A video-based basketball goal detection method and device

Abstract

The present invention relates to a basketball goal detection method and device based on video, the method comprising: constructing a recursive convolutional neural network model based on a convolutional neural network and a recursive neural network; constructing a picture library sample set of a basketball video, said The pictures in the picture library have tags, and the tags include timing information and goal identification information; the recursive convolutional neural network model is trained based on the sample set; images are extracted from the basketball video to be detected, and the training is used The final recursive convolutional neural network model processes the extracted image to obtain an output vector; according to the output vector of the recursive convolutional neural network, it is judged whether there is a goal in the current basketball video. The invention can accurately detect whether a basketball is scored or not based on the video.

Description

technical field [0001] The present invention relates to video detection technology, and more particularly relates to a method and device for detecting basketball goals based on video. Background technique [0002] With the rapid development of science and technology, videos that only professional cameras can shoot in the past can now be completed with a smart phone. Based on this, various types of videos uploaded to the Internet have shown a blowout state in recent years, and With the continuous development of Internet technology and digital media technology, how to analyze a specific type of video has gradually become a research hotspot. [0003] There are a large number of sports videos on the Internet today, a large part of which are basketball videos. There are some studies on basketball videos, but most of them focus on player detection or stadium event analysis, such as the analysis of players or stadium audiences. There are very few goal detections in basketball vide...

AI Technical Summary

Problems solved by technology

[0003] There are a large number of sports videos on the Internet today, a large part of which are basketball videos. There are some studies on basketball videos, but most of them focus on player detection or stadium event analysis, such as the analysis of players or stadium audiences. There are very few goal detections in basketball videos. A large part of the reason is that the goals in basketball videos are a continuous and dynamic process, unlike player detection or audience analysis, which is a relatively static process.

Images