AUT LibraryAUT
View Item 
  •   Open Research
  • AUT Faculties
  • Faculty of Design and Creative Technologies (Te Ara Auaha)
  • School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau
  • View Item
  •   Open Research
  • AUT Faculties
  • Faculty of Design and Creative Technologies (Te Ara Auaha)
  • School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Local Fast R-CNN Flow for Object-centric Event Recognition in Complex Traffic Scenes

Gu, Q; Yang, J; Yan, W-Q; Li, Y; Klette, R
Thumbnail
View/Open
Conference Contribution (1.185Mb)
Permanent link
http://hdl.handle.net/10292/12758
Metadata
Show full metadata
Abstract
This paper presents a solution for an integrated object-centric event recognition problem for intelligent traffic supervision. We propose a novel event-recognition framework using deep local flow in a fast regionbased convolutional neural network (R-CNN). First, we use a fine-tuned fast R-CNN to accurately extract multi-scale targets in the open environment. Each detected object corresponds to an event candidate. Second, a deep belief propagation method is proposed for the calculation of local fast R-CNN flow (LFRCF) between local convolutional feature matrices

of two non-adjacent frames in a sequence. Third, by using the LFRCF features, we can easily identify the moving pattern of each extracted object and formulate a conclusive description of each event candidate. The contribution of this paper is to propose an optimized framework for accurate event recognition. We verify the accuracy of multi-scale object detection and behavior recognition in extensive experiments on real complex road-intersection surveillance videos.
Keywords
Deep learning; Event recognition; Convolutional neural network; Belief propagation
Date
November 21, 2017
Source
In: Satoh S. (eds) Image and Video Technology. PSIVT 2017. Lecture Notes in Computer Science, vol 10799. Springer, Cham
Item Type
Conference Contribution
Publisher
Springer
DOI
10.1007/978-3-319-92753-4_34
Publisher's Version
https://link.springer.com/chapter/10.1007/978-3-319-92753-4_34#copyrightInformation
Rights Statement
An author may self-archive an author-created version of his/her article on his/her own website and or in his/her institutional repository. He/she may also deposit this version on his/her funder’s or funder’s designated repository at the funder’s request or as a result of a legal obligation, provided it is not made publicly available until 12 months after official publication. He/ she may not use the publisher's PDF version, which is posted on www.springerlink.com, for the purpose of self-archiving or deposit. Furthermore, the author may only post his/her version provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at www.springerlink.com”. (Please also see Publisher’s Version and Citation).

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library

 

 

Browse

Open ResearchTitlesAuthorsDateSchool of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, PāngarauTitlesAuthorsDate

Alternative metrics

 

Statistics

For this itemFor all Open Research

Share

 
Follow @AUT_SC

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library