Detection and location of unsafe behaviour in digital images: A visual grounding approach
Authors:
- Jiajing LiuJLJiajing Liu
- Weili FangWFWeili Fang
- Peter E.D. LovePLPeter E.D. Love
- Timo HartmannTHTimo Hartmann
- Hanbin LuoHLHanbin Luo
- Lulu WangLWLulu Wang
- 30 July 2022
- journal article
- research article
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 53
Abstract
No abstract availableKeywords
Funding Information
- Alexander von Humboldt-Stiftung
- National Natural Science Foundation of China (51978302, 71732001, U21A20151)
This publication has 44 references indexed in Scilit:
- Detecting non-hardhat-use by a deep learning method from far-field surveillance videosAutomation in Construction, 2018
- Error estimation based on variance analysis of k -fold cross-validationPattern Recognition, 2017
- An Attention-based Regression Model for Grounding Textual Phrases in Images2017
- YOLO9000: Better, Faster, Stronger2017
- Vision-Based Object-Centric Safety Assessment Using Fuzzy Inference: Monitoring Struck-By Accidents with Moving ObjectsJournal of Computing in Civil Engineering, 2016
- Natural Language Object Retrieval2016
- Hardhat-Wearing Detection for Enhancing On-Site Safety of Construction WorkersJournal of Construction Engineering and Management, 2015
- Deep learningNature, 2015
- Edge Boxes: Locating Object Proposals from Edges2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013