• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >Fine-Grained Visual Dribbling Style Analysis for Soccer Videos With Augmented Dribble Energy Image
【24h】

Fine-Grained Visual Dribbling Style Analysis for Soccer Videos With Augmented Dribble Energy Image

机译：用于增强运球能量图像的足球视频的细粒度视觉驱动风格分析

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recent advances in interpretations of soccer are predominantly made through analyzing high-level contents of soccer videos. This work targets on these highlight actions and movements in soccer games and it focuses on dribbling skills performed by the top players. Our work leverages understanding of complex dribbling video clips by representing a video sequence with a single Dribble Energy Image(DEI) that is informative for dribbling styles recognition. To overcome the shortage of labelled data, this paper introduces a dataset of soccer video clips from Youtube, employs Mask-RCNN to segment out dribbling players and OpenPose to obtain joints information of dribbling players. Besides, to solve issues caused by camera motions in highlight soccer videos, our work proposes to register a video sequence to generate a single image representation DEI and dribbling styles classification. Our approach can achieve an accuracy of 87.65% on dribbling styles classification and it is observed that data augmentation using joints-reasoned GAN can improve the classification performance.
机译：通过分析足球视频的高级别内容，主要提出了足球解释的最新进展。这项工作的目标是在足球比赛中的这些突出的行动和运动中，它侧重于顶级球员执行的运球技巧。我们的工作通过代表具有单个运输能量图像（DEI）的视频序列来利用复杂的运行视频剪辑，该序列是对运球的识别进行了贸易识别的信息。为了克服标记数据的短缺，本文介绍了来自YouTube的足球视频剪辑的数据集，采用Mask-RCNN分割了运行运行的玩家并展示以获取运球人员的联合信息。此外，为了解决突出足球视频中的摄像机运动引起的问题，我们的工作建议注册视频序列以生成单个图像表示DEI和DRIBBLED STYLES分类。我们的方法可以在运球的款式分类上实现87.65％的准确性，并且观察到使用关节推理GaN的数据增强可以提高分类性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号