Abnormal behavior detection using hybrid agents in crowded scenes

Please save a copy of this file, complete and upload as the " Confirmation of Authorship " file. 1. This manuscript, or a large part of it, has not been published, was not, and is not being submitted to any other journal. If presented at a conference, the conference is identified. If published in conference proceedings, the publication is identified below and substantial justification for re-publication must be presented. 2. All text and graphics, except for those marked with sources, are original works of the authors, and all necessary permissions for publication were secured prior to submission of the manuscript. 3. All authors each made a significant contribution to the research reported and have read and approved the submitted manuscript. 1. The sentence in lines 266-269 is still not properly written. Please correct to something like "Since SFM only uses interaction information between neighbor agents to detect abnormal behavior, it is not productive to detect abnormal behavior when the interaction among neighbors is not represented by the behavior of foreground objects." Answer) We rephrase the statement according to reviewer's comments Before) Since SFM is only used interaction information between neighbor agents to detect abnormal behavior, it is not productive to detect abnormal behavior when the interaction among neighbors is not represented by the behavior of foreground objects. After) Since SFM only uses interaction information between neighbor agents to detect abnormal behavior, it is not productive to detect abnormal behavior when the interaction among neighbors is not represented by the behavior of foreground objects. 2. Please include in the caption of figure 6 the methods to which the red and blue lines refer to. Answer) We modified the caption in figure 6 as follows (a) PETS 2009 dataset (b) UCSD 2009 dataset Fig. 6. Results of abnormal behavior detection in two datasets (Red line : SFM, Blue line: our method). • We categorize the behaviors of people into individual and group interactive behavior. • We propose a hybrid agent system that includes static and dynamic agents in a scene. • We represent the behavior of a crowd as a bag of words to detect abnormal behavior. *Manuscript [Word or (La)TeX] Click here to download Manuscript [Word or (La)TeX]: paper_revision_final.docx Click here to view linked References Abstract 26 In this paper, we propose a hybrid agent method to detect abnormal behaviors in a crowded 27 scene. In real-life situations, abnormal behavior occurs …