A High Accuracy, Robust and Fast Workpiece Localization Algorithm Based on Statistics

This paper proposes an edge detection algorithm based on statistics, which is very suitable for workpiece localization in industrial automated production systems; as this algorithm has no threshold, it is not sensitive to changes of light intensity, and can be well adapted to production environment of various light intensities without adjusting any parameters. This algorithm is also very robust to pollutions, water stains, shadows on the surface of the workpiece and various noise interference in the imaging process, which can significantly improve the vision system’s ability to adapt to the production environment. This algorithm has high localization accuracy, and the average deviation of angle detection of this algorithm is within 0.1 degrees under normal conditions, indicating our algorithm has good adaptability to actual working conditions.