This document describes Region-of-Interest Advanced Video Coding (RoI-AVC), a semantic video codec that achieves coding efficiency and complexity advantages over H.264/AVC. RoI-AVC uses a joint optimized design that bridges computer vision and video coding. It detects regions of interest using multi-scale motion detection and flexibly encodes those regions using H.264, saving up to 34% bitrate with similar quality compared to H.264. The detection is fast, reliable, and operates directly on video frames without background modeling.
Was ist neu in Exchange 2013? Die neueste Generation der marktführenden Collaboration Software ist da! Erfahren Sie mehr über die Architekturänderungen, die vertiefte Integration mit SharePoint und Lync, die Anbindung an die Welt des Cloud Computings, die neue Client Software für den Zugriff und das Management und vieles mehr!
Was ist neu in Exchange 2013? Die neueste Generation der marktführenden Collaboration Software ist da! Erfahren Sie mehr über die Architekturänderungen, die vertiefte Integration mit SharePoint und Lync, die Anbindung an die Welt des Cloud Computings, die neue Client Software für den Zugriff und das Management und vieles mehr!
Lecturing on Eye Tracking (theory, applications and personal account) to Master students for a course in Advanced Consumer Marketing at Linköping University, Sweden.
More info about the experiment at http://tmblr.co/ZabjQq19R8z26 or at http://www.slideshare.net/guyaderhugo/nrwc2014-closing-the-green-gap-what-can-the-retailer-do-inside-the-store-41209567
Eye tracking and its economic feasibilityJeffrey Funk
These slides use concepts from my (Jeff Funk) course entitled analyzing hi-tech opportunities to analyze how the economic feasibility of eye tracking technology is becoming better through improvements in infrared LEDs, micro-projectors, image sensors, and microprocessors. The capability to track an eye’s movement can help us better identify tired drivers and equipment operators, understand the eye movements of retail shoppers, and develop better human-computer interfaces. Tired drivers and machine operators lead to accidents and these accidents lead to loss of human life and equipment damage. Retailers would like to better understand the eye movements of their customers in order to better design retail stores. Eye trackers would enable one type of human-computer interface, Google Glasses, to understand the information that users are viewing and thus what they want to access
Eye tracking is done with a combination of infrared LEDs, micro-projectors, image sensors, and microprocessors. All of these components are experiencing rapid improvements in cost and performance as feature sizes are made smaller and the number of transistors are increased. Improvements in image sensors have led to higher accuracy and precision where precision refers to consistency. Much of these improvements have come from higher pixel densities and sampling frequencies of the image sensors; the latter enables tracking even when there are head movements.
These improvements have also led to lower costs and cost reductions continue to occur. The cost of high-end eye tracking systems have dropped from about 30,000 USD in 2000 to 18,000 in 2010 and 5,000 in 2013. Further reductions will occur as Moore’s Law continues and as higher volumes enable lower margins.
An eye tracker analysis of the influence of applicant attractiveness on emplo...Hakan Boz
Abstract: Tourism sector is one of the biggest service sectors in the world economy. Not just because of its number of staffs but also due to sector income. The importance of this sector in Turkey increases day by day as well. One of the Structural problems of this sector, which provides almost %5 of the GDP of Turkey, is that labor turnover rate is relatively high. This ratio increases up to %300 according to claims of several studies, and this causes great loss of productivity and income for the tourism companies. Due to the continuous change of employees, companies have difficulty in reaching standard of service and as a result of this difficulty, the possibility of appearance of service errors increases. The problems related to the inexperience staff decrease the customer satisfaction and also they have negative effects on companies’ image.
This study aims to explore the role and influence of attractiveness/attractively on the recruitment process in the touristourism and hospitality sector. The study particularly aims to measure the influence of attractiveness on the selection of job candidates by human resource managers or other managers involved in recruitment. Particularly, the study aims explore to what extent managers act rationally or under the influence of Pavlovian conditioning in making their recruitment decisions. That is to what extent managers resort to heuristics, i.e. make their decision based on the attractively of the candidate, though her/his attractively should not matter as the two positions are back stage positions.
In this study, a part of neurologic data gathering techniques of Eye Tracker(ET) will be used, thereby it is planned to obtain results concerning how much the factor of attractiveness is important in evaluating the candidates who applied a position in tourism sector.
Interactive Video Search - Tutorial at ACM Multimedia 2015klschoef
This is the presentation given by Klaus Schoeffmann and Frank Hopfgartner at the ACM Multimedia 2015 Tutorial in Brisbane, Australia (October 26, 2015). #acmmm15
Find paper here:
http://dl.acm.org/citation.cfm?id=2807417
Immersive Telepresence - case study : Kirari
By Yoshihide Tonomura, Nippon Telegraph and Telephone (NTT) Corporation
at 2nd ITU-T Mini-Workshop on Immersive Live Experience (ILE) in 19 January 2017
This presentation is based on a poster presentation presented at the 2008 PBIRG conference in Washington, D.C.
It demonstrates how we used only eye-gaze information to improve critical metrics in ad that are related to later recall. Once the most important element within an ad is determined, we measure 2 critical metrics; \"time to first fixation\" and \"total gaze duration\".
In February 2012 Annika Naschitzki presented to both Wellington and Auckland audiences about Optimal Usability's new eye tracker, and what it can do. Here is the presentation, however if you would like Anni to come into your organisation to do the presentation please get in touch: anni@optimalusability.com
Lecturing on Eye Tracking (theory, applications and personal account) to Master students for a course in Advanced Consumer Marketing at Linköping University, Sweden.
More info about the experiment at http://tmblr.co/ZabjQq19R8z26 or at http://www.slideshare.net/guyaderhugo/nrwc2014-closing-the-green-gap-what-can-the-retailer-do-inside-the-store-41209567
Eye tracking and its economic feasibilityJeffrey Funk
These slides use concepts from my (Jeff Funk) course entitled analyzing hi-tech opportunities to analyze how the economic feasibility of eye tracking technology is becoming better through improvements in infrared LEDs, micro-projectors, image sensors, and microprocessors. The capability to track an eye’s movement can help us better identify tired drivers and equipment operators, understand the eye movements of retail shoppers, and develop better human-computer interfaces. Tired drivers and machine operators lead to accidents and these accidents lead to loss of human life and equipment damage. Retailers would like to better understand the eye movements of their customers in order to better design retail stores. Eye trackers would enable one type of human-computer interface, Google Glasses, to understand the information that users are viewing and thus what they want to access
Eye tracking is done with a combination of infrared LEDs, micro-projectors, image sensors, and microprocessors. All of these components are experiencing rapid improvements in cost and performance as feature sizes are made smaller and the number of transistors are increased. Improvements in image sensors have led to higher accuracy and precision where precision refers to consistency. Much of these improvements have come from higher pixel densities and sampling frequencies of the image sensors; the latter enables tracking even when there are head movements.
These improvements have also led to lower costs and cost reductions continue to occur. The cost of high-end eye tracking systems have dropped from about 30,000 USD in 2000 to 18,000 in 2010 and 5,000 in 2013. Further reductions will occur as Moore’s Law continues and as higher volumes enable lower margins.
An eye tracker analysis of the influence of applicant attractiveness on emplo...Hakan Boz
Abstract: Tourism sector is one of the biggest service sectors in the world economy. Not just because of its number of staffs but also due to sector income. The importance of this sector in Turkey increases day by day as well. One of the Structural problems of this sector, which provides almost %5 of the GDP of Turkey, is that labor turnover rate is relatively high. This ratio increases up to %300 according to claims of several studies, and this causes great loss of productivity and income for the tourism companies. Due to the continuous change of employees, companies have difficulty in reaching standard of service and as a result of this difficulty, the possibility of appearance of service errors increases. The problems related to the inexperience staff decrease the customer satisfaction and also they have negative effects on companies’ image.
This study aims to explore the role and influence of attractiveness/attractively on the recruitment process in the touristourism and hospitality sector. The study particularly aims to measure the influence of attractiveness on the selection of job candidates by human resource managers or other managers involved in recruitment. Particularly, the study aims explore to what extent managers act rationally or under the influence of Pavlovian conditioning in making their recruitment decisions. That is to what extent managers resort to heuristics, i.e. make their decision based on the attractively of the candidate, though her/his attractively should not matter as the two positions are back stage positions.
In this study, a part of neurologic data gathering techniques of Eye Tracker(ET) will be used, thereby it is planned to obtain results concerning how much the factor of attractiveness is important in evaluating the candidates who applied a position in tourism sector.
Interactive Video Search - Tutorial at ACM Multimedia 2015klschoef
This is the presentation given by Klaus Schoeffmann and Frank Hopfgartner at the ACM Multimedia 2015 Tutorial in Brisbane, Australia (October 26, 2015). #acmmm15
Find paper here:
http://dl.acm.org/citation.cfm?id=2807417
Immersive Telepresence - case study : Kirari
By Yoshihide Tonomura, Nippon Telegraph and Telephone (NTT) Corporation
at 2nd ITU-T Mini-Workshop on Immersive Live Experience (ILE) in 19 January 2017
This presentation is based on a poster presentation presented at the 2008 PBIRG conference in Washington, D.C.
It demonstrates how we used only eye-gaze information to improve critical metrics in ad that are related to later recall. Once the most important element within an ad is determined, we measure 2 critical metrics; \"time to first fixation\" and \"total gaze duration\".
In February 2012 Annika Naschitzki presented to both Wellington and Auckland audiences about Optimal Usability's new eye tracker, and what it can do. Here is the presentation, however if you would like Anni to come into your organisation to do the presentation please get in touch: anni@optimalusability.com
This is the deck that I used at the January 2012 Hyper-V.nu event in Amsterdam, Netherlands. It focuses on the Build announced details on Windows Server 8 Hyper-V networking.
2. RoI-AVC = Region-of-Interest Advanced Video Coding
For stationary camera video applications:
(e.g., video conference, video surveillance, news broadcast)
• Foreground moving objects of crucial interest RoI for smart video processing
• RoiAVC straddling computer vision & video coding a joint optimized design
• Battery powered cameras for low bandwidth scenarios encoding efficiency
& complexity crucial
Frame-based Object -based
RoiAVC RoI-based
A practical semantic video codec with the coding efficiency
and complexity advantages over state-of-art H.264/AVC
Striking a sweet spot between frame-based video coding paradigm
and object-based video coding paradigm
Powered by our key competence in fast reliable RoI detection and
coding schemes
2
3. Outline: RoI-AVC framework and strength
A joint optimized design bridging the two worlds
Vision world Video world
Multi-scale motion RoI bounding - H.264 video H.264 video
RoI detection box generation encoder decoder
Metadata of
Bounding-boxes
Previous frame Current frame Reconstructed frame
• Avoiding the initial background • Up to 34% bit-rate saving @
training and online updating similar quality over H.264/AVC
• Reliable motion RoI detection • 2.x to 3.x faster (including RoI
• 20 fps @ 352x288 w/o manual overhead) than H.264 reference
optimization on Intel Pentium 4 encoder, similar for the decoder
3
To appear in IEEE ICASSP 2007
4. Vision world: multi-scale motion RoI detection
Multi-scale motion RoI detection
Previous frame Pixel-
Pixel - level Region-
Region-level
processing processing
Detected motion RoI
Current frame
Multi-scale motion RoI detection
Multi-scale structural change aggregation as the key contribution
An integrated fast and reliable motion RoI detection approach
Directly applied to two successive video frames w/o a BG model
Robust to flicking lighting and camera noise, and less sensitive to the
thresholds
4
6. Video world: flexible MB-based H.264/AVC coding
Flexible MB-based H.264/AVC codec
Flexible MB-based Flexible MB-based
H.264 encoder H.264 decoder
Detected motion RoI Reconstructed frame
Metadata of
Bounding-boxes MB-based RoI coding
Flexible organization of MBs
16 17 18
Flexible MB-based codec:
1 2 3 19 20 21 1 2 3 4 Largely reduced coding bit-rate and
4 5 6 22 23 24 5 6 7 8
7 8 9 9 10 11 12 complexity
10 11 12
13 14 15
13 14 15 16 21 22
17 18 19 20 23 24
Data locality-preserving ordering
25 26 27 28
w/o changing MB-based pipeline
m MB of 1st Motion RoI n MB of 2 nd Motion RoI MB of background
Could be fully compliant to AVC
6
7. Compared to the prior methods from different worlds
Video
world
Current input frame Results of [CSVT’01] Results of [MM’01] Our results
Vision
world
Current input frame Gaussian hypothesis test The single-scale variant Our multi-scale scheme
7
8. Video demo 1: multi-scale motion RoI detection
Ballet @ 1024 x 768 from MSR camera-4
Detected motion blobs Bounding-boxes superimposed
upon the original frames
8
9. Video demo 2: perceptual quality of RoI-AVC
Indoor
monitoring
News
broadcast
Original video sequences Reconstructed video sequences 9