Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor

Flores, Fabricio; Munir, Sirajum; Quintana, Matias; Krishnan Prakash, Anand; Berges, Mario

doi:10.5281/zenodo.3404204

Title: Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor

Dataset
Other Related Research

Abstract

Occupancy detection, tracking, and estimation has a wide range of applications including improving building energy efficiency, safety, and security of the occupants. As depth sensors are getting cheaper, they offer a viable solution to estimate occupancy accurately in a non-privacy invasive manner. Even though there are publicly available depth datasets, they do not consider placing the sensor in the ceiling looking downwards to estimate occupancy. We deployed four Kinect for XBOX One in four CMU classrooms and conference rooms for a period of four weeks in 2017 and collected over 6 TB of depth data. We annotate this huge dataset by labelling bounding boxes around occupants and release the annotated dataset.

Authors:

Flores, Fabricio; Munir, Sirajum; Quintana, Matias; Krishnan Prakash, Anand; Berges, Mario

Carnegie Mellon Univ., Pittsburgh, PA (United States); Carnegie Mellon University
Bosch Research & Technology Center
National University of Singapore
Lawrence Berkeley National Laboratory
Carnegie Mellon Univ., Pittsburgh, PA (United States)

Publication Date:: Sun Nov 10 04:00:00 UTC 2019

DOE Contract Number:: EE0007682

Research Org.:: Carnegie Mellon Univ., Pittsburgh, PA (United States)

Sponsoring Org.:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Building Technologies Office (EE-5B)

Collaborations:: Bosch Research & Technology Center National University of Singapore Lawrence Berkeley National Laboratory

Subject:: 47 OTHER INSTRUMENTATION; Datasets; depth data; human detection; occupancy estimation

OSTI Identifier:: 1576967

DOI:: https://doi.org/10.5281/zenodo.3404204

Citation Formats


                    Flores, Fabricio, Munir, Sirajum, Quintana, Matias, Krishnan Prakash, Anand, and Berges, Mario. Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor.  United States: N. p., 2019. 
        Web.  doi:10.5281/zenodo.3404204.

Copy to clipboard


                    Flores, Fabricio, Munir, Sirajum, Quintana, Matias, Krishnan Prakash, Anand, & Berges, Mario. Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor.  United States.  doi:https://doi.org/10.5281/zenodo.3404204

Copy to clipboard


                    Flores, Fabricio, Munir, Sirajum, Quintana, Matias, Krishnan Prakash, Anand, and Berges, Mario. 2019.  
"Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor".  United States.  doi:https://doi.org/10.5281/zenodo.3404204.  https://www.osti.gov/servlets/purl/1576967. Pub date:Sun Nov 10 04:00:00 UTC 2019

Copy to clipboard


                    
@article{osti_1576967,

  title        = {Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor},

  author       = {Flores, Fabricio and Munir, Sirajum and Quintana, Matias and Krishnan Prakash, Anand and Berges, Mario},

  abstractNote = {Occupancy detection, tracking, and estimation has a wide range of applications including improving building energy efficiency, safety, and security of the occupants. As depth sensors are getting cheaper, they offer a viable solution to estimate occupancy accurately in a non-privacy invasive manner. Even though there are publicly available depth datasets, they do not consider placing the sensor in the ceiling looking downwards to estimate occupancy. We deployed four Kinect for XBOX One in four CMU classrooms and conference rooms for a period of four weeks in 2017 and collected over 6 TB of depth data. We annotate this huge dataset by labelling bounding boxes around occupants and release the annotated dataset.},

  doi          = {10.5281/zenodo.3404204},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {Sun Nov 10 04:00:00 UTC 2019},

  month        = {Sun Nov 10 04:00:00 UTC 2019}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.5281/zenodo.3404204

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

Dataset: Occupancy Detection, Tracking, and Estimation Using a Vertically Mounted Depth Sensor

Conference Flores, Fabricio ; Munir, Sirajum ; Quintana, Matias ; ... - DATA'19: Proceedings of the 2nd Workshop on Data Acquisition To Analysis

Occupancy detection, tracking, and estimation has a wide range of applications including improving building energy efficiency, safety, and security of the occupants. As depth sensors are getting cheaper, they offer a viable solution to estimate occupancy accurately in a non-privacy invasive manner. Even though there are publicly available depth datasets, they do not consider placing the sensor in the ceiling looking downwards to estimate occupancy. We deployed four Kinect for XBOX One in four CMU classrooms and conference rooms for a period of four weeks in 2017 and collected over 6 TB of depth data. We annotate this huge datasetmore »« less
Motion Tracking Above and Below Water Dataset

Dataset Bosma, Bret ; Lomonaco, Pedro

This data set includes one trial of above and under water motion tracking measurements from a Qualysis motion tracking system. The Qualisys native .qtm file can be opened by the Qualisys Track Manager software. Data from this file has been exported to a tab separated value (.tsv) file which is a generic ASCII file format that can be read by a text editor, MATLAB, Excel, etc... Also exported is a native MATLAB formatted file (.mat) which can be loaded directly into MATLAB. The trial is from a three body wave energy converter device, using the underwater system for the centralmore »« less
LBNL Fault Detection and Diagnostics Datasets

Dataset Granderson, Jessica ; Lin, Guanjing ; Chen, Yimin ; ...

These datasets can be used to evaluate and benchmark the performance accuracy of Fault Detection and Diagnostics (FDD) algorithms or tools. It contains operational data from simulation, laboratory experiments, and field measurements from real buildings for seven HVAC systems/equipment (rooftop unit, single-duct air handler unit, dual-duct air handler unit, variable air volume box, fan coil unit, chiller plant, and boiler plant). Each dataset includes a .pdf file to document key information necessary to understand the content and scope, multiple csv files containing all the time-series data for faults at different severity levels and one fault-free case, and a ttl filemore »« less
NREL Bifacial Experimental Single-Axis Tracking dataset

Dataset Ayala Pelaez, Silvana ; Deline, Chris ; Marion, Bill ; ...

Time-series, PV performance field data from 2019-2020 for the bifacial tracking research field at NREL. Dataset also contains meterological data for site.
Brady Well Coordinates and Observation Sensor Depths

Dataset Lim, David

Contains metadata associated with the wells used in the 2016 Spring Campaign led partially by UW - Madison, LBNL, and LLNL scientists. Included with the well coordinates are the depths to the pressure sensors used in observation and pumping wells. Read me files are included for each .csv file.

Similar Records