Gaze-aligned head-mounted camera with pan, tilt, and roll motion control for medical documentation and teaching applications

Schneider, Erich; Bartl, Klaus; Dera, T.; Bardins, Stanislavs; Böning, Guido; Wagner, Philipp; Brandt, Thomas

doi:10.1109/icsmc.2006.384403

Cited by 11 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comments from the remote experts suggest that the overview may not need to be of very high quality. This finding is different from many other studies looking at remote experts [13,8,6] where the video image of what was being done is considered to be the major information source. These studies deal with primary a teacher/student situation or a manual and visual task.…”

Section: Discussioncontrasting

confidence: 84%

“…The use of videoconferencing systems in healthcare settings is not a new practise in itself and many hospitals today have invested in an infrastructure for these applications [5,7,14]. Research has also been conducted on how to create advanced systems to cater for mediated communication in healthcare, such as using wearable computers [1] and remote-controlled laser pointers [10] Studies have been made focusing on how a remote expert [2] can get the best visual view of the task being performed by a single person using body mounted cameras [13,8] or remote controlled cameras [6]. This makes sense when focusing on simple manual tasks, but what if more complicated tasks are performed involving several participants, for example when remotely supporting a trauma team?…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remote supported trauma care: Understanding the situation from afar

Nilsson¹,

Yngling²,

Groth³

et al. 2013

Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems

View full text Add to dashboard Cite

We present results from a study of information needs when teleconsultation is used in trauma resuscitation. Three trauma team training sessions including 14 patient cases were observed together with field studies at emergency units. Technology probes like headcams and visualization of data usually available in the trauma room were used to better understand what information that is important or not for the remote expert to achieve a satisfactory Situation Awareness to support the trauma resuscitation. It was found that the two major information sources that the remote expert relies on are the vital signs and an overview, not necessarily with high video quality, of the team in the trauma room.

show abstract

Section: Discussioncontrasting

confidence: 84%

Section: Introductionmentioning

confidence: 99%

Remote supported trauma care: Understanding the situation from afar

Nilsson¹,

Yngling²,

Groth³

et al. 2013

Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems

View full text Add to dashboard Cite

show abstract

“…That demands the use of small light weight pivotable cameras. The results achieved in our lab by developing the head mounted gaze driven camera [17] can be used for this aim. …”

Section: Gaze Trackingmentioning

confidence: 99%

“…2, www.eyeseecam.org). This system has been already successfully used in applications and experimental setups like the gaze driven head mounted camera [17]. Since the system computes the gaze direction in the head coordinate system, we extended the EyeSeeCam to be used as a head-free gaze tracker that calculates not only eyein-head but also gaze-in-space.…”

Section: Gaze Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Gaze-based interaction in various environments

Bardins

Poitschke

Kohlbecher

2008

Proceedings of the 1st ACM Workshop on Vision Networks for Behavior Analysis

Self Cite

View full text Add to dashboard Cite

The analysis of cognitive processes during human-machine and human-human interaction requires various tracking technologies. The human gaze is a very important cue to gather information concerning the user's intentions, current mental state, etc. To get this data the framework consisting of a highly accurate head-mounted gaze tracker combined with a low latency head tracking method was developed. Its integration into various experimental environments forces an easy to use calibration method for multiple working areas and also the implementation of numerous interfaces. Therefore a calibration method by simply looking at known fixation points was integrated. Also, first results of a brief user study using the proposed framework are presented.

show abstract

Using context from inside‐out vision for improved activity recognition

Noor

Uddin²

2018

IET Computer Vision

View full text Add to dashboard Cite

The authors propose a method to improve activity recognition by including the contextual information from first person vision (FPV). Adding the context, i.e. objects seen while performing an activity, increases the activity recognition precision. This is because, in goal-oriented tasks, human gaze precedes the action and tends to focus on relevant objects. They extract object information from FPV images and combine it with the activity information from external or FPV videos to train an Artificial Neural Network (ANN). They used four configurations as combination of gaze/eye-tracker, head-mounted and externally mounted cameras using three standard cooking datasets from Georgia Tech Egocentric Activities Gaze, Technische Universität München kitchen and CMU multi-modal activity database. Adding object information when training the ANN increased the precision and accuracy of activity recognition from average 58.02% (and 89.78%) to 74.03% (and 93.42%). Experiments also showed that when objects are not considered, having an external camera is necessary. However, when objects are considered, the combination of internal and external cameras is optimal because of their complementary advantages in observing hand and objects. Adding object information also decreases ANN training cycles from 513.25 to 139, which shows that it provides critical information that speeds up training.

show abstract

Gaze-aligned head-mounted camera with pan, tilt, and roll motion control for medical documentation and teaching applications

Cited by 11 publications

References 8 publications

Remote supported trauma care: Understanding the situation from afar

Remote supported trauma care: Understanding the situation from afar

Gaze-based interaction in various environments

Using context from inside‐out vision for improved activity recognition

Contact Info

Product

Resources

About