Comparison of two simplified method for real-time object detection: An application in safety engineering

摘要

We present and compare two simple systems of image processing for safety control. The sequence of the images from two cameras is presented to the system in order to detect a new object appearing in a detection zone. In order to make our system able to adapt to changes in illumination level the analysis is performed in HSV (Hue, Saturation, Value) color space. On the basis of images from camera the distance between man and moving parts of a machine is calculated and compared to the minimum acceptable. Experiments conducted using artificial images indicate that our system can work in a real time and detect successively dangerous situations. As results from the experiments, the safety system is able to work for a wide range of illumination and noise. An example of possible application of the system is presented. Performed simulations show that application of vision based system can significantly decrease downtime.