Back to Search
Start Over
Sports Sequence Images Based on Convolutional Neural Network
- Source :
- Mathematical Problems in Engineering, Vol 2021 (2021)
- Publication Year :
- 2021
- Publisher :
- Hindawi Limited, 2021.
-
Abstract
- Convolution neural network has become a hot research topic in the field of computer vision because of its superior performance in image classification. Based on the above background, the purpose of this paper is to analyze sports sequence images based on convolutional neural network. In view of the low detection rate of single-frame and the complexity of multiframe detection algorithms, this paper proposes a new algorithm combining single-frame detection and multiframe detection, so as to improve the detection rate of small targets and reduce the detection time. Based on the traditional residual network, an improved, multiscale, residual network is proposed in this paper. The network structure enables the convolution layer to “observe” data from different scales and obtain more abundant input features. Moreover, the depth of the network is reduced, the gradient vanishing problem is effectively suppressed, and the training difficulty is reduced. Finally, the ensemble learning method of relative majority voting is used to reduce the classification error rate of the network to 3.99% on CIFAR-10, and the error rate is reduced by 3% compared with the original residual neural network.
- Subjects :
- Majority rule
Article Subject
Contextual image classification
business.industry
Computer science
General Mathematics
General Engineering
Word error rate
020206 networking & telecommunications
Pattern recognition
02 engineering and technology
Engineering (General). Civil engineering (General)
Residual
Convolutional neural network
Ensemble learning
Field (computer science)
Convolution
QA1-939
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
TA1-2040
business
Mathematics
Subjects
Details
- ISSN :
- 15635147 and 1024123X
- Volume :
- 2021
- Database :
- OpenAIRE
- Journal :
- Mathematical Problems in Engineering
- Accession number :
- edsair.doi.dedup.....816f6e7610256c89ed4f8134fa3cb801