• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2011, Vol. 33 ›› Issue (1): 97-101.doi: 10.3969/j.issn.1007130X.2011.

• 论文 • 上一篇    下一篇

基于OpenCV的通用人脸检测模块设计

张莹,李勇平,敖新宇   

  1. (中国科学院上海应用物理研究所,上海 201800)
  • 收稿日期:2009-09-25 修回日期:2010-04-15 出版日期:2011-01-25 发布日期:2011-01-25
  • 通讯作者: 张莹 E-mail:chrysoidine@gmail.com
  • 作者简介:张莹(1986),女,河南获嘉人,硕士,研究方向为生物特征识别。李勇平(1963),男,江西南昌人,研究员,博士生导师,研究方向为图像处理与模式识别、束线控制等。
  • 基金资助:

    国家863计划资助项目(2008AA01Z124)

Design of a Common Face Detection Module Based on OpenCV

ZHANG Ying,LI Yongping,AO Xinyu   

  1. (Shanghai Institute of Applied Physics,Chinese Academy of Sciences,Shanghai 201800,China)
  • Received:2009-09-25 Revised:2010-04-15 Online:2011-01-25 Published:2011-01-25

摘要:

人脸检测是智能视频监控系统中的重要组成部分,OpenCV实现的Adaboost人脸检测算法达到了实时检测人脸的处理速度。但在实际应用中,由于平台移植等障碍,现有系统升级兼容此模块困难。本文提出了一种支持多编程语言平台的通用人脸检测模块,详细阐述了.NET平台调用技术和改进的JNI方法调用OpenCV人脸检测模块的具体步骤和关键过程。该模块解决了.NET、Java和OpenCV彩色图像数据的传递问题,定义了人脸检测模块调用的接口标准,为更多跨平台调用提供参考,可很容易地集成到原有视频监控系统当中。通过多次实验验证,集成该模块的视频系统在系统资源有限的条件下获得了较高的检测率和处理速度。

关键词: 本地方法接口, OpenCV人脸检测, 视频监控, 性能测试

Abstract:

Face detection is an important part in intelligent video surveillance systems. The Adaboost face detection algorithm of OpenCV can process videos in a realtime way. Because of the languages and platforms, very few systems are compatible with such a function. A module of face detection that supports multiple program languages is presented,and the P/Invoke techniques in the .NET and the improved JNI methods for calling the OpenCV face detection module are explained in detail. This module solves the problems of parameter passing among .NET, Java and OpenCV for color images and can be simply integrated into most existing videobased application systems. It also defines a standard interface for module scheduling and can be referenced by more crossplatform applications. The experimental results show that the video systems which integrate this module obtain a high detection rate and realtime processing speed with limited system resources.

Key words: native interface;OpenCV face detection;video surveillance;performance evaluation