A Multiviewpoint Outdoor Dataset for Human Action Recognition

Date

2020

Authors

Perera, A.G.
Law, Y.W.
Ogunwa, T.T.
Chahl, J.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

IEEE Transactions on Human-Machine Systems, 2020; 50(5):405-413

Statement of Responsibility

Conference Name

Abstract

Advancements in deep neural networks have contributed to near-perfect results for many computer vision problems,such as object recognition, face recognition, and pose estimation.However, human action recognition is still far from human-level performance. Owing to the articulated nature of the human body,it is challenging to detect an action from multiple viewpoints,particularly from an aerial viewpoint. This is further compounded by a scarcity of datasets that cover multiple viewpoints of actions.To fill this gap and enable research in wider application areas,in this article we present a multiviewpoint outdoor action recognition dataset collected from YouTube and our own drone. The dataset consists of 20 dynamic human action classes, 2324 video clips, and 503 086 frames. All videos are cropped and resized to720 × 720 without distorting the original aspect ratio of the human subjects in videos. This dataset should be useful to many research areas, including action recognition, surveillance, and situational awareness.We evaluate the dataset with a two-stream convolutional neural network architecture coupled with a recently proposed temporal pooling scheme called kernelized rank pooling that produces nonlinear feature subspace representations. The overall baseline action recognition accuracy is 74.0%.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2020 IEEE

License

Grant ID

Call number

Persistent link to this record