Characterizing Illumination Levels of an Image Sensor as Input to a Camera Based Illumination Controller

Abstract

Illumination is crucial in human activities and in machine vision applications. For indoor surveillance applications, Infrared (IR) Light Emitting Diodes (LEDs) are the common means of providing illumination to the camera to cause no discomfort to human occupants. While IR provides non-obtrusive illumination for the camera, the same energy consumed does not provide the illumination to indoor spaces of the building. In this work, the characteristics of an LED based camera illumination for detecting human occupant motion and detecting the face was carried out. Using algorithms from the OpenCV library, the size of the bounding box during detection of motion, walking and faces were used as indication of the distance of the object from the camera. Results indicate that walking human motion is detected at illumination level of 32.3 lux at a distance of 12 feet, while face detection is obtained at illumination level of 15 lux from a distance of 8 feet. The results obtained in this work can be used in designing a camera based illumination control using fuzzy control system to automatically set the illumination level at the least energy consumption.