| 基于CNN和RNN的像素级视频目标跟踪算法 |
| |
| 引用本文： | 崔家梁,冯朝晖,李芹,赵红颖.基于CNN和RNN的像素级视频目标跟踪算法[J].全球定位系统,2019,44(3):1-6. |
| |
| 作者姓名： | 崔家梁 冯朝晖 李芹 赵红颖 |
| |
| 作者单位： | 北京大学 地球与空间科学学院, 北京 100871 |
| |
| 基金项目： | 国家自然科学基金(61672043);国家重点研发计划项目(2017 YEB0503003) |
| |
| 摘 要： | 影像目标跟踪定位技术是当前计算机视觉领域的研究热点,目标跟踪算法也是现阶段将视频结果用于定位的薄弱环节之一.本文分析了像素级目标跟踪存在的问题,根据深度学习在图像领域的最新研究成果与视频跟踪需求,结合最新的图像分割、卷积神经网络(CNN)、循环神经网络(RNN)和加密解码结构等方法提出了一种像素级视频目标跟踪算法.使用公开数据集实现算法并设计了定量评价指标.实验结果表明该算法具有较强的像素级视频目标跟踪定位能力.
|
| 关 键 词： | 视频处理 目标跟踪定位 像素级 深度学习 |
CNN and RNN-based pixel-wise video object tracking algorithm |
| |
| CUI Jialiang,FENG Zhaohui,LI Qin,ZHAO Hongying.CNN and RNN-based pixel-wise video object tracking algorithm[J].Gnss World of China,2019,44(3):1-6. |
| |
| Authors: | CUI Jialiang FENG Zhaohui LI Qin ZHAO Hongying |
| |
| Institution: | School of Earth and Space Sciences, Peking University,Beijing100871,China |
| |
| Abstract: | Video object tracking is a research hotpot of computer vision, but the object tracking algorithm is one of weaknesses in localization with video. In this paper, we introduced the pixel-wise video object tracking problem. We proposed a pixel-wise video object tracking algorithm based on convolution and recurrent neural network of deep learning technology and the latest research results in image segmentation to solve the problem. By designed and conducted an experiment and evaluation on a public dataset, the algorithm shows abilities on obtaining the boundary of objects in videos. |
| |
| Keywords: | video processing object tracking pixel-wise deep learning |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《全球定位系统》浏览原始摘要信息 |
| 点击此处可从《全球定位系统》下载免费的PDF全文 |
