Deep learning and anthropometric plane based workflow monitoring by detecting and tracking workers

N. A. Gard, J. Chen, Pingbo Tang, A. Yilmaz

Research output: Contribution to journalConference article

Abstract

The worker productivity, a critical variable in project management, significantly affects the progress of a project. The key to measuring productivity is analysis of activities, which provides necessary information by identifying how workers spend their time at certain areas in the site. In this work, we propose a novel joint image-trajectory space for automatic detection and tracking of workers using a single fixed camera. A two-branch convolutional neural network detects workers and their body joints. Instead of tracking the body joints in the image space, we transform detected joints onto virtual parallel planes called “Anthropometric Planes”. The detected joints are, then, tracked using a Kalman Filter on these planes which are created based on anthropometric measures of an average American male. Finally, an uncertainty measure is introduced to reduce the number of identity changes and to handle missing joints. The experiments conducted on an image sequence captured in a nuclear plant shows promising detection and tracking results.

Original languageEnglish (US)
Pages (from-to)149-154
Number of pages6
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume42
Issue number1
DOIs
StatePublished - Sep 20 2018
Externally publishedYes
Event2018 ISPRS Technical Commission I Midterm Symposium on Innovative Sensing - From Sensors to Methods and Applications - Karlsruhe, Germany
Duration: Oct 10 2018Oct 12 2018

Fingerprint

workflow
Productivity
learning
monitoring
worker
Monitoring
Project management
Kalman filters
productivity
Cameras
Trajectories
Neural networks
project management
neural network
Kalman filter
Experiments
uncertainty
transform
trajectory
Deep learning

Keywords

  • Anthropometric Measures
  • Critical Path
  • Detection
  • Tracking

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development

Cite this

@article{b2d2ec2b560f482c84f47a44dfaabcb7,
title = "Deep learning and anthropometric plane based workflow monitoring by detecting and tracking workers",
abstract = "The worker productivity, a critical variable in project management, significantly affects the progress of a project. The key to measuring productivity is analysis of activities, which provides necessary information by identifying how workers spend their time at certain areas in the site. In this work, we propose a novel joint image-trajectory space for automatic detection and tracking of workers using a single fixed camera. A two-branch convolutional neural network detects workers and their body joints. Instead of tracking the body joints in the image space, we transform detected joints onto virtual parallel planes called “Anthropometric Planes”. The detected joints are, then, tracked using a Kalman Filter on these planes which are created based on anthropometric measures of an average American male. Finally, an uncertainty measure is introduced to reduce the number of identity changes and to handle missing joints. The experiments conducted on an image sequence captured in a nuclear plant shows promising detection and tracking results.",
keywords = "Anthropometric Measures, Critical Path, Detection, Tracking",
author = "Gard, {N. A.} and J. Chen and Pingbo Tang and A. Yilmaz",
year = "2018",
month = "9",
day = "20",
doi = "10.5194/isprs-archives-XLII-1-149-2018",
language = "English (US)",
volume = "42",
pages = "149--154",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
issn = "1682-1750",
number = "1",

}

TY - JOUR

T1 - Deep learning and anthropometric plane based workflow monitoring by detecting and tracking workers

AU - Gard, N. A.

AU - Chen, J.

AU - Tang, Pingbo

AU - Yilmaz, A.

PY - 2018/9/20

Y1 - 2018/9/20

N2 - The worker productivity, a critical variable in project management, significantly affects the progress of a project. The key to measuring productivity is analysis of activities, which provides necessary information by identifying how workers spend their time at certain areas in the site. In this work, we propose a novel joint image-trajectory space for automatic detection and tracking of workers using a single fixed camera. A two-branch convolutional neural network detects workers and their body joints. Instead of tracking the body joints in the image space, we transform detected joints onto virtual parallel planes called “Anthropometric Planes”. The detected joints are, then, tracked using a Kalman Filter on these planes which are created based on anthropometric measures of an average American male. Finally, an uncertainty measure is introduced to reduce the number of identity changes and to handle missing joints. The experiments conducted on an image sequence captured in a nuclear plant shows promising detection and tracking results.

AB - The worker productivity, a critical variable in project management, significantly affects the progress of a project. The key to measuring productivity is analysis of activities, which provides necessary information by identifying how workers spend their time at certain areas in the site. In this work, we propose a novel joint image-trajectory space for automatic detection and tracking of workers using a single fixed camera. A two-branch convolutional neural network detects workers and their body joints. Instead of tracking the body joints in the image space, we transform detected joints onto virtual parallel planes called “Anthropometric Planes”. The detected joints are, then, tracked using a Kalman Filter on these planes which are created based on anthropometric measures of an average American male. Finally, an uncertainty measure is introduced to reduce the number of identity changes and to handle missing joints. The experiments conducted on an image sequence captured in a nuclear plant shows promising detection and tracking results.

KW - Anthropometric Measures

KW - Critical Path

KW - Detection

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=85056198904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056198904&partnerID=8YFLogxK

U2 - 10.5194/isprs-archives-XLII-1-149-2018

DO - 10.5194/isprs-archives-XLII-1-149-2018

M3 - Conference article

AN - SCOPUS:85056198904

VL - 42

SP - 149

EP - 154

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

IS - 1

ER -