Face detection for low power event detection in intelligent surveillance system

Recently, the development of intelligent surveillance system increasingly requires low power consumption. For the power saving, this paper presents an event detection function based on automatically detected human faces, which adaptively convert from low power camera mode to high performance camera...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyung-Il Kim, Seung Ho Lee, Jung Ik Moon, Hyun-Sang Park, Yong Man Ro
Format: Conference Proceeding
Language:English
Subjects:
Cameras
event detection
Face
face detection
Feature extraction
intelligent surveillance system
Lighting
low power hardware architecture
Memory management
Support vector machines
Surveillance
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, the development of intelligent surveillance system increasingly requires low power consumption. For the power saving, this paper presents an event detection function based on automatically detected human faces, which adaptively convert from low power camera mode to high performance camera mode. We propose an efficient face detection (FD) method for operating under the low power camera mode. By employing two-stage structure (i.e., region-of-interest (ROI) selection and false positive (FP) reduction), the proposed FD method requires a very low computational complexity and memory requirements without sacrificing the face detection robustness. Experimental results demonstrated that the proposed FD could be implemented in low power video cameras with promising performance.
ISSN:1546-1874
2165-3577
DOI:10.1109/ICDSP.2014.6900728