Violent Action Detection for Elevator

This paper presents a new critical event detection method simplified for built into elevators. We first define that the critical event is unusual action such as violent action, counteraction, etc, and introduce the violent action level (VA level). We use an optical flow based method to analyze the current state of the motion through an ITV (Industrial TeleVision) camera. After motion analysis, we calculate a normalized statistical value, which is the VA level. The statistical value is the multiple of the optical flow direction variance, the optical flow magnitude variance, and optical flow area. Our method calculates the statistical value variance and normalize it by the variance. At last we can detect critical event by thresholding the VA level. Then we implement this method on a built-in device. The device has an A/D converter with special designed frame buffer, a 400 MIPS high-performance microprocessor, dynamic memory, and flash ROM. Since we need to process the method 4Hz or faster to keep the detection performance, we shrink the images into 80 by 60 pixels, introduce recursive correlation, and analyze optical flows. The specially designed frame buffer enables us to capture two sequential images at any time. After that we achieved a processing performance of 8Hz on it. Our method detects 80% of critical events where at a maximum false acception rate of 6%.