Leveraging CNN and transfer learning for vision-based human activity recognition

Samundra Deep, Xi Zheng

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

34 Citations (Scopus)


With the advent of the Internet of Things (IoT), there have been significant advancements in the area of human activity recognition (HAR) in recent years. HAR is applicable to wider application such as elderly care, anomalous behaviour detection and surveillance system. Several machine learning algorithms have been employed to predict the activities performed by the human in an environment. However, traditional machine learning approaches have been outperformed by feature engineering methods which can select an optimal set of features. On the contrary, it is known that deep learning models such as Convolutional Neural Networks (CNN) can extract features and reduce the computational cost automatically. In this paper, we use CNN model to predict human activities from Wiezmann Dataset. Specifically, we employ transfer learning to get deep image features and trained machine learning classifiers. Our experimental results showed the accuracy of 96.95% using VGG-16. Our experimental results also confirmed the high performance of VGG-16 as compared to rest of the applied CNN models.
Original languageEnglish
Title of host publication2019 29th International Telecommunication Networks and Applications Conference (ITNAC)
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages4
ISBN (Print)9781728136738
Publication statusPublished - 2019
EventInternational Telecommunication Networks and Applications Conference (29th : 2019) - Auckland, New Zealand
Duration: 27 Nov 201929 Nov 2019


ConferenceInternational Telecommunication Networks and Applications Conference (29th : 2019)
Abbreviated titleITNAC 2019
Country/TerritoryNew Zealand


  • Activity recognition
  • deep learning
  • convolutional neural network


Dive into the research topics of 'Leveraging CNN and transfer learning for vision-based human activity recognition'. Together they form a unique fingerprint.

Cite this