Translator Disclaimer
Paper
7 October 2019 Action localization and classification in long-distance surveillance
Author Affiliations +
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.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Eli Chen, Oren Haik, and Yitzhak Yitzhaky "Action localization and classification in long-distance surveillance", Proc. SPIE 11166, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III, 111660U (7 October 2019); https://doi.org/10.1117/12.2534670
PROCEEDINGS
6 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Profile video
Proceedings of SPIE (April 28 2009)
SVM based classification of moving objects in video
Proceedings of SPIE (October 30 2009)
Temporal synchronization in video watermarking
Proceedings of SPIE (April 29 2002)
New car plate recognition method based on fuzzy entropy
Proceedings of SPIE (September 13 2002)

Back to Top