Length estimation of moving objects with ANN and gripping with robotic arm

Kürsad Ucar; Hasan Erdinc Kocer

Length estimation of moving objects with ANN and gripping with robotic arm

Kürsad Ucar, Hasan Erdinc Kocer

Abstract

It is possible to obtain general information about objects with image processing. However, while measuring the size of objects, especially with 2D cameras, the calibrated systems have been worked with restrictions such as fixed length and distance. However, without depth information and for objects of arbitrary positions and lengths, calculating their dimensions is a rather difficult task. In this study, an ANN-based application was carried out to calculate the amount of movement and the length of the object by viewing the moving objects from the side and top with two cameras. Objects moving on the conveyor belt are detected by deep learning-based YOLO. The motion amount of the object was calculated in the second image with the template created on the detected objects. An ANN is trained with the amount of movement and position information measured by two cameras. At the end of the training, the network estimates the lengths of the objects with small errors. The speed of the objects was calculated according to the calculated length and the targets were grasped with a robot arm.

Keywords

Artificial Neural Network;Grasping; Moving object; Object dimension

Full Text:

PDF

References

Z. Yin and Y. Li, "Overview of Robotic Grasp Detection from 2D to 3D," Cognitive Robotics, 2022.

J. Aleotti and S. Caselli, "A 3D shape segmentation approach for robot grasping by parts," Robotics and Autonomous Systems, vol. 60, no. 3, pp. 358-366, 2012.

D. Yang, T. Tosun, B. Eisner, V. Isler, and D. Lee, "Robotic grasping through combined image-based grasp proposal and 3d reconstruction," in 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021: IEEE, pp. 6350-6356.

J. Yu, K. Weng, G. Liang, and G. Xie, "A vision-based robotic grasping system using deep learning for 3D object recognition and pose estimation," in 2013 IEEE international conference on robotics and biomimetics (ROBIO), 2013: IEEE, pp. 1175-1180.

K. Uçar and H. E. Koçer, "Determination of Angular Status and Dimensional Properties of Objects for Grasping with Robot Arm," IEEE Latin America Transactions, vol. 21, no. 2, pp. 335-343, 2023.

R. Beschi, X. Feng, S. Melillo, L. Parisi, and L. Postiglione, "Stereo camera system calibration: the need of two sets of parameters," arXiv preprint arXiv:2101.05725, 2021.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.

S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," Advances in neural information processing systems, vol. 28, 2015.

D. Wu, S. Lv, M. Jiang, and H. Song, "Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments," Computers and Electronics in Agriculture, vol. 178, p. 105742, 2020.

S. Shinde, A. Kothari, and V. Gupta, "YOLO based human action recognition and localization," Procedia computer science, vol. 133, pp. 831-838, 2018.

K. Uçar, "Robot Kolu ile Hareketli Nesnenin Segmentasyonu ve Kavranması için Derin Öğrenme Tabanlı Bir Yaklaşım," Selçuk Üniversitesi Fen Bilimleri Enstitüsü, 2023.

A. Goshtasby, "Template matching in rotated images," IEEE Transactions on Pattern Analysis and Machine Intelligence, no. 3, pp. 338-344, 1985.

E. Egrioglu, C. H. Aladag, U. Yolcu, V. R. Uslu, and M. A. Basaran, "A new approach based on artificial neural networks for high order multivariate fuzzy time series," Expert Systems with Applications, vol. 36, no. 7, pp. 10589-10594, 2009.