计算机应用 ›› 2016, Vol. 36 ›› Issue (5): 1371-1377.DOI: 10.11772/j.issn.1001-9081.2016.05.1371

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于时间上下文跟踪学习检测的指尖跟踪方法

侯荣波, 康文雄, 房育勋, 黄荣恩, 徐伟钊   

  1. 华南理工大学 自动化科学与工程学院, 广州 510640
  • 收稿日期:2015-07-20 修回日期:2015-09-15 出版日期:2016-05-10 发布日期:2016-05-09
  • 通讯作者: 康文雄
  • 作者简介:侯荣波(1993-),男,广东肇庆人,硕士研究生,主要研究方向:图像处理、计算机视觉、目标跟踪;康文雄(1976-),男,湖南新化人,副教授,博士,主要研究方向:图像处理、模式识别、生物特征识别、计算机视觉;房育勋(1993-),男,广东梅州人,硕士研究生,主要研究方向:机器学习、生物特征识别;黄荣恩(1994-),男,广东中山人,硕士研究生,主要研究方向:小型无人直升机导航定位、跟踪算法;徐伟钊(1993-),男,广东新会人,硕士研究生,主要研究方向:表面肌电信号处理。
  • 基金资助:
    国家自然科学基金资助项目(61573151);广州市科技计划项目(201510010088);广州市越秀区科技计划项目(2014-CY-003);中央高校基本科研业务费资助项目(2014ZG0041,10561201446)。

Fingertip tracking method based on temporal context tracking-learning-detection

HOU Rongbo, KANG Wenxiong, FANG Yuxun, HUANG Rongen, XU Weizhao   

  1. College of Automation Science and Engineering, South China University of Technology, Guangzhou Guangdong 510640, China
  • Received:2015-07-20 Revised:2015-09-15 Online:2016-05-10 Published:2016-05-09
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61573151), the Science and Technology Program of Guangzhou (201510010088), the Science and Technology Program of Yuexiu District, Guangzhou (2014-CY-003), and the Fundamental Research Funds for the Central Universities (2014ZG0041, 10561201446).

摘要: 针对在基于视频的空中签名认证系统中,现有方法无法满足指尖跟踪的准确性、实时性和鲁棒性要求的问题,在对比研究目前常用的多种跟踪方法的基础上,提出一种基于时间上下文的跟踪-学习-检测(TLD)方法。在原始TLD算法的基础上引入时间上下文信息,即相邻两帧间指尖运动具有连续性的先验知识,自适应地缩小检测和跟踪的搜索范围,以提高跟踪的速度。对12组公开的1组自录的视频序列的实验结果表明,改进后的TLD算法能够准确地跟踪指尖,并且跟踪速度达到43帧/秒;与原始TLD跟踪算法相比,准确率提高了15%,跟踪速度至少提高1倍,达到了指尖跟踪的准确性、实时性和鲁棒性要求。

关键词: 目标跟踪, 指尖跟踪, 跟踪-学习-检测算法, 时间上下文, 人机交互

Abstract: In the video based in-air signature verification system, the existed methods cannot meet the requirement of accuracy, real time, robustness for fingertip tracking. To solve this problem, the Tracking-Learning-Detection (TLD) method based on temporal context was proposed. Based on the original TLD algorithm, the temporal context massage, namely the prior knowledge that the movement of fingertip is continuity in two adjacent frames, was introduced to narrow the search range of detection and tracking adaptively, thereby improving tracking speed. The experimental results on 12 public and 1 self-made video sequences show that the improved TLD algorithm can accurately track fingers, and tracking speed can reach 43 frames per secend. Compared with the original TLD tracking algorithm, the accuracy was increased by 15% and the tracking speed was increased more than 100%, which make the proposed method meet the real-time requirements for fingertip tracking.

Key words: object tracking, fingertip tracking, Tracking-Learning-Detection (TLD) algorithm, temporal context, human computer interaction

中图分类号: