TY - GEN
T1 - Automatic basketball detection in sport video based on R-FCN and soft-NMS
AU - Liang, Qiaokang
AU - Mei, Li
AU - Wu, Wanneng
AU - Sun, Wei
AU - Wang, Yaonan
AU - Zhang, Dan
N1 - Publisher Copyright:
© 2019 Copyright is held by the owner/author(s).
PY - 2019/7/19
Y1 - 2019/7/19
N2 - 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.
AB - 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.
KW - Ball detection
KW - Object recognition
KW - Region-based fully convolutional networks
UR - https://www.scopus.com/pages/publications/85073240153
U2 - 10.1145/3351917.3351970
DO - 10.1145/3351917.3351970
M3 - Conference article published in proceeding or book
AN - SCOPUS:85073240153
T3 - ACM International Conference Proceeding Series
BT - Proceedings - 2019 4th International Conference on Automation, Control and Robotics Engineering, CACRE 2019
A2 - Zhang, Fumin
PB - Association for Computing Machinery
T2 - 4th International Conference on Automation, Control and Robotics Engineering, CACRE 2019
Y2 - 19 July 2019 through 21 July 2019
ER -