Object Identification Method in Robot Vision Systems
DOI:
https://doi.org/10.52575/2687-0932-2022-49-4-782-787Keywords:
object identification, cue points, segmentation, classification, clusteringAbstract
It is proposed a method object recognition that ensures the minimization of overheads, that has the rotation invariance since objects can be in a random position. To reduce the time and hardware overheads while ensuring object position invariance, it is proposed to use special cue points to define the contour. One could hypothesize that through the application of motion imaging and the availability of multiple views, recognition of certain objects could become easier. The line connecting two nearly points defines the axis of the autonomous Cartesian coordinate system, in which the extreme points are determined. The number of coordinates and the extreme points position in them seems to be the decisive rule for object identification. These architectures are general-purpose, so they can be used to create a number of modules for a bigger system (e.g., object recognition, key points, and object detection modules of a robot vision system). As mobile robots and generally self-driving machines like quad-copters, drones, and soon service robots, are used more and more, object detection systems are becoming more important.
Downloads
References
Aggarwal C.C. 2018. Neural Networks and Deep Learning. A Textbook. Springer International Pub-lishing AG, DOI 10.1007/978-3-319-94463-0 ISBN 978-3-319-94462-3.
Barroso-Laguna A., Riba E., Ponsa D., Mikolajczyk K. 2019. Key.Net: Keypoint detection by handcrafted and learned CNN filters //Proceedings of the IEEE/CVF International Conference on Computer Vision, 5836-5844.
Biryukov A. 2017. Neural network clustering methods to evaluate the totality of taxpayers accord-ing to their degree of creditworthiness. Artificial societies. 12(1-2). URL: https://artsoc.jes.su/s207751800000103-2-1/ DOI: 10.18254/S0000103-2-1
Cui S., Zhong Y., Ma A., Zhang L. 2019. A Novel Robust Feature Descriptor for Multi-Source Re-mote Sensing Image Registration. IEEE International Geoscience and Remote Sensing Sym-posium (IGARSS), 919-922.
Haykin S. 2018. Neural Networks and Learning Machines. 3rd Edition. Pearson.
Hebb D.O. 1949. The Organization of Behavior, Wiley. New York.
Jiang X., Ma J., Xiao G., Shao Z., Guo X. 2021. A review of multimodal image matching: Methods and applications //Information Fusion, Т. 73, 22-71.
Leng C., Zhang H., Li B., Cai G., Pei Z., He L. 2018. Local feature descriptor for image matching: A survey. IEEE Access, Т. 7, 6424-6434.
Protsenko M.А., Pavelyeva E.A. 2019. Iris Image Key Points Descriptors Based on Phase Congru-ency. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42(2/W12). 167-171.
Tikhonova V.A., Pavelyeva E.A. 2020. Hybrid Iris Segmentation Method Based on CNN and Prin-cipal Curvatures. CEUR Workshop Proceedings, Vol. 2744,
Paper 31, 1–10.
Андреев А.Ю., Бобков С.П. 2014. Сегментация символов в изображении модифицированным методом жука. Современные наукоемкие технологии. Региональное приложение. 1(37). 85-88.
Жээнбеков А.А., Сарыбаева А.А. 2016. Метод распознавания изображений на принципах дву-направленной ассоциативной памяти. Евразийский Союз Ученых (ЕСУ). 1(22), 148-151.
Павельева Е.А. 2018. Обработка и анализ изображений на основе использования информации о фазе. Компьютерная оптика, 42(6), 1022-1034.
Райченко Б.В., Некрасов В.В. 2013. Практическое применение методов ключевых точек на примере сопоставления снимков со спутника «Канопус-В». ГЕОМАТИКА №2.
Abstract views: 89
Share
Published
How to Cite
Issue
Section
Copyright (c) 2022 ECONOMICS. INFORMATION TECHNOLOGIES
This work is licensed under a Creative Commons Attribution 4.0 International License.
