Home
Resource
Exploiting multispectral and contextual information to improve human detection
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(9.63 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Liu, Jingjing. Exploiting multispectral and contextual information to improve human detection. Retrieved from https://doi.org/doi:10.7282/T3MC935C

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleExploiting multispectral and contextual information to improve human detection
NameLiu, Jingjing (author); Metaxas, Dimitris N. (chair); Bekris, Kostas (internal member); Yu, Jingjin (internal member); Ratha, Nalini K. (outside member); Rutgers University; School of Graduate Studies
Date Created2017
Other Date2017-10 (degree)
SubjectComputer Science, Robotics--Human factors, Human-robot interaction
Extent1 online resource (xiv, 81 p. : ill.)
DescriptionHuman detection has various applications, e.g., autonomous driving car, surveillance system, and retail. In this dissertation, we first exploit multispectral images (i.e., RGB and thermal images) for human detection. We extensively analyze Faster R-CNN for the detection task and then model multispectral human detection into a fusion problem of convolutional networks (ConvNets). We design four distinct ConvNet fusion architectures that integrate two-branch ConvNets on different stages of neural networks, all of which yield better performance compared with the baseline detector. In the second part of this dissertation, we leverage instance-level contextual information in crowded scenes to boost performance of human detection. Based on a context graph that incorporates both geometric and social contextual patterns from crowds, we apply progressive potential propagation algorithm to discover weak detections that are contextually compatible with true detections while suppressing irrelevant false alarms. The method significantly improves the performance of any shallow human detectors, obtaining comparable results to deep learning based methods.
NotePh.D.
NoteIncludes bibliographical references
Noteby Jingjing Liu
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/T3MC935C
Languageeng
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024