Show simple item record

dc.contributor.advisorWang, Guanghui
dc.contributor.authorSajid, Usman
dc.date.accessioned2019-11-01T01:15:32Z
dc.date.available2019-11-01T01:15:32Z
dc.date.issued2019-05-31
dc.date.submitted2019
dc.identifier.otherhttp://dissertations.umi.com/ku:16563
dc.identifier.urihttp://hdl.handle.net/1808/29710
dc.description.abstractAs people gather during different social, political or musical events, automated crowd analysis can lead to effective and better management of such events to prevent any unwanted scene as well as avoid political manipulation of crowd numbers. Crowd counting remains an integral part of crowd analysis and also an active research area in the field of computer vision. Existing methods fail to perform where crowd density is either too high or too low in an image, thus resulting in either overestimation or underestimation. These methods also mix crowd-like cluttered background regions (e.g. tree leaves or small and continuous patterns) in images with actual crowd, resulting in further crowd overestimation. In this work, we present a novel deep convolutional neural network (CNN) based framework ZiZoNet for automated crowd counting in static images in very low to very high crowd density scenarios to address above issues. ZiZoNet consists of three modules namely Crowd Density Classifier (CDC), Decision Module (DM) and Count Regressor Module (CRM). The test image, divided into 224x224 patches, passes through the CDC module that classifies each patch to a class label (no-crowd, low-crowd, medium-crowd, high-crowd). Based on the CDC information and using either heuristic Rule-set Engine (RSE) or machine learning based Random Forest based Decision Block (RFDB), DM decides which mode (zoom-in, normal or zoom-out) this image should use for crowd counting. CRM then performs patch-wise crowd estimate for this image accordingly as decided or instructed by the DM module. Extensive experiments on three diverse and challenging crowd counting benchmarks (UCF-QNRF, ShanghaiTech, AHU-Crowd) show that our method outperforms current state-of-the-art models under most of the evaluation criteria.
dc.format.extent54 pages
dc.language.isoen
dc.publisherUniversity of Kansas
dc.rightsCopyright held by the author.
dc.subjectComputer science
dc.subjectdeep learning
dc.subjectdensenet
dc.subjectmachine learning
dc.titleZiZoNet: A Zoom-In and Zoom-Out Mechanism for Crowd Counting in Static Images
dc.typeThesis
dc.contributor.cmtememberLuo, Bo
dc.contributor.cmtememberYun, Heechul
dc.thesis.degreeDisciplineElectrical Engineering & Computer Science
dc.thesis.degreeLevelM.S.
dc.identifier.orcidhttps://orcid.org/0000-0002-2443-5215
dc.rights.accessrightsopenAccess


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record