Show simple item record

dc.contributor.advisorBeveridge, J. Ross
dc.contributor.advisorDraper, Bruce A.
dc.contributor.authorKulkarni, Hrushikesh N.
dc.contributor.committeememberPasricha, Sudeep
dc.contributor.committeememberAlciatore, David G.
dc.date.accessioned2007-01-03T06:39:32Z
dc.date.available2007-01-03T06:39:32Z
dc.date.issued2014
dc.description2014 Summer.
dc.descriptionIncludes bibliographical references.
dc.description.abstractHuman activity recognition has gathered a lot of interest. The ability to accurately detect carried objects on human beings will directly help activity recognition. This thesis performs evaluation of four different features for carried object detection. To detect carried objects, image chips in a video are extracted by tracking moving objects using an off the shelf tracker. Pixels with similar colors are grouped together by using a superpixel segmentation algorithm. Features are calculated with respect to every superpixel, encoding information regarding their location in the track chip, shape of the superpixel, pose of the person in the track chip, and appearance of the superpixel. ROC curves are used for analyzing the detection of a superpixel as a carried object using these features individually or in a combination. These ROC curves show that the detection using Shape features as they are calculated have very less information. The location features, though simple to calculate, have a significant usable information. Detection using pose of a person in the track chip and appearance of the superpixel depend largely on the data used for their calculation. Pose detections are more likely to be correct if there are no occlusions, while appearance work better if we have high resolution of input images.
dc.format.mediumborn digital
dc.format.mediummasters theses
dc.identifierKulkarni_colostate_0053N_12609.pdf
dc.identifier.urihttp://hdl.handle.net/10217/83983
dc.languageEnglish
dc.publisherColorado State University. Libraries
dc.relation.ispartof2000-2019 - CSU Theses and Dissertations
dc.rightsCopyright of the original work is retained by the author.
dc.subjectcarried object detection
dc.subjectcomputer vision
dc.subjectimage processing
dc.subjectmachine learning
dc.subjectperformance evaluation of features
dc.subjectvideo surveillance
dc.titlePerformance evaluation of feature sets for carried object detection in still images
dc.typeText
dcterms.rights.dplaThe copyright and related rights status of this item has not been evaluated (https://rightsstatements.org/vocab/CNE/1.0/). Please refer to the organization that has made the Item available for more information.
thesis.degree.disciplineElectrical and Computer Engineering
thesis.degree.grantorColorado State University
thesis.degree.levelMasters
thesis.degree.nameMaster of Science (M.S.)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record