Poster abstract: 3D activity localization with multiple sensors

Xinyu Li, Yanyi Zhang, Jianyu Zhang, Shuhong Chen, Yue Gu, Richard A. Farneth, Ivan Marsic, Randall S. Burd

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a deep learning framework for fast 3D activity localization and tracking in a dynamic and crowded real world seting. Our training approach reverses the traditional activity localization approach, which first estimates the possible location of activities and then predicts their occurrence. Instead, we first trained a deep convolutional neural network for activity recognition using depth video and RFID data as input, and then used the activation maps of the network to locate the recognized activity in the 3D space. Our system achieved around 20cm average localization error (in a 4m × 5m room) which is comparable to Kinect's body skeleton tracking error (10-20cm), but our system tracks activities instead of Kinect's location of people.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 16th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2017
PublisherAssociation for Computing Machinery, Inc
Pages297-298
Number of pages2
ISBN (Electronic)9781450348904
DOIs
StatePublished - Apr 18 2017
Event16th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2017 - Pittsburgh, United States
Duration: Apr 18 2017Apr 20 2017

Publication series

NameProceedings - 2017 16th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2017

Other

Other16th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2017
Country/TerritoryUnited States
CityPittsburgh
Period4/18/174/20/17

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Keywords

  • Activity recognition
  • Activity tracking
  • Deep learning
  • Locolization
  • Passive RFID

Fingerprint

Dive into the research topics of 'Poster abstract: 3D activity localization with multiple sensors'. Together they form a unique fingerprint.

Cite this