The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries

Chia Chi Tsai; Yong Hsiang Yang; Hung Wei Lin; Bo Xun Wu; En Chih Chang; Hung Yu Liu; Jhih Sheng Lai; Po Yuan Chen; Jia Jheng Lin; Jen Shuo Chang; Li Jen Wang; Ted Kuo; Jenq Neng Hwang; Jiun-In Guo

doi:10.1109/ICMEW46912.2020.9106010

The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries

Chia Chi Tsai, Yong Hsiang Yang, Hung Wei Lin, Bo Xun Wu, En Chih Chang, Hung Yu Liu, Jhih Sheng Lai, Po Yuan Chen, Jia Jheng Lin, Jen Shuo Chang, Li Jen Wang, Ted Kuo, Jenq Neng Hwang, Jiun-In Guo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Scopus citations

Abstract

The 2020 Embedded Deep Learning Object Detection Model Compression Competition for traffic in Asian countries held in IEEE ICME2020 focuses on the object detection technologies in autonomous driving scenarios. This competition targets on realizing the deep learning object detection through embedded systems with low complexity and model size. The dataset, recorded in Asian countries (e.g., Taiwan), contains several harsh driving environments, including crowded scooters, bicycles, pedestrians and vehicles. There are 89, 002 annotated images provided for training and 1, 000 images for validation. Additional 5, 400 testing images are used in the contest evaluation process, in which 2, 700 of them is used in the qualification stage, and the rest are used in the final stage. There are in total 133 of registered participating teams joining this competition. We have selected the top 10 teams with the highest detection accuracy entering the final competition, from which 8 teams submitted the final results. The overall best model belongs to team USTC-NELSLIP, followed by team "BUPT_MCPRL"and team "DD_VISION". Two special awards of best bicycle and scooter detections go to teams "IBDO-AIOT"and "Deep Learner", respectively.

Original language	English
Title of host publication	2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781728114859
DOIs	https://doi.org/10.1109/ICMEW46912.2020.9106010
State	Published - Jul 2020
Event	2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020 - London, United Kingdom Duration: 6 Jul 2020 → 10 Jul 2020

Publication series

Name	2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020

Conference

Conference	2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020
Country/Territory	United Kingdom
City	London
Period	6/07/20 → 10/07/20

Keywords

And embedded deep learning
Autonomous driving
Object detection

Access to Document

10.1109/ICMEW46912.2020.9106010

Cite this

Tsai, C. C., Yang, Y. H., Lin, H. W., Wu, B. X., Chang, E. C., Yu Liu, H., Lai, J. S., Chen, P. Y., Lin, J. J., Chang, J. S., Wang, L. J., Kuo, T., Hwang, J. N., & Guo, J.-I. (2020). The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries. In 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020 (pp. 1-6). Article 9106010 (2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMEW46912.2020.9106010

Tsai, Chia Chi ; Yang, Yong Hsiang ; Lin, Hung Wei et al. / The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries. 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 1-6 (2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020).

@inproceedings{caffe43ef47f42afb3137331a1283814,

title = "The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries",

abstract = "The 2020 Embedded Deep Learning Object Detection Model Compression Competition for traffic in Asian countries held in IEEE ICME2020 focuses on the object detection technologies in autonomous driving scenarios. This competition targets on realizing the deep learning object detection through embedded systems with low complexity and model size. The dataset, recorded in Asian countries (e.g., Taiwan), contains several harsh driving environments, including crowded scooters, bicycles, pedestrians and vehicles. There are 89, 002 annotated images provided for training and 1, 000 images for validation. Additional 5, 400 testing images are used in the contest evaluation process, in which 2, 700 of them is used in the qualification stage, and the rest are used in the final stage. There are in total 133 of registered participating teams joining this competition. We have selected the top 10 teams with the highest detection accuracy entering the final competition, from which 8 teams submitted the final results. The overall best model belongs to team USTC-NELSLIP, followed by team {"}BUPT_MCPRL{"}and team {"}DD_VISION{"}. Two special awards of best bicycle and scooter detections go to teams {"}IBDO-AIOT{"}and {"}Deep Learner{"}, respectively. ",

keywords = "And embedded deep learning, Autonomous driving, Object detection",

author = "Tsai, {Chia Chi} and Yang, {Yong Hsiang} and Lin, {Hung Wei} and Wu, {Bo Xun} and Chang, {En Chih} and {Yu Liu}, Hung and Lai, {Jhih Sheng} and Chen, {Po Yuan} and Lin, {Jia Jheng} and Chang, {Jen Shuo} and Wang, {Li Jen} and Ted Kuo and Hwang, {Jenq Neng} and Jiun-In Guo",

year = "2020",

month = jul,

doi = "10.1109/ICMEW46912.2020.9106010",

language = "English",

series = "2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--6",

booktitle = "2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020",

address = "United States",

note = "2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020 ; Conference date: 06-07-2020 Through 10-07-2020",

}

Tsai, CC, Yang, YH, Lin, HW, Wu, BX, Chang, EC, Yu Liu, H, Lai, JS, Chen, PY, Lin, JJ, Chang, JS, Wang, LJ, Kuo, T, Hwang, JN & Guo, J-I 2020, The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries. in 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020., 9106010, 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020, London, United Kingdom, 6/07/20. https://doi.org/10.1109/ICMEW46912.2020.9106010

The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries. / Tsai, Chia Chi; Yang, Yong Hsiang; Lin, Hung Wei et al.
2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 1-6 9106010 (2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries

AU - Tsai, Chia Chi

AU - Yang, Yong Hsiang

AU - Lin, Hung Wei

AU - Wu, Bo Xun

AU - Chang, En Chih

AU - Yu Liu, Hung

AU - Lai, Jhih Sheng

AU - Chen, Po Yuan

AU - Lin, Jia Jheng

AU - Chang, Jen Shuo

AU - Wang, Li Jen

AU - Kuo, Ted

AU - Hwang, Jenq Neng

AU - Guo, Jiun-In

PY - 2020/7

Y1 - 2020/7

N2 - The 2020 Embedded Deep Learning Object Detection Model Compression Competition for traffic in Asian countries held in IEEE ICME2020 focuses on the object detection technologies in autonomous driving scenarios. This competition targets on realizing the deep learning object detection through embedded systems with low complexity and model size. The dataset, recorded in Asian countries (e.g., Taiwan), contains several harsh driving environments, including crowded scooters, bicycles, pedestrians and vehicles. There are 89, 002 annotated images provided for training and 1, 000 images for validation. Additional 5, 400 testing images are used in the contest evaluation process, in which 2, 700 of them is used in the qualification stage, and the rest are used in the final stage. There are in total 133 of registered participating teams joining this competition. We have selected the top 10 teams with the highest detection accuracy entering the final competition, from which 8 teams submitted the final results. The overall best model belongs to team USTC-NELSLIP, followed by team "BUPT_MCPRL"and team "DD_VISION". Two special awards of best bicycle and scooter detections go to teams "IBDO-AIOT"and "Deep Learner", respectively.

AB - The 2020 Embedded Deep Learning Object Detection Model Compression Competition for traffic in Asian countries held in IEEE ICME2020 focuses on the object detection technologies in autonomous driving scenarios. This competition targets on realizing the deep learning object detection through embedded systems with low complexity and model size. The dataset, recorded in Asian countries (e.g., Taiwan), contains several harsh driving environments, including crowded scooters, bicycles, pedestrians and vehicles. There are 89, 002 annotated images provided for training and 1, 000 images for validation. Additional 5, 400 testing images are used in the contest evaluation process, in which 2, 700 of them is used in the qualification stage, and the rest are used in the final stage. There are in total 133 of registered participating teams joining this competition. We have selected the top 10 teams with the highest detection accuracy entering the final competition, from which 8 teams submitted the final results. The overall best model belongs to team USTC-NELSLIP, followed by team "BUPT_MCPRL"and team "DD_VISION". Two special awards of best bicycle and scooter detections go to teams "IBDO-AIOT"and "Deep Learner", respectively.

KW - And embedded deep learning

KW - Autonomous driving

KW - Object detection

UR - http://www.scopus.com/inward/record.url?scp=85091790496&partnerID=8YFLogxK

U2 - 10.1109/ICMEW46912.2020.9106010

DO - 10.1109/ICMEW46912.2020.9106010

M3 - Conference contribution

AN - SCOPUS:85091790496

T3 - 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020

SP - 1

EP - 6

BT - 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020

Y2 - 6 July 2020 through 10 July 2020

ER -

Tsai CC, Yang YH, Lin HW, Wu BX, Chang EC, Yu Liu H et al. The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries. In 2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 1-6. 9106010. (2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020). doi: 10.1109/ICMEW46912.2020.9106010

The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this