Dynamic key frame presentation techniques for augmenting video browsing

Because of unique temporal and spatial properties of video data, different techniques for summarizing videos have been proposed. Key frames extracted directly from video inform users about content without requiring them to view the entire video. As part of ongoing work to develop video browsing interfaces, several interface displays based on key frames were investigated. Variations on dynamic key frame "slide shows" were examined and compared to a static key frame "filmstrip" display. The slide show mechanism displays key frames in rapid succession and is designed to facilitate visual browsing by exploiting human perceptual capabilities. User studies were conducted in a series of three experiments. Key frame display rate, number of simultaneous displays, and user perception were investigated as a function of user performance in object recognition and gist determination tasks. No significant performance degradation was detected at display rates up to 8 key frames per second, but performance degraded significantly at higher rates. Performance on gist determination tasks degraded less severely than performance on object recognition tasks as display rates increased. Furthermore, gist determination performance dropped significantly between three and four simultaneous slide shows in a single display. Users generally preferred key frame filmstrips to dynamic displays, although objective measures of performance were mixed. Implications for visual interface design and further questions for future research are provided.

[1]  James T. Enns,et al.  High-speed visual estimation using preattentive processing , 1996, TCHI.

[2]  Takeo Kanade,et al.  Intelligent Access to Digital Video: Informed m , 1996 .

[3]  Boon-Lock Yeo,et al.  Analysis And Presentation Of Soccer Highlights From Digital Video , 1995 .

[4]  Edward Lee Elliott Watch-grab-arrange-see : thinking with motion images via streams and collages , 1993 .

[5]  Brian C. O'Connor,et al.  Selecting Key Frames of Moving Image Documents: A Digital Environment for Analysis and Navigation. , 1991 .

[6]  “ Previewing Video Data : Browsing Key Frames Rates Using a Video Slide Show Interface , .

[7]  C. Wickens Engineering psychology and human performance, 2nd ed. , 1992 .

[8]  Takeo Kanade,et al.  Intelligent Access to Digital Video: Informedia Project , 1996, Computer.

[9]  Michael G. Christel,et al.  Improving Access to a Digital Video Library , 1997, INTERACT.

[10]  Gary Marchionini,et al.  Information Seeking in Electronic Environments , 1995 .

[11]  M. Potter Short-term conceptual memory for pictures. , 1976, Journal of experimental psychology. Human learning and memory.

[12]  Henry C. Ellis,et al.  Fundamentals of human memory and cognition , 1983 .

[13]  Walter Bender,et al.  Salient video stills: content and context preserved , 1993, MULTIMEDIA '93.

[14]  Boon-Lock Yeo,et al.  Video browsing using clustering and scene transitions on compressed sequences , 1995, Electronic Imaging.

[15]  Gary Marchionini,et al.  Comprehension and Object Recognition Capabilities for Presentations of Simultaneous Video Key Frame Surrogates , 1997, ECDL.

[16]  K. Rayner,et al.  The effect of background information on object identification , 2017 .

[17]  K. Rayner,et al.  Effect of background information on object identification. , 1989 .

[18]  Steven S. Beauchemin,et al.  The computation of optical flow , 1995, CSUR.