首页> 外文期刊>Microprocessors and microsystems >Image recognition of sports training based on open IoT and embedded wearable devices
【24h】

Image recognition of sports training based on open IoT and embedded wearable devices

机译:基于Open IoT和嵌入式可穿戴设备的体育训练的图像识别

获取原文
获取原文并翻译 | 示例
           

摘要

Computer Vision (CV) is a branch of artificial intelligence that is used to create a system for preparing a computer to understand and eliminate problem with artificial sense and images. Since video is a continuous image, or "shell" classification, this is more it can be used for recording. CV Visually they want to do something with the support framework visual inspection and learning model and high dynamic and visually complex simulation of human visibility part of the precision identification team use real-world images to transform real-world images. Supported vector machines can be used for incredible continuous order in order to be an asset, regular helper vector machine which has high stable performance. Therefore, depending on the installation of the adhesive hop field stabilizing the vector machine image, it is shown in this article. First, the first paragraph is used to prepare the screen confirmation model for deleting image elements based on population, input data acquisition technology invention, and two measurements each program, including carrier information, falls into the blur frame form of an image measurement carrier. At this point, can use the support vector machine 6 alone, the hop field of the support vector machine. The test results may confirm Support Vector Machine (SVM) capability in the hop field of insertion, show it in class 7, to realize an image that is clearer than conventional SVM.
机译:计算机视觉(CV)是人工智能的分支,用于创建用于准备计算机以理解和消除人工意义和图像问题的系统。由于视频是连续图像,或“shell”分类,这更像可用于录制。简历在视觉上,他们想用支持框架的目视检查和学习模型和高动态和视觉复杂模拟的精确识别团队的人体可见性部分使用真实世界的图像来改变现实世界的图像。支持的向量机可用于令人难以置信的连续订单,以便成为一个具有高稳定性能的常规辅助矢量机。因此,根据稳定矢量机图像的粘合跳场的安装,在本文中示出。首先,第一段落用于基于群体,输入数据采集技术发明删除图像元素的屏幕确认模型,以及两个测量每个节目,包括载波信息,落入图像测量载体的模糊框架形式。此时,可以单独使用支持向量机6,支持向量机的跳跃场。测试结果可以在插入的跳跃场中确认支持向量机(SVM)能力,在第7类中显示它,以实现比传统SVM更清晰的图像。

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