Understanding the world around us from large-scale video data requires vision systems that can perform automatic interpretation. While human eyes can unconsciously perceive independent objects in crowded scenes and other challenging operating environments, automated systems have difficulty detecting, counting, and understanding their behavior in similar scenes. Computer scientists at ORNL have a developed a technology termed as "Coherent Motion Region Detection" that invloves identifying multiple indepedent moving objects in crowded scenes by aggregating low-level motion cues extracted from moving objects. Humans and other species exploit such low-level motion cues seamlessely to perform perceptual grouping for visual understanding. The algorithm detects and tracks feature points on moving objects resulting in partial trajectories that span coherent 3D region in the space-time volume defined by the video. In the case of multi-object motion, many possible coherent motion regions can be constructed around the set of trajectories. The unique approach in the algorithm is to identify all possible coherent motion regions, then extract a subset of motion regions based on an innovative measure to automatically locate moving objects in crowded environments.The software reports snapshot of the object, count, and derived statistics ( count over time) from input video streams. The software can directly process videos streamed over the internet or directly from a hardware device (camera).
To order this software or receive further information, please fill out the following request: Request Software
Cheriyadat, Anil M. (2013, January 4). Detecting and Analyzing Multiple Moving Objects in Crowded Environments with Coherent Motion Regions (Version 00) [Computer software].
Cheriyadat, Anil M. Detecting and Analyzing Multiple Moving Objects in Crowded Environments with Coherent Motion Regions.
Computer software. Version 00. January 4, 2013.
@misc{osti_1231644,
title = {Detecting and Analyzing Multiple Moving Objects in Crowded Environments with Coherent Motion Regions, Version 00},
author = {Cheriyadat, Anil M.},
abstractNote = {Understanding the world around us from large-scale video data requires vision systems that can perform automatic interpretation. While human eyes can unconsciously perceive independent objects in crowded scenes and other challenging operating environments, automated systems have difficulty detecting, counting, and understanding their behavior in similar scenes. Computer scientists at ORNL have a developed a technology termed as "Coherent Motion Region Detection" that invloves identifying multiple indepedent moving objects in crowded scenes by aggregating low-level motion cues extracted from moving objects. Humans and other species exploit such low-level motion cues seamlessely to perform perceptual grouping for visual understanding. The algorithm detects and tracks feature points on moving objects resulting in partial trajectories that span coherent 3D region in the space-time volume defined by the video. In the case of multi-object motion, many possible coherent motion regions can be constructed around the set of trajectories. The unique approach in the algorithm is to identify all possible coherent motion regions, then extract a subset of motion regions based on an innovative measure to automatically locate moving objects in crowded environments.The software reports snapshot of the object, count, and derived statistics ( count over time) from input video streams. The software can directly process videos streamed over the internet or directly from a hardware device (camera).},
doi = {},
url = {https://www.osti.gov/biblio/1231644},
year = {Fri Jan 04 00:00:00 EST 2013},
month = {Fri Jan 04 00:00:00 EST 2013},
note =
}
