A New Algorithm for Shape Estimation with a Low Cost Sensor
Keziban Şaloğlu Arda Hoşafçı Merve Birbilen Alpay Baybörü Ege Dinler Ahmet Güneş
AbstractIn this paper, a measurement system composed of a single low-cost sensor and a shape estimation algorithm is proposed. Measurement mechanism consists of a low-cost infrared sensor, two servo motors and a microcontroller. This mechanism provides flexibility to scan at different heights and angle intervals. From the obtained scanning results, the features of the shapes are extracted and objects are classified accordingly.Classified objects are square prism, triangular prism, cylinder and pyramid. The extracted features are change in the width of the object depending on its height, having corner, corner angle and slope of the surface. The algorithm uses segmentation and fractured line fitting on the contour data of the shapes. The proposed algorithm is proved to be superior to our former method using RANSAC algorithm.