Convolutional neural networks of the YOLO class in computer vision systems for mobile robotic complexes

Ivan V. Zoev, Alexey P. Beresnev, Nikolay G. Markov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An important scientific direction is the development and study of computer vision systems (CVS) for mobile robotic complexes. Today, developers of CVS are most often using convolutional neural networks (CNN). For increasing the speed detection of objects on images in CVS, there has been a trend of using CNN, which are hardware-implemented on field-programmable gate array (FPGAs).This article shows that the perspective for hardware implementation on the FPGA is the tiny-YOLO CNN from the YOLO class. For reduce required FPGA computing resources in this CNN, was proposed to use Inception-ResNet modules. We was found that with high detection accuracy of objects in images with minimum resources requirements provide by the tiny-YOLO-Inception-ResNet2 network architecture. It is obtained from replacing the fifth tiny-YOLO convolutional layer of the tiny-YOLO CNN with two sequential processing Inception-ResNet modules. Also results of the study of the detection accuracy of objects using the CNN for this architecture with the lack of resource-intensive operations: batch normalization and bias from calculations were given. These studies were performed for different formats of representation numbers in the FPGA.

Original languageEnglish
Title of host publication2019 International Siberian Conference on Control and Communications, SIBCON 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538651414
DOIs
Publication statusPublished - 1 Apr 2019
Event2019 International Siberian Conference on Control and Communications, SIBCON 2019 - Tomsk, Russian Federation
Duration: 18 Apr 201920 Apr 2019

Publication series

Name2019 International Siberian Conference on Control and Communications, SIBCON 2019 - Proceedings

Conference

Conference2019 International Siberian Conference on Control and Communications, SIBCON 2019
CountryRussian Federation
CityTomsk
Period18.4.1920.4.19

Keywords

  • Computer vision systems
  • Convolutional neural networks
  • Field-programmable gate array
  • Mobile robotic systems
  • Object detection on images

ASJC Scopus subject areas

  • Control and Optimization
  • Computer Networks and Communications
  • Signal Processing

Fingerprint Dive into the research topics of 'Convolutional neural networks of the YOLO class in computer vision systems for mobile robotic complexes'. Together they form a unique fingerprint.

  • Cite this

    Zoev, I. V., Beresnev, A. P., & Markov, N. G. (2019). Convolutional neural networks of the YOLO class in computer vision systems for mobile robotic complexes. In 2019 International Siberian Conference on Control and Communications, SIBCON 2019 - Proceedings [8729605] (2019 International Siberian Conference on Control and Communications, SIBCON 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIBCON.2019.8729605