To enable socially situated human-robot interaction, a robot must both understand and control proxemics, the social use of space, to employ communication mechanisms analogous to those used by humans. In this work, we investigate speech and gesture production and recognition as a function of social agent spacing during both human-human and human-robot interactions. These models were used to implement an autonomous proxemic robot controller. The controller utilizes a sampling-based method, wherein each sample represents inter-agent pose, as well as agent speech and gesture production and recognition estimates; a particle filter uses these estimates to maximize the performance of both the robot and the human during the interaction. This functional approach yields pose, speech, and gesture estimates consistent with related literature. This work contributes to the understanding of the underlying pre-cultural processes that govern proxemic behavior, and has implications for robust proxemic controllers for robots in complex interactions and environments.
{"title":"Autonomous control of human-robot spacing: a socially situated approach","authors":"Ross Mead, M. Matarić","doi":"10.1145/2491367.2491402","DOIUrl":"https://doi.org/10.1145/2491367.2491402","url":null,"abstract":"To enable socially situated human-robot interaction, a robot must both understand and control proxemics, the social use of space, to employ communication mechanisms analogous to those used by humans. In this work, we investigate speech and gesture production and recognition as a function of social agent spacing during both human-human and human-robot interactions. These models were used to implement an autonomous proxemic robot controller. The controller utilizes a sampling-based method, wherein each sample represents inter-agent pose, as well as agent speech and gesture production and recognition estimates; a particle filter uses these estimates to maximize the performance of both the robot and the human during the interaction. This functional approach yields pose, speech, and gesture estimates consistent with related literature. This work contributes to the understanding of the underlying pre-cultural processes that govern proxemic behavior, and has implications for robust proxemic controllers for robots in complex interactions and environments.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129071921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Spatial Augmented Reality (SAR) systems can be used to convey guidance in a physical task from a remote expert. Sometimes that remote expert is provided with a single camera view of the workspace but, if they are given a live captured 3D model and can freely control their point of view, the local worker needs to know what the remote expert can see. We present three new SAR techniques, Composite Wedge, Vector Boxes, and Eyelight, for visualizing off-surface 3D viewpoints and supporting the required workspace awareness. Our study showed that the Composite Wedge cue was best for providing location awareness, and the Eyelight cue was best for providing visibility map awareness.
{"title":"Visualization of off-surface 3D viewpoint locations in spatial augmented reality","authors":"Matt Adcock, David Feng, B. Thomas","doi":"10.1145/2491367.2491378","DOIUrl":"https://doi.org/10.1145/2491367.2491378","url":null,"abstract":"Spatial Augmented Reality (SAR) systems can be used to convey guidance in a physical task from a remote expert. Sometimes that remote expert is provided with a single camera view of the workspace but, if they are given a live captured 3D model and can freely control their point of view, the local worker needs to know what the remote expert can see. We present three new SAR techniques, Composite Wedge, Vector Boxes, and Eyelight, for visualizing off-surface 3D viewpoints and supporting the required workspace awareness. Our study showed that the Composite Wedge cue was best for providing location awareness, and the Eyelight cue was best for providing visibility map awareness.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131130673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As sensing technology has evolved, spatial user interfaces have become increasingly popular platforms for interacting with video games and virtual environments. In particular, recent advances in consumer-level motion tracking devices such as the Microsoft Kinect have sparked a dramatic increase in user interfaces controlled directly by the user's hands and body. However, existing skeleton tracking middleware created for these sensors, such as those developed by Microsoft and OpenNI, tend to focus on coarse full-body motions, and suffers from several well-documented limitations when attempting to track the positions of the user's hands and segment them from the background. In this paper, we present an approach for more robustly handling these failure cases by combining the original skeleton tracking positions with the color and depth information returned from the sensor.
{"title":"Fusing depth, color, and skeleton data for enhanced real-time hand segmentation","authors":"Yu-Jen Huang, M. Bolas, Evan A. Suma","doi":"10.1145/2491367.2491401","DOIUrl":"https://doi.org/10.1145/2491367.2491401","url":null,"abstract":"As sensing technology has evolved, spatial user interfaces have become increasingly popular platforms for interacting with video games and virtual environments. In particular, recent advances in consumer-level motion tracking devices such as the Microsoft Kinect have sparked a dramatic increase in user interfaces controlled directly by the user's hands and body. However, existing skeleton tracking middleware created for these sensors, such as those developed by Microsoft and OpenNI, tend to focus on coarse full-body motions, and suffers from several well-documented limitations when attempting to track the positions of the user's hands and segment them from the background. In this paper, we present an approach for more robustly handling these failure cases by combining the original skeleton tracking positions with the color and depth information returned from the sensor.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133026867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we describe the design and implementation of the Pure Land AR, which is an installation that employs spatial user interface and allows users to virtually visit the UNESCO world heritage -- Mogao Caves by using handheld devices. The installation was shown to the public at different museums and galleries. The result of the work and the user responses is discussed.
{"title":"Spatial user interface for experiencing Mogao caves","authors":"L. Chan, S. Kenderdine, J. Shaw","doi":"10.1145/2491367.2491372","DOIUrl":"https://doi.org/10.1145/2491367.2491372","url":null,"abstract":"In this paper, we describe the design and implementation of the Pure Land AR, which is an installation that employs spatial user interface and allows users to virtually visit the UNESCO world heritage -- Mogao Caves by using handheld devices. The installation was shown to the public at different museums and galleries. The result of the work and the user responses is discussed.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125800169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wataru Naya, Kazuya Fukumoto, Tsuyoshi Yamamoto, Y. Dobashi
We propose a real-time image-based animation technique for virtual fitting applications. Our method uses key image finding from a database which uses skeletal data as a search key, and then create in-between images by using image morphing. Comparing to conventional method using 3DCG rendering, our method achieves higher frame rate and realistic textile representation. Unlike [1], data size and search time are reduced with database optimization.
{"title":"Real-time image-based animation using morphing with human skeletal tracking","authors":"Wataru Naya, Kazuya Fukumoto, Tsuyoshi Yamamoto, Y. Dobashi","doi":"10.1145/2491367.2491395","DOIUrl":"https://doi.org/10.1145/2491367.2491395","url":null,"abstract":"We propose a real-time image-based animation technique for virtual fitting applications. Our method uses key image finding from a database which uses skeletal data as a search key, and then create in-between images by using image morphing. Comparing to conventional method using 3DCG rendering, our method achieves higher frame rate and realistic textile representation. Unlike [1], data size and search time are reduced with database optimization.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124735738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The ability to use free-hand gestures is extremely important for mobile augmented reality applications. This paper proposes a computer vision-driven model for natural free-hands interaction in augmented reality. The novelty of the research is the use of robust hand modeling by combining Viola&Jones and Active Appearance Models. A usability study evaluates the hands free interaction model in with a focus on the accuracy of hand based pointing for menu navigation and menu item selection. The results indicate high accuracy of pointing and high usability of the free-hands interaction in augmented reality. The research is part of a joint project of TU Delft and the Netherlands Forensic Institute in The Hague, aiming at the development of novel technologies for crime scene investigations.
{"title":"Free-hands interaction in augmented reality","authors":"D. Datcu, S. Lukosch","doi":"10.1145/2491367.2491370","DOIUrl":"https://doi.org/10.1145/2491367.2491370","url":null,"abstract":"The ability to use free-hand gestures is extremely important for mobile augmented reality applications. This paper proposes a computer vision-driven model for natural free-hands interaction in augmented reality. The novelty of the research is the use of robust hand modeling by combining Viola&Jones and Active Appearance Models. A usability study evaluates the hands free interaction model in with a focus on the accuracy of hand based pointing for menu navigation and menu item selection. The results indicate high accuracy of pointing and high usability of the free-hands interaction in augmented reality. The research is part of a joint project of TU Delft and the Netherlands Forensic Institute in The Hague, aiming at the development of novel technologies for crime scene investigations.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"30 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116406157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lining Yao, Anthony DeVincenzi, Anna Pereira, H. Ishii
We introduce FocalSpace, a video conferencing system that dynamically recognizes relevant activities and objects through depth sensing and hybrid tracking of multimodal cues, such as voice, gesture, and proximity to surfaces. FocalSpace uses this information to enhance users' focus by diminishing the background through synthetic blur effects. We present scenarios that support the suppression of visual distraction, provide contextual augmentation, and enable privacy in dynamic mobile environments. Our user evaluation indicates increased memory accuracy and user preference for FocalSpace techniques compared to traditional video conferencing.
{"title":"FocalSpace: multimodal activity tracking, synthetic blur and adaptive presentation for video conferencing","authors":"Lining Yao, Anthony DeVincenzi, Anna Pereira, H. Ishii","doi":"10.1145/2491367.2491377","DOIUrl":"https://doi.org/10.1145/2491367.2491377","url":null,"abstract":"We introduce FocalSpace, a video conferencing system that dynamically recognizes relevant activities and objects through depth sensing and hybrid tracking of multimodal cues, such as voice, gesture, and proximity to surfaces. FocalSpace uses this information to enhance users' focus by diminishing the background through synthetic blur effects. We present scenarios that support the suppression of visual distraction, provide contextual augmentation, and enable privacy in dynamic mobile environments. Our user evaluation indicates increased memory accuracy and user preference for FocalSpace techniques compared to traditional video conferencing.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122331844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present an experiment that examines 3D pointing in fish tank VR using the ISO 9241-9 standard. The experiment used three pointing techniques: mouse, ray, and touch using a stylus. It evaluated user pointing performance with stereoscopically displayed varying height targets above an upward-facing display. Results show differences in upwards and downwards motions for the 3D touch technique.
{"title":"Up- and downwards motions in 3D pointing","authors":"Sidrah Laldin, Robert J. Teather, W. Stuerzlinger","doi":"10.1145/2491367.2491393","DOIUrl":"https://doi.org/10.1145/2491367.2491393","url":null,"abstract":"We present an experiment that examines 3D pointing in fish tank VR using the ISO 9241-9 standard. The experiment used three pointing techniques: mouse, ray, and touch using a stylus. It evaluated user pointing performance with stereoscopically displayed varying height targets above an upward-facing display. Results show differences in upwards and downwards motions for the 3D touch technique.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"302 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132772437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jorge H. dos S. Chernicharo, Kazuki Takashima, Y. Kitamura
In this work, we study ways to use a portable projector to extend the workspace in a perspective corrected multi display environment (MDE). This system uses the relative position between the user and displays in order to show the content perpendicularly to the user's point of view in a deformation-free fashion. We introduce the image created by the portable projector as a new, temporary and movable image in the perspective corrected MDE, creating a more flexible workspace to the user. In our study, we combined two ways of using the projector (handheld or head-mounted) with two ways of moving the cursor on the screens (using a mouse or a laser-pointing based strategy), proposing four techniques to be tried by the users. Also, two exploratory evaluation experiments were performed in order to evaluate our system. The first experiment (5 participants) aimed to evaluate how using a movable screen in order to fill the gaps between displays affects the performance of the user in a cross-display pointing task; while the second (6 participants) aimed to evaluate how using the projector to extend the workspace impacts the task completion time in an off-screen content recognition task. Our results showed that while no significant improvement of the performance of the users could be seen on the pointing task, the users were significantly faster when recognizing off-screen content. Also, the introduction of the portable projector reduced the overall task load on both tasks.
{"title":"Seamless interaction using a portable projector in perspective corrected multi display environments","authors":"Jorge H. dos S. Chernicharo, Kazuki Takashima, Y. Kitamura","doi":"10.1145/2491367.2491375","DOIUrl":"https://doi.org/10.1145/2491367.2491375","url":null,"abstract":"In this work, we study ways to use a portable projector to extend the workspace in a perspective corrected multi display environment (MDE). This system uses the relative position between the user and displays in order to show the content perpendicularly to the user's point of view in a deformation-free fashion. We introduce the image created by the portable projector as a new, temporary and movable image in the perspective corrected MDE, creating a more flexible workspace to the user. In our study, we combined two ways of using the projector (handheld or head-mounted) with two ways of moving the cursor on the screens (using a mouse or a laser-pointing based strategy), proposing four techniques to be tried by the users. Also, two exploratory evaluation experiments were performed in order to evaluate our system. The first experiment (5 participants) aimed to evaluate how using a movable screen in order to fill the gaps between displays affects the performance of the user in a cross-display pointing task; while the second (6 participants) aimed to evaluate how using the projector to extend the workspace impacts the task completion time in an off-screen content recognition task. Our results showed that while no significant improvement of the performance of the users could be seen on the pointing task, the users were significantly faster when recognizing off-screen content. Also, the introduction of the portable projector reduced the overall task load on both tasks.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131482195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a study that investigates user performance benefits of using head tracking in modern video games. We explored four different carefully chosen commercial games with tasks which can potentially benefit from head tracking. For each game, quantitative and qualitative measures were taken to determine if users performed better and learned faster in the experimental group (with head tracking) than in the control group (without head tracking). A game expertise pre-questionnaire was used to classify participants into casual and expert categories to analyze a possible impact on performance differences. Our results indicate that head tracking provided a significant performance benefit for experts in two of the games tested. In addition, our results indicate that head tracking is more enjoyable for slow paced video games and it potentially hurts performance in fast paced modern video games. Reasoning behind our results is discussed and is the basis for our recommendations to game developers who want to make use of head tracking to enhance game experiences.
{"title":"Evaluating performance benefits of head tracking in modern video games","authors":"Arun K. Kulshreshth, J. Laviola","doi":"10.1145/2491367.2491376","DOIUrl":"https://doi.org/10.1145/2491367.2491376","url":null,"abstract":"We present a study that investigates user performance benefits of using head tracking in modern video games. We explored four different carefully chosen commercial games with tasks which can potentially benefit from head tracking. For each game, quantitative and qualitative measures were taken to determine if users performed better and learned faster in the experimental group (with head tracking) than in the control group (without head tracking). A game expertise pre-questionnaire was used to classify participants into casual and expert categories to analyze a possible impact on performance differences. Our results indicate that head tracking provided a significant performance benefit for experts in two of the games tested. In addition, our results indicate that head tracking is more enjoyable for slow paced video games and it potentially hurts performance in fast paced modern video games. Reasoning behind our results is discussed and is the basis for our recommendations to game developers who want to make use of head tracking to enhance game experiences.","PeriodicalId":370782,"journal":{"name":"Symposium on Spatial User Interaction","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114225158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：