Automatic basketball detection in sport video based on R-FCN and soft-NMS

Qiaokang Liang, Li Mei, Wanneng Wu, Wei Sun, Yaonan Wang, Dan Zhang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

10 Citations (Scopus)

Abstract

In basketball videos, the ball is always so small in the camera that its appearance feature is hard to be extracted. In this paper, we introduce a deep-learning technology to detect the basketball. Specifically, we train our basketball detection model based on the Region-based Fully Convolutional Networks (R-FCN) which uses the fully convolutional Residual Network (ResNet) as the backbone network. What’s more, we apply some new techniques including Online Hard Example Mining (OHEM), Soft-NMS and multi-scale training strategy to achieve higher detection accuracy. In detail, the OHEM method can reduce the cost of fine-tuning during training by calculating the loss of the RoIs. Soft-NMS can reduce the false positive rate by decreasing the object detection score between the overlap object. And the multi-scale training can improve the detection performance by receiving the good feature from the object with different scale. Finally, we achieve a mean average precision (mAP) value of 89.7% on a public basketball dataset. It proves that applying the deep-learning approach to basketball detection is effective.

Original languageEnglish
Title of host publicationProceedings - 2019 4th International Conference on Automation, Control and Robotics Engineering, CACRE 2019
EditorsFumin Zhang
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450371865
DOIs
Publication statusPublished - 19 Jul 2019
Externally publishedYes
Event4th International Conference on Automation, Control and Robotics Engineering, CACRE 2019 - Shenzhen, China
Duration: 19 Jul 201921 Jul 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Conference on Automation, Control and Robotics Engineering, CACRE 2019
Country/TerritoryChina
CityShenzhen
Period19/07/1921/07/19

Keywords

  • Ball detection
  • Object recognition
  • Region-based fully convolutional networks

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Automatic basketball detection in sport video based on R-FCN and soft-NMS'. Together they form a unique fingerprint.

Cite this