Action-Based Multifield Video Visualization

Abstract

One challenge in video processing is to detect actions and events, known or unknown, in video streams dynamically. This paper proposes a visualization solution, where a video stream is depicted as a series of snapshots at a relatively sparse interval, and detected actions are highlighted with continuous abstract illustrations. The combined imagery and illustrative visualization conveys multi-field information in a manner similar to electrocardiograms (ECG) and seismographs. We thus name this type of video visualization as VideoPerpetuoGram (VPG). In this paper, we describe a system that handles the aw and processed information of the video stream in a multi-field visualization pipeline. As examples, we consider the needs for highlighting several types of processed information, including detected actions in video streams, and estimated relationship between recognized objects. We examine the effective means for depicting multi-field information in VPG, and support our choice of visual mappings through a survey. Our GPU implementation facilitates the VPG-specific viewing specification through a sheared object space, as well as volume bricking and combinational rendering of volume data and glyphs.

Evaluating video visualizations of human behavior

“…Through motion detection they visualize contextual paths and provide detail through strategic camera views. Botchen et al present a 2D time lapse video visualization with highlighted abstractions of target objects and activities [1]. We propose similar goals and techniques to these papers, except our video has a near one-to-one correspondence with architectural space that naturally supports space-centric queries.…”

Glyph-Based Video Visualization for Semen Analysis

“…The development of the subject has been heavily influenced by many applications in entertainment [24], [49], sports [28], [40], [58], and security [8]. In a recent survey, Borgo et al [6] proposed a taxonomy to categorize the concepts and techniques in this newly-emerged body of knowledge.…”

Visual analytics for video applications

“…The system also provides a detail-on-demand technique for selected parts of data, as well as a filter feedback to verify the hypotheses [13]. A visualization technique called "VideoPerpetuoGram" or VPG [1] is employed in systems by Höferlin et al to snap the sequences of video stream for detected objects with continuous illustrations. The use of this method has been demonstrated in the IEEE VAST Challenge 2009 [12,13].…”