Please use this identifier to cite or link to this item: https://doi.org/10.1109/AVSS.2015.7301807
Title: An end-to-end system for content-based video retrieval using behavior, actions, and appearance with interactive query refinement
Authors: Hoogs A.
Perera A.G.A.
Collins R.
Basharat A.
Fieldhouse K.
Atkins C.
Sherrill L.
Boeckel B.
Blue R.
Woehlke M.
Greco C.
Sun Z.
Swears E.
Cuntoor N.
Luck J.
Drew B.
Hanson D.
Rowley D.
Kopaz J.
Rude T.
Keefe D.
Srivastava A.
Khanwalkar S.
Kumar A.
Chen C.C.
Aggarwal J.K.
Davis L.
Yacoob Y.
Jain A.
Liu D.
Chang S.-F.
Song B.
Roy-Chowdhury A.
Sullivan K.
Tešić J.
Chandrasekaran S.
Manjunath B.S.
Wang X.
Ji Q.
Reddy K.
Liu J.
Shah M.
Chang K.
Chen T. 
Desai M.
Keywords: Cameras
Graphical user interfaces
Image resolution
Metadata
Surveillance
Tracking
Vehicles
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Hoogs A., Perera A.G.A., Collins R., Basharat A., Fieldhouse K., Atkins C., Sherrill L., Boeckel B., Blue R., Woehlke M., Greco C., Sun Z., Swears E., Cuntoor N., Luck J., Drew B., Hanson D., Rowley D., Kopaz J., Rude T., Keefe D., Srivastava A., Khanwalkar S., Kumar A., Chen C.C., Aggarwal J.K., Davis L., Yacoob Y., Jain A., Liu D., Chang S.-F., Song B., Roy-Chowdhury A., Sullivan K., Tešić J., Chandrasekaran S., Manjunath B.S., Wang X., Ji Q., Reddy K., Liu J., Shah M., Chang K., Chen T., Desai M. (2015). An end-to-end system for content-based video retrieval using behavior, actions, and appearance with interactive query refinement. AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance : 7301807. ScholarBank@NUS Repository. https://doi.org/10.1109/AVSS.2015.7301807
Abstract: We describe a system for content-based retrieval from large surveillance video archives, using behavior, action and appearance of objects. Objects are detected, tracked, and classified into broad categories. Their behavior and appearance are characterized by action detectors and descriptors, which are indexed in an archive. Queries can be posed as video exemplars, and the results can be refined through relevance feedback. The contributions of our system include the fusion of behavior and action detectors with appearance for matching; the improvement of query results through interactive query refinement (IQR), which learns a discriminative classifier online based on user feedback; and reasonable performance on low resolution, poor quality video. The system operates on video from ground cameras and aerial platforms, both RGB and IR. Performance is evaluated on publicly-available surveillance datasets, showing that subtle actions can be detected under difficult conditions, with reasonable improvement from IQR.
Source Title: AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance
URI: http://scholarbank.nus.edu.sg/handle/10635/146074
ISBN: 9781467376327
DOI: 10.1109/AVSS.2015.7301807
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

3
checked on Aug 23, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.