Decision-making system for detection of moving vehicles using a field programmable gate array combining conventional techniques of digital image processing with a fuzzy integral

Ieno, Egidio; Socarrás, Luis Manuel Garcés; Pimenta, Tales Cleber

doi:10.1117/1.jei.27.4.043001

Cited by 2 publications

(1 citation statement)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sports images in physical education are mainly identified by artificial feature extraction or deep learning methods [1]. It can be seen from the research mentioned above the status of human action recognition methods based on standard artificial features that, limited by the performance of artificial features, it is difficult to handle more complex human action recognition tasks, and the drawbacks are too significant and consume too much human and material resources [2]. In recent years, Convolutional Neural Networks (CNN) have achieved good results in object recognition, image classification, etc.…”

Section: Introductionmentioning

confidence: 99%

Application of Depth Learning Algorithm in Automatic Processing and Analysis of Sports Images

Yang¹

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

With the rapid development of sports, the number of sports images has increased dramatically. Intelligent and automatic processing and analysis of moving images are significant, which can not only facilitate users to quickly search and access moving images but also facilitate staff to store and manage moving image data and contribute to the intellectual development of the sports industry. In this paper, a method of table tennis identification and positioning based on a convolutional neural network is proposed, which solves the problem that the identification and positioning method based on color features and contour features is not adaptable in various environments. At the same time, the learning methods and techniques of table tennis detection, positioning, and trajectory prediction are studied. A deep learning framework for recognition learning of rotating flying table tennis is put forward. The mechanism and methods of positioning, trajectory prediction, and intelligent automatic processing of moving images are studied, and the self-built data sets are trained and verified.

show abstract

Section: Introductionmentioning

confidence: 99%