Open Access Open Access  Restricted Access Subscription or Fee Access

Human Action Monitering Using HoG of optical flow

Siddharth Sharma, Keshaw Kumar, Alex Noel Joseph Raj

Abstract



Due to immence increase in the number of CCTV cameras it has become a requrement that computers should be able to automatically detect and analyse human actions in the video feed. This research paper is intended to make the serviellance system fully autonomous, an ultimate goal in the area of smart serveillence system research. In this paper a new methodlogy is presented for autonomous multiple human actions recognition using HoG of optical flow. Three features viz. HoG of Optical Flow, shape, and trajectory have been fused together to define the motion descriptor. This motion descriptor is used to train a feedforward neural network using backpropagation algorithm to classify the human actions in the video feed in real time. The method proves to be very effective in calssifying multiple behaviors with an overall efficency of 80.9%. Also the running time of the algorithm is small enough to be used in real time.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.