BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Canada/Eastern BEGIN:DAYLIGHT DTSTART:20200308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20201101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20201005T174806Z UID:28F2747D-9D9D-4F2C-BC7D-906A39F204A1 DTSTART;TZID=Canada/Eastern:20200924T143000 DTEND;TZID=Canada/Eastern:20200924T153000 DESCRIPTION:The demand for video streaming is growing every day which impli es a higher demand for new video transmitting and compression techniques t o avoid data traffics over telecommunication networks. In this dissertatio n\, we studied saliency detection in order to apply it to video streaming problem to be able to transmit different regions of video frames in a rank ed manner based on their importance (i.e.\, saliency). Salient areas are t he regions of interest that stand out relative to their surroundings and c onsequently attract more attention. To determine the salient areas within a scene\, visual importance and distinctiveness of the regions must be mea sured. The lack of a comprehensive and precise biologically-inspired study on the saliency of bottom-up stimuli prevents justifying the level of imp ortance for different stimuli such as color\, luminance\, texture\, and mo tion on the human visual system (HVS). To overcome this barrier\, we inves tigated the bottom-up features using an eye-tracking procedure and human s ubjects in video sequences to provide a ranking saliency system stating th e most dominant elements for each feature individually as well as in combi nation with other features. The experiment was performed under conditions in which we had no cognitive bias in order to speed up the video streaming procedure. Next\, we introduced a gradual saliency detection framework fo r both still images and video sequences using color\, texture\, and motion features (based on our experimental estimations). In our algorithm\, we p roposed new feature maps for color and texture features\, and we also impr oved the optical flow field estimation in our motion map. Finally\, differ ent feature maps were combined and classified as different saliency levels using a Naive Bayesian Network. This work provides a benchmark to specify the gradual saliency for both static and dynamic (i.e.\, moving backgroun ds) scenes. The main contribution of this work is the ability to assign a gradual saliency for the entirety of an image/video frame rather than simp ly extracting a salient object/area\, which is widely performed in the sta te-of-the-art.\n\nSpeaker(s): Dr. Jila Hosseinkhani \, \n\nVirtual: https: //events.vtools.ieee.org/m/240720 LOCATION:Virtual: https://events.vtools.ieee.org/m/240720 ORGANIZER:m.abdelazez.ca@ieee.org SEQUENCE:2 SUMMARY:IEEE EMBS - Gradual Saliency Detection in Video Sequences Using Bot tom-up Attributes URL;VALUE=URI:https://events.vtools.ieee.org/m/240720 X-ALT-DESC:Description: <br /><p>The demand for video streaming is growing every day which implies a higher demand for new video transmitting and com pression techniques to avoid data traffics over telecommunication networks . In this dissertation\, we studied saliency detection in order to apply i t to video streaming problem to be able to transmit different regions of v ideo frames in a ranked manner based on their importance (i.e.\, saliency) . Salient areas are the regions of interest that stand out relative to the ir surroundings and consequently attract more attention. To determine the salient areas within a scene\, visual importance and distinctiveness of th e regions must be measured. The lack of a comprehensive and precise biolog ically-inspired study on the saliency of bottom-up stimuli prevents justif ying the level of importance for different stimuli such as color\, luminan ce\, texture\, and motion on the human visual system (HVS). To overcome th is barrier\, we investigated the bottom-up features using an eye-tracking procedure and human subjects in video sequences to provide a ranking salie ncy system stating the most dominant elements for each feature individuall y as well as in combination with other features. The experiment was perfor med under conditions in which we had no cognitive bias in order to speed u p the video streaming procedure. Next\, we introduced a gradual saliency d etection framework for both still images and video sequences using color\, texture\, and motion features (based on our experimental estimations). In our algorithm\, we proposed new feature maps for color and texture featur es\, and we also improved the optical flow field estimation in our motion map. Finally\, different feature maps were combined and classified as diff erent saliency levels using a Naive Bayesian Network. This work provides a benchmark to specify the gradual saliency for both static and dynamic (i. e.\, moving backgrounds) scenes. The main contribution of this work is the ability to assign a gradual saliency for the entirety of an image/video f rame rather than simply extracting a salient object/area\, which is widely performed in the state-of-the-art.</p> END:VEVENT END:VCALENDAR