A PERSON DETECTION AND MULTI-VIEW VIDEO TRACKING K MEANS CLUSTERING OF FACES
| Author(s) | : | M.Senbagapriya, Dr.P.Sumitra |
| Institution | : | M.Phil Full time Rresearch Scholar, PG and Research Department of Computer Science Vivekananda College of Arts and Sciences for Women (Autonomous),Elayamapalayam |
| Published In | : | Vol. 4, Issue 8 — August 2017 |
| Page No. | : | 517-522 |
| Domain | : | Engineering |
| Type | : | Research Paper |
| ISSN (Online) | : | 2348-4470 |
| ISSN (Print) | : | 2348-6406 |
A generic methodology for the semi-automatic generation of reliable position annotations for evaluatingmulti-camera people-trackers on large video data sets. Most of the annotation data are automatically computed, byestimating a consensus tracking result from multiple existing trackers and people detectors and classifying it as eitherreliable or not.A small subset of the data, composed of tracks with insufficient reliability, is verified by a human using asimple binary decision task, a process faster than marking the correct person position. The proposed framework is genericand can handle additional trackers. In this thesis studied the most commonly used face edge detection techniques of K meansclustering of faces. Higher-level edge detection techniques and appropriate programming tools only facilitate the process butdo not make it a simple task.
M.Senbagapriya, Dr.P.Sumitra, “A PERSON DETECTION AND MULTI-VIEW VIDEO TRACKING K MEANS CLUSTERING OF FACES”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 8, pp. 517-522, August 2017.
