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 proceedingConference contributionpeer-review

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 languageEnglish
Title of host publication2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728114859
DOIs
StatePublished - Jul 2020
Event2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020 - London, United Kingdom
Duration: 6 Jul 202010 Jul 2020

Publication series

Name2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020

Conference

Conference2020 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2020
CountryUnited Kingdom
CityLondon
Period6/07/2010/07/20

Keywords

  • And embedded deep learning
  • Autonomous driving
  • Object detection

Fingerprint Dive into the research topics of 'The 2020 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries'. Together they form a unique fingerprint.

Cite this