arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05101cs.CVcs.AI
收藏

基于时空光流的视频动作识别

Video Action Recognition Using spatio-temporal optical flow video frames

Kapital Bank(资本银行);Khazar University(哈扎尔大学);Consumer Experience Tribe(消费者体验部落);Lumos Extension(Lumos扩展);School of Data(数据学院)

Aytekin Nebisoy, Saber Malekzadeh

摘要:

基于视频的人体动作识别是近年来计算机视觉研究的热点之一。该领域有许多应用,如监控,机器人,医疗保健,视频搜索和人机交互。在视频中识别人的动作存在许多问题,例如背景杂乱、障碍物、视点变化、执行速度和摄像机移动。已经提出了大量的方法来解决这些问题。本文重点研究了使用深度神经网络进行视频分类的空间和时间模式识别。该模型将RGB图像和光流作为输入数据,并输出动作类编号。最终的识别准确率约为94%。

英文摘要:

Recognizing human actions based on videos has became one of the most popular areas of research in computer vision in recent years. This area has many applications such as surveillance, robotics, health care, video search and human-computer interaction. There are many problems associated with recognizing human actions in videos such as cluttered backgrounds, obstructions, viewpoints variation, execution speed and camera movement. A large number of methods have been proposed to solve the problems. This paper focus on spatial and temporal pattern recognition for the classification of videos using Deep Neural Networks. This model takes RGB images and Optical Flow as input data and outputs an action class number. The final recognition accuracy was about 94%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑