Proceedings of International Conference on Applied Innovation in IT 2023/03/09, Volume 11, Issue 1, pp.127-132 Research of Methods to Increase the Efficiency of the Object Detection System on the Raspberry Pi PlatformDaria Koshutina and Svetlana AntoshchukAbstract: The work is devoted to the consideration and solution of the problems of object detection efficiency. This article analyzes object detection methods. The existing methods and systems of object detection are considered. On the basis of the researched methods, prospects and further directions for the development of object detection programs are defined. This research is relevant in today’s world, because smart devices, robots and robotic systems are increasingly being used to improve life. Therefore, the object detection system is an important part of robotics and automation. The development of a real-time object detection algorithm on the Raspberry Pi platform is described. The method of automatic detection and recognition of objects is described. To check the effectiveness of the methods, a system was designed and implemented, which is a camera connected to Raspberry Pi using the algorithm developed during the work. The problem consists in creating algorithms and methods to improve the response time and accuracy of object detection in real time. The system was created on the basis of already existing research results, refinement and implementation of the methods proposed in them In the course of the study, the results of the development of the object detection system based on the developed algorithms were presented and their effectiveness was investigated. Keywords: Robotics, Raspberry Pi, Python, Machine Learning, Deep Learning, Convolutional Neural Networks, Computer Vision, Object Detection, Single-Shot MultiBox Detector, R-CNN. DOI: 10.25673/101928 Download: PDF References:
|
|
DOI: http://dx.doi.org/10.25673/115729
Proceedings of the International Conference on Applied Innovations in IT by Anhalt University of Applied Sciences is licensed under CC BY-SA 4.0
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License
ISSN 2199-8876
Publisher: Edition Hochschule Anhalt
Location: Anhalt University of Applied Sciences
Email: leiterin.hsb@hs-anhalt.de
Phone: +49 (0) 3496 67 5611
Address: Building 01 - Red Building, Top floor, Room 425, Bernburger Str. 55, D-06366 Köthen, Germany
Except where otherwise noted, all works and proceedings on this site is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.