Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation

Bhattacharya, Indrani; Radke, Richard J.

doi:10.1109/wacv.2016.7477671

Cited by 11 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Temporary false alarms or misses are handled using logic that people cannot spontaneously appear or disappear from the middle of the room. As shown in our group's previous work [7,23], this relatively simple approach is quite accurate for our purposes; more complex and computationally demanding Kalman or particle filters for tracking are not necessary. A maximum likelihood estimator based on features extracted from the time series of ToF measurements is used to classify human pose into sitting, standing or walking states.…”

Section: Estimation Of Body Orientation Of Seated Individuals Using Low Resolution Overhead Tof Sensorsmentioning

confidence: 78%

See 1 more Smart Citation

Unobtrusive Analysis of Group Interactions without Cameras

Bhattacharya

2018

Proceedings of the 20th ACM International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

Group meetings are often inefficient, unorganized and poorly documented. Factors including "group-think", fear of speaking, unfocused discussion, and bias can affect the performance of a group meeting. In order to actively or passively facilitate group meetings, automatically analyzing group interaction patterns is critical. Existing research on group dynamics analysis still heavily depends on video cameras in the lines of sight of participants or wearable sensors, both of which could affect the natural behavior of participants. In this thesis, we present a smart meeting room that combines microphones and unobtrusive ceiling-mounted Time-of-Flight (ToF) sensors to understand group dynamics in team meetings. Since the ToF sensors are ceiling-mounted and out of the lines of sight of the participants, we posit that their presence would not disrupt the natural interaction patterns of individuals. We collect a new multi-modal dataset of group interactions where participants have to complete a task by reaching a group consensus, and then fill out a post-task questionnaire. We use this dataset for the development of our algorithms and analysis of group meetings. In this paper, we combine the ceiling-mounted ToF sensors and lapel microphones to: (1) estimate the seated body orientation of participants, (2) estimate the head pose and visual focus of attention (VFOA) of meeting participants, (3) estimate the arm pose and body posture of participants, and (4) analyze the multimodal data for passive understanding of group meetings, with a focus on perceived leadership and contribution. CCS CONCEPTS• Human-centered computing → Collaborative and social computing systems and tools; • Applied computing → Psychology;

show abstract

Section: Estimation Of Body Orientation Of Seated Individuals Using Low Resolution Overhead Tof Sensorsmentioning

confidence: 78%

“…• Occupancy tracking using low-resolution ceiling-mounted ToF sensors (published as [7]) • Estimation of seated body orientation (published as [5])…”

Section: Progress To Date and Expected Contributionsmentioning

confidence: 99%

Unobtrusive Analysis of Group Interactions without Cameras

Bhattacharya

2018

Proceedings of the 20th ACM International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…The general setup of each meeting is illustrated in Figure 1, which shows one frame from the reference camera view of a meeting, the low-resolution ToF depth map, and the corresponding location tracking and coarse body orientation estimation results. The sparse ToF sensors are sufficient for occupant tracking [12,28] and coarse body orientation estimation [11], but they do not provide enough information for head pose estimation. Hence, we use two ceiling-mounted Kinects for this purpose; Figure 2 illustrates an example elevation map from one of these Kinects, which contains the heads and upper torsos (with the chairs) of the seated individuals.…”

Section: Head Pose and Vfoa Estimation Using Time-of-flight Sensorsmentioning

confidence: 99%

A Multimodal-Sensor-Enabled Room for Unobtrusive Group Meeting Analysis

Bhattacharya

Foley

Zhang

et al. 2018

Proceedings of the 20th ACM International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

Group meetings can suffer from serious problems that undermine performance, including bias, "groupthink", fear of speaking, and unfocused discussion. To better understand these issues, propose interventions, and thus improve team performance, we need to study human dynamics in group meetings. However, this process currently heavily depends on manual coding and video cameras. Manual coding is tedious, inaccurate, and subjective, while active video cameras can affect the natural behavior of meeting participants. Here, we present a smart meeting room that combines microphones and unobtrusive ceiling-mounted Time-of-Flight (ToF) sensors to understand group dynamics in team meetings. We automatically process the multimodal sensor outputs with signal, image, and natural language processing algorithms to estimate participant head pose, visual focus of attention (VFOA), non-verbal speech patterns, and discussion content. We derive metrics from these automatic estimates and correlate them with user-reported rankings of emergent group leaders and major contributors to produce accurate predictors. We validate our algorithms and report results on a new dataset of lunar survival tasks of 36 individuals across 10 groups collected in the multimodal-sensor-enabled smart room.

show abstract

“…We are also currently investigating even sparser arrays of single-pixel ToF sensors, e.g., mounting one sensor per 60 cm × 60 cm ceiling tile, for real-time person tracking and coarse pose estimation, which would be more suitable for delicate environments like nursing homes or restrooms. On the other hand, since there are substantial "blind spots" between the ToF rays in the sparser system, additional logic about how people actually move and interact in the room is required to accurately infer positions and poses [5].…”

Section: Impactmentioning

confidence: 99%

17-2:Invited Paper: Advanced Sensing and Control in the Smart Conference Room at the Center for Lighting Enabled Systems and Applications

Radke¹,

Woodstock²,

Imam³

et al. 2016

SID Symposium Digest of Technical Papers

Self Cite

View full text Add to dashboard Cite

We describe the Smart Conference Room at the National Science Foundation (NSF) Engineering Research Center for Lighting Enabled Systems and Applications (LESA), which features a networked system of 5-channel Light Emitting Diode (LED) fixtures, custom color sensors, time-of-flight sensors, and advanced algorithms to enable real-time, privacy-preserving occupancy tracking and energy-efficient feedback control.

show abstract

Arrays of single pixel time-of-flight sensors for privacy preserving tracking and coarse pose estimation

Cited by 11 publications

References 12 publications

Unobtrusive Analysis of Group Interactions without Cameras

Unobtrusive Analysis of Group Interactions without Cameras

A Multimodal-Sensor-Enabled Room for Unobtrusive Group Meeting Analysis

17-2:Invited Paper: Advanced Sensing and Control in the Smart Conference Room at the Center for Lighting Enabled Systems and Applications

Contact Info

Product

Resources

About