataset show that our method is effective in crowd counting, crowd localization, and size prediction tasks.en_US
dc.language.isoenen_US
dc.publisherNanyang Technological Universityen_US
dc.subjectEngineering::Computer science and engineering::Computing methodologies::Pattern recognitionen_US
dc.subjectEngineering::Computer science and engineering::Computing methodologies::Image processing and computer visionen_US
dc.titleCrowd counting for intelligent video surveillanceen_US
dc.typeThesis-Master by Courseworken_US
dc.contributor.supervisorLap-Pui Chauen_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.degreeMaster of Science (Computer Control and Automation)en_US
dc.contributor.supervisoremailelpchau@ntu.edu.sgen_US
item.grantfulltextrestricted-
item.fulltextWith Fulltext-
Appears in Collections:EEE Theses
Files in This Item:
File Description SizeFormat 
Crowd Counting for Intelligent Video Surveillance_Chen Pengyu_final.pdf
  Restricted Access
28.73 MBAdobe PDFView/Open

Page view(s)

53
Updated on Jun 27, 2022

Download(s)

9
Updated on Jun 27, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.