Dense motion segmentation for first-person activity recognition

Kai Zhan, Vitor Guizilini, Fabio Ramos

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

In this paper, we propose a dense motion segmentation method for human daily activity recognition from a wearable device - 'Smart Glasses'. The glasses are embedded with a camera, which allows the system to automatically recognise the wearer's activities from a first-person perspective. This application can be broadly applied to patients, elderly, safety workers, e-health monitoring, or anyone requiring cognitive assistance or guidance on their activities of daily living (ADLs). We validate our system in challenging real-world scenarios, and compare two feature extraction approaches: averaged optical flow and a combined dense motion segmentation approach. We classify them using LogitBoost (on Decision Stumps) and Support Vector Machine (SVM). We also suggest the optimal settings of the classifiers through cross-validation over our ADLs database. The results show that the optical flow with average pooling has a good performance when classifying general locomotive activities. The results also indicate the benefits that dense motion segmentation features can have on reliably classify activities involving a moving object, such as hands. We achieve an overall accuracy of up to 69.76% on 12 ADLs using local classifiers, and with a Hidden Markov Model (HMM) process this accuracy improves to up to 89.59%.
Original languageEnglish
Title of host publication13th International Conference on Control, Automation, Robotics and Vision, ICARCV 2014
Subtitle of host publicationMarina Bay Sands, Singapore, 10-12th December 2014
EditorsHan Wang
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages123 - 128
Number of pages6
ISBN (Electronic)9781479951994
ISBN (Print)9781479952007
DOIs
Publication statusPublished - 2014
Externally publishedYes
EventInternational Conference on Control, Automation, Robotics and Vision 2014 - Marina Bay Sands, Singapore
Duration: 10 Dec 201412 Dec 2014
Conference number: 13th
https://ieeexplore.ieee.org/xpl/conhome/7056237/proceeding (Proceedings)

Conference

ConferenceInternational Conference on Control, Automation, Robotics and Vision 2014
Abbreviated titleICARCV 2014
Country/TerritorySingapore
CityMarina Bay Sands
Period10/12/1412/12/14
Internet address

Cite this