Action localization and classification in long-distance surveillance

Eli Chen, Oren Haik, Yitzhak Yitzhaky

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Suspicious human behaviors can be defined by the user, and in long distance imaging it may include bending the body during walking or crawling, in contrast to regular walking for instance. State-of-the-art methods using convolutional neural networks (CNNs) dealt in general with "clean" signals, in which the object of interest is relatively close to the camera, and therefore fairly clear and easily distinguished from the surrounding environment. This makes it easier to capture detailed information regarding the object and its action. However, in relatively long distance imaging (few kilometers and above) additional difficulties occur which affect the performances of these tasks, since the captured videos are likely to be degraded by the atmospheric path that cause blur and spatiotemporal-varying distortions. Both of these degradation types may reduce the ability for action recognition. These effects become more significant for longer imaging distances and smaller sizes of the objects of interest in the image. The images of objects in imaging through long distance are usually relatively small, and hence, the range of actions that can be resolved is more limited, particularly under strong atmospheric effects. In this study, we perform action localization by first applying optical flow unique processing, and also using a variant of SSD (Single Shot MultiBox Detector) to regress and classify detection boxes in each video frame potentially containing an action of interest.

Original languageEnglish
Title of host publicationCounterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III
EditorsHenri Bouma, Radhakrishna Prabhu, Robert James Stokes, Yitzhak Yitzhaky
PublisherSPIE
ISBN (Electronic)9781510630352
DOIs
StatePublished - 1 Jan 2019
EventCounterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III 2019 - Strasbourg, France
Duration: 9 Sep 201911 Sep 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11166
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceCounterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III 2019
Country/TerritoryFrance
CityStrasbourg
Period9/09/1911/09/19

Fingerprint

Dive into the research topics of 'Action localization and classification in long-distance surveillance'. Together they form a unique fingerprint.

Cite this