Real Time Face Detection and Tracking using HAAR Classifier on SOC

1R.S. Sidharth Raj and Dr.B. Karthik

149 Views
60 Downloads
Abstract:

In this paper we intend to Implement a real time Face detection and tracking the head poses position’s from high definition video using Haar Classifier through Raspberry Pi BCM2835 CPU processor which is an combination of SoC with GPU based Architecture. OVA5647 CMOS Image sensor with 5-megapixel used for obtaining high definition video H.264 video data via GPU’s hardware video decoder to improve playback ofH.264 Video data supporting from 1080p at 30fps with complete user control over formatting and output data transfer also supporting with 720p/60HD video in full field of View(FOV). Simple CV and Open CV libraries are used for face detection and tracking the head posesposition. The experimental result computed by using computer vision Simple CV and Open CV framework libraries along with above mentioned hardware results in a sustained throughput of 30 fps under 1080p resolutions for with higher accuracy and speediness for face detection and tracking the head posesposition.

Keywords:

Computer Vision, Face Detection, Haar Classifier, Tracking.

Paper Details
Month7
Year2018
Volume22
IssueIssue 4
Pages16-28