Small Human Group Detection and Validation using Pyramidal Histogram of Oriented Gradients and Gray Level Run Length Method
Seemanthini K.1, Manjunath S. S.2

1Seemanthini K, Asst.Professor, Dept.of ISE,DSATM, Bangalore, India
2Dr.Manjunath S. S., Professor & HOD, ATME, Mysore, India
Manuscript received on November 22, 2019. | Revised Manuscript received on December 08, 2019. | Manuscript published on December 30, 2019. | PP: 2284-2397 | Volume-9 Issue-2, December, 2019. | Retrieval Number:  A2252109119/2019©BEIESP | DOI: 10.35940/ijeat.A2252.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Over the decade’s human detection in security and surveillance system became dynamic research part in computer vision. This concern is focused by wide functions in several areas such as smart surveillance, multiple human interface, human pose characterization, person counting and person identification etc. Video surveillance organism mainly deals with recognition plus classification of moving objects with respect to several actions like walking, talking and hand shaking etc. The specific processing stages of small human group detection and validation includes frame generation, segmentation using hierarchical clustering, To achieve accurate classification feature descriptors namely Multi-Scale Completed Local Binary Pattern (MS-CLBP) and Pyramidal Histogram Of Oriented Gradients (PHOG) are employed to extract the features efficiently, Recurrent Neural Network (RNN) classifier helps to classify the features into human and group in a crowd, To extract statistical features Gray Level Run Length Method (GLRLM) is incorporated which helps in group validation.
Keywords: Frame Generation, Hierarchical clustering, Multi-scale completed local binary pattern, Pyramidal histogram of oriented gradients, RNN and Gray level run length method.