Two-step long short-term memory method for identifying construction activities through positional and attentional cues
Authors:
- Jiannan CaiJCJiannan Cai
- Yuxi ZhangYZYuxi Zhang
- Hubo CaiHCHubo Cai
- 1 October 2019
- journal article
- research article
- Published by Elsevier in Automation in Construction
- Vol. 106
Abstract
No abstract availableKeywords
This publication has 37 references indexed in Scilit:
- Vision-based action recognition of earthmoving equipment using spatio-temporal features and support vector machine classifiersAdvanced Engineering Informatics, 2013
- Automated 2D detection of construction equipment and workers from site video streams using histograms of oriented gradients and colorsAutomation in Construction, 2013
- Construction worker detection in video frames for initializing vision trackersAutomation in Construction, 2012
- Three-Dimensional Tracking of Construction Resources Using an On-Site Camera SystemJournal of Computing in Civil Engineering, 2012
- Part based model and spatial–temporal reasoning to recognize hydraulic excavators in construction images and videosAutomation in Construction, 2012
- Learning and classifying actions of construction workers and equipment using Bag-of-Video-Feature-Words and Bayesian network modelsAdvanced Engineering Informatics, 2011
- Automated vision tracking of project related entitiesAdvanced Engineering Informatics, 2011
- Accelerometer-Based Activity Recognition in ConstructionJournal of Computing in Civil Engineering, 2011
- Human activity analysisACM Computing Surveys, 2011
- Tracking multiple workers on construction sites using video camerasAdvanced Engineering Informatics, 2010