Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine

Youhak Lee, Chul Hee Lee, Hyuk Jae Lee, Jin Sung Kim

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

Abstract

Fast object detection is important to enable a vision-based automated vending machine. This paper proposes a new scheme to enhance the operation speed of YOLOv3 by removing the computation for the region of non-interest. In order to avoid the accuracy drop by a removal of computation, characteristics of a convolutional layer and a YOLO layer are investigated, and a new processing method is proposed from experimental results. As a result, the operation speed is increased in proportion to the size of the region of non-interest. Experimental results show that the speed is improved by 3.29 times while the accuracy degradation is 2.81% in mAP-50.

Original languageEnglish
Title of host publicationProceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages132-136
Number of pages5
ISBN (Electronic)9781538678848
DOIs
Publication statusPublished - 2019 Mar 1
Event1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 - Hsinchu, Taiwan, Province of China
Duration: 2019 Mar 182019 Mar 20

Publication series

NameProceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

Conference

Conference1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
CountryTaiwan, Province of China
CityHsinchu
Period19/3/1819/3/20

Fingerprint

Vending machines
Degradation
Processing

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Lee, Y., Lee, C. H., Lee, H. J., & Kim, J. S. (2019). Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine. In Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 (pp. 132-136). [8771517] (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICAS.2019.8771517
Lee, Youhak ; Lee, Chul Hee ; Lee, Hyuk Jae ; Kim, Jin Sung. / Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine. Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 132-136 (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019).
@inproceedings{27ae3926d4ac400087df003e5b576c94,
title = "Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine",
abstract = "Fast object detection is important to enable a vision-based automated vending machine. This paper proposes a new scheme to enhance the operation speed of YOLOv3 by removing the computation for the region of non-interest. In order to avoid the accuracy drop by a removal of computation, characteristics of a convolutional layer and a YOLO layer are investigated, and a new processing method is proposed from experimental results. As a result, the operation speed is increased in proportion to the size of the region of non-interest. Experimental results show that the speed is improved by 3.29 times while the accuracy degradation is 2.81{\%} in mAP-50.",
author = "Youhak Lee and Lee, {Chul Hee} and Lee, {Hyuk Jae} and Kim, {Jin Sung}",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/AICAS.2019.8771517",
language = "English",
series = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "132--136",
booktitle = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",
address = "United States",

}

Lee, Y, Lee, CH, Lee, HJ & Kim, JS 2019, Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine. in Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019., 8771517, Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 132-136, 1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, Hsinchu, Taiwan, Province of China, 19/3/18. https://doi.org/10.1109/AICAS.2019.8771517

Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine. / Lee, Youhak; Lee, Chul Hee; Lee, Hyuk Jae; Kim, Jin Sung.

Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 132-136 8771517 (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019).

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

TY - GEN

T1 - Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine

AU - Lee, Youhak

AU - Lee, Chul Hee

AU - Lee, Hyuk Jae

AU - Kim, Jin Sung

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Fast object detection is important to enable a vision-based automated vending machine. This paper proposes a new scheme to enhance the operation speed of YOLOv3 by removing the computation for the region of non-interest. In order to avoid the accuracy drop by a removal of computation, characteristics of a convolutional layer and a YOLO layer are investigated, and a new processing method is proposed from experimental results. As a result, the operation speed is increased in proportion to the size of the region of non-interest. Experimental results show that the speed is improved by 3.29 times while the accuracy degradation is 2.81% in mAP-50.

AB - Fast object detection is important to enable a vision-based automated vending machine. This paper proposes a new scheme to enhance the operation speed of YOLOv3 by removing the computation for the region of non-interest. In order to avoid the accuracy drop by a removal of computation, characteristics of a convolutional layer and a YOLO layer are investigated, and a new processing method is proposed from experimental results. As a result, the operation speed is increased in proportion to the size of the region of non-interest. Experimental results show that the speed is improved by 3.29 times while the accuracy degradation is 2.81% in mAP-50.

UR - http://www.scopus.com/inward/record.url?scp=85070457049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070457049&partnerID=8YFLogxK

U2 - 10.1109/AICAS.2019.8771517

DO - 10.1109/AICAS.2019.8771517

M3 - Conference contribution

AN - SCOPUS:85070457049

T3 - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

SP - 132

EP - 136

BT - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lee Y, Lee CH, Lee HJ, Kim JS. Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine. In Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 132-136. 8771517. (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019). https://doi.org/10.1109/AICAS.2019.8771517