Increasing measurement accuracy of a chickpea pile weight estimation tool using Moore-neighbor tracing algorithm in sphe
- PDF / 5,351,708 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 103 Downloads / 139 Views
ORIGINAL PAPER
Increasing measurement accuracy of a chickpea pile weight estimation tool using Moore‑neighbor tracing algorithm in sphericity calculation Gokhan Bayar1 Received: 31 March 2020 / Accepted: 31 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this study, a new perspective for increasing the measurement accuracy of a chickpea pile volume and weight estimation tool is proposed. The system proposed uses the principles of machine learning methods and focuses on the adaptation of Moore-neighbor tracing algorithm in sphericity calculation of chickpeas. An experimental setup including a two degrees of freedom moving mechanism, a low-cost laser scanning rangefinder sensor, and a vision unit combining a camera and image processing algorithm is constructed. The methodology proposed is tested to estimate the weight of a chickpea pile using this experimental setup. In order to make comparisons, the estimations are also performed by the use of approaches proposed in the literature. The results of the experimental studies show that at least 5% weight estimation error is obtained when the estimation procedures given in the literature are used. On the other hand, the algorithm proposed in this study yields estimation error less than 0.57%. The details of the procedure proposed, the experimental setup designed and built, the computational environment developed and the experiments conducted are presented in this study. Keywords Measurement accuracy · Moore-neighbor · Chickpea pile · Volume estimation · Weight estimation
Introduction Measurement and estimation and the accuracies of them are important factors to achieve success in robotics, mechatronics, automation and control applications. They provide required feedback data to the control system which is responsible for taking necessary actions for completing a task. These feedbacks are also used in the agricultural applications. In order to increase the efficiency and accuracy in mechanized farming and agricultural operations, autonomous systems and tools are enhanced by the use of estimation and recognition algorithms [1]. Recognition of an object has a meaning that the volume of it can be estimated. Depending on the sensorial system’s technical specifications, volume of an object could be obtained with a high accuracy if the integration of mechanical, electronic, hardware and computational platforms is harmoniously done. It * Gokhan Bayar [email protected] 1
Mechanical Engineering Department, Zonguldak Bulent Ecevit University, Incivez Mah, 67100 Zonguldak, Turkey
is a fact that if the volume of an object is properly estimated and the density is known, the weight of it can be predicted. The proper volume estimation can be achieved by estimating the shape of the object. If the object has a regular shape like exact sphere, square prism, rectangular prism, etc., the volume can precisely be obtained. If not, a methodology which can be able to make an accurate volume estimation is required. When the shape of the object
Data Loading...
