A Precise and Low Complexity Distance and Size Measurement of Circular Objects from Camera Position using Still Images
Sheikh Faridul Hasan, Rafi Md. Najmus Sadat, Md. Atiqur Rahman, Md. Hasanul Kabir · 2006
Object detection and their properties estimation is a critical area of many image recognition systems. In this paper, we have discussed the circular shape object detection, their size and distance from camera position in case of still color images. Our proposed method integrates color image edge extraction result with a circle parameter determination algorithm efficiently. For each pixel in the image a precise isotropic edge detector estimates exact gradient direction which assures subsequent circle detection. We use one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduce storage requirement and time complexity, to detect circles of any radius. Finally by using diameter of circle (y), focus length of camera lens (f), distance between lens and film (v), we calculate the exact size and the distance of the object from the camera position.