DeepCounter

Using deep learning to count garbage bags

Kazuhiro Mikami, Yin Chen, Jin Nakazawa, Yasuhiro Iida, Yasunari Kishimoto, Yu Oya

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

3 Citations (Scopus)

Abstract

This paper proposes DeepCounter, an automotive sensing system where deep learning based image processing technology is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck in order to sense a fine-grain spatio-temporal distribution on the amount of disposed garbage in cities that is envisioned to be helpful to develop novel applications related to garbage collection there. A prototype system is implemented on a GPU-integrated signal-board computer. A detection-tracking-counting (DTC) algorithm is developed and implemented based on the single shot multibox detector (SSD), a well-known real-time object detection algorithm. Experimental evaluation validates the feasibility of the proposed approach using video of realistic garbage collection in Fujisawa city, Japan.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-10
Number of pages10
ISBN (Electronic)9781538677599
DOIs
Publication statusPublished - 2019 Jan 9
Event24th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018 - Hakodate, Japan
Duration: 2018 Aug 292018 Aug 31

Publication series

NameProceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018

Conference

Conference24th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018
CountryJapan
CityHakodate
Period18/8/2918/8/31

Fingerprint

Garbage trucks
Printed circuit boards
Image processing
Cameras
Detectors
Deep learning
Object detection
Graphics processing unit

Keywords

  • Automotive sensing
  • Deep learning
  • Image processing
  • Smart cities
  • Urban sensing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Mikami, K., Chen, Y., Nakazawa, J., Iida, Y., Kishimoto, Y., & Oya, Y. (2019). DeepCounter: Using deep learning to count garbage bags. In Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018 (pp. 1-10). [8607228] (Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RTCSA.2018.00010

DeepCounter : Using deep learning to count garbage bags. / Mikami, Kazuhiro; Chen, Yin; Nakazawa, Jin; Iida, Yasuhiro; Kishimoto, Yasunari; Oya, Yu.

Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1-10 8607228 (Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018).

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

Mikami, K, Chen, Y, Nakazawa, J, Iida, Y, Kishimoto, Y & Oya, Y 2019, DeepCounter: Using deep learning to count garbage bags. in Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018., 8607228, Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1-10, 24th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018, Hakodate, Japan, 18/8/29. https://doi.org/10.1109/RTCSA.2018.00010
Mikami K, Chen Y, Nakazawa J, Iida Y, Kishimoto Y, Oya Y. DeepCounter: Using deep learning to count garbage bags. In Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1-10. 8607228. (Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018). https://doi.org/10.1109/RTCSA.2018.00010
Mikami, Kazuhiro ; Chen, Yin ; Nakazawa, Jin ; Iida, Yasuhiro ; Kishimoto, Yasunari ; Oya, Yu. / DeepCounter : Using deep learning to count garbage bags. Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1-10 (Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018).
@inproceedings{ede524b1e8aa41c798936c5ef20bdf41,
title = "DeepCounter: Using deep learning to count garbage bags",
abstract = "This paper proposes DeepCounter, an automotive sensing system where deep learning based image processing technology is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck in order to sense a fine-grain spatio-temporal distribution on the amount of disposed garbage in cities that is envisioned to be helpful to develop novel applications related to garbage collection there. A prototype system is implemented on a GPU-integrated signal-board computer. A detection-tracking-counting (DTC) algorithm is developed and implemented based on the single shot multibox detector (SSD), a well-known real-time object detection algorithm. Experimental evaluation validates the feasibility of the proposed approach using video of realistic garbage collection in Fujisawa city, Japan.",
keywords = "Automotive sensing, Deep learning, Image processing, Smart cities, Urban sensing",
author = "Kazuhiro Mikami and Yin Chen and Jin Nakazawa and Yasuhiro Iida and Yasunari Kishimoto and Yu Oya",
year = "2019",
month = "1",
day = "9",
doi = "10.1109/RTCSA.2018.00010",
language = "English",
series = "Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--10",
booktitle = "Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018",

}

TY - GEN

T1 - DeepCounter

T2 - Using deep learning to count garbage bags

AU - Mikami, Kazuhiro

AU - Chen, Yin

AU - Nakazawa, Jin

AU - Iida, Yasuhiro

AU - Kishimoto, Yasunari

AU - Oya, Yu

PY - 2019/1/9

Y1 - 2019/1/9

N2 - This paper proposes DeepCounter, an automotive sensing system where deep learning based image processing technology is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck in order to sense a fine-grain spatio-temporal distribution on the amount of disposed garbage in cities that is envisioned to be helpful to develop novel applications related to garbage collection there. A prototype system is implemented on a GPU-integrated signal-board computer. A detection-tracking-counting (DTC) algorithm is developed and implemented based on the single shot multibox detector (SSD), a well-known real-time object detection algorithm. Experimental evaluation validates the feasibility of the proposed approach using video of realistic garbage collection in Fujisawa city, Japan.

AB - This paper proposes DeepCounter, an automotive sensing system where deep learning based image processing technology is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck in order to sense a fine-grain spatio-temporal distribution on the amount of disposed garbage in cities that is envisioned to be helpful to develop novel applications related to garbage collection there. A prototype system is implemented on a GPU-integrated signal-board computer. A detection-tracking-counting (DTC) algorithm is developed and implemented based on the single shot multibox detector (SSD), a well-known real-time object detection algorithm. Experimental evaluation validates the feasibility of the proposed approach using video of realistic garbage collection in Fujisawa city, Japan.

KW - Automotive sensing

KW - Deep learning

KW - Image processing

KW - Smart cities

KW - Urban sensing

UR - http://www.scopus.com/inward/record.url?scp=85061719711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061719711&partnerID=8YFLogxK

U2 - 10.1109/RTCSA.2018.00010

DO - 10.1109/RTCSA.2018.00010

M3 - Conference contribution

T3 - Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018

SP - 1

EP - 10

BT - Proceedings - 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -