Soccer object motion recognition based on 3D convolutional neural networks
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 17, Issue
Abstract
Due to the development of video understanding and big data analysis research field using deep learning technique, intelligent machines have replaced the tasks that people performed in the past in various fields such as traffic, surveillance, and security area. In the sports field, especially in soccer games, it is also attempting quantitative analysis of players and games through deep learning or big data analysis technique. However, because of the nature of soccer analysis, it is still difficult to make sophisticated automatic analysis due to technical limitations. In this paper, we propose a deep learning based motion recognition technique which is the basis of high level automatic soccer analysis. For sophisticated motion recognition, we maximize recognition accuracy by sequentially processing the data in three steps: data acquisition, data augmentation, and 3D CNN based motion classifier learning. As can be seen from the experimental results, the proposed method guarantees real-time speed performance and satisfactory accuracy performance.
Authors and Affiliations
Jiwon Lee, Do-Won Nam, Wonyoung Yoo, Yoonhyung Kim, Minki Jeong, Changick Kim
Keywords
Related Articles
- EP ID EP568930
- DOI 10.15439/2018F48
- Views 20
- Downloads 0
Unintended effects of dependencies in source code on the flexibility of IT in organizations
This study links business requirements and adaptability of existing software systems. Organizations expect flexibility of IT with regard to business requirements. We hypothesize that the flexibility of business requireme...
Clustered Comparative Analysis of Security Sensor Discrimination Data
Security alarm is used to protect from burglary (theft), property damage and from intruders. These security alarms consists sensors and alerting device to indicate the intrusion. Clustering is data mining technique which...
An Innovative B2C E-commerce Websites Selection using the ME-OWA and Fuzzy AHP
Today internet has emerged as a huge marketplace of products and services for meeting needs of more than a million customers worldwide. It provides users a platform to access information globally in electronic form as we...
Representation Matters: An Unexpected Property of Polynomial Rings and its Consequences for Formalizing Abstract Field Theory
In this paper we develop a Mizar formalization of Kronecker's construction, which states that for every field $F$ and irreducible polynomial $p \in F[X]$ there exists a field extension $E$ of $F$ such that $p$ has a root...
A Survey on Advanced Approaches of EHR in inter-related data using Machine Learning
Medical data is being used for huge number of research works over the globe which is for predicting something novel case studies in each work. The current research which we are handling is on utilizing the EHR (Electroni...