| 基于多阈值PCNN的运动目标检测算法 |
| |
| 引用本文： | 刘映杰,马若飞,朱望飞,者昊,绽琨,马义德.基于多阈值PCNN的运动目标检测算法[J].计算机应用,2009,29(3):739-741. |
| |
| 作者姓名： | 刘映杰 马若飞 朱望飞 者昊 绽琨 马义德 |
| |
| 作者单位： | 1. 兰州大学信息科学与工程学院,兰州,730000
2. 中国华阴兵器试验中心,陕西渭南,714200 |
| |
| 基金项目： | 国家自然科学基金，教育部新世纪优秀人才支持计划，甘肃省自然科学基金 |
| |
| 摘 要： | 在经典的基于混合高斯模型减背景算法的基础上，在脉冲耦合神经网络（PCNN）对前景和背景的分割过程中，运用了多阈值思想，其迭代次数由简化的最大熵准则决定，并且提出了一种新的模型学习率。经过实验证明，该算法在检测能力、抑制噪声、稳定性等方面得到了较好的改进。
|
| 关 键 词： | 运动目标检测 脉冲耦合神经网络 多阈值 简化最大熵 学习率 |
| 收稿时间： | 2008-09-23 |
Moving object detection algorithm based on multi-threshold for PCNN |
| |
| LIU Ying-jie,MA Ruo-fei,ZHU Wang-fei,ZHE Hao,ZHAN Kun,MA Yi-de.Moving object detection algorithm based on multi-threshold for PCNN[J].journal of Computer Applications,2009,29(3):739-741. |
| |
| Authors: | LIU Ying-jie MA Ruo-fei ZHU Wang-fei ZHE Hao ZHAN Kun MA Yi-de |
| |
| Affiliation: | 1.College of Information Science and Engineering;Lanzhou University;Lanzhou Gansu 730000;China;2.China Huayin Weapons Testing Center;Weinan Shaanxi 714200;China |
| |
| Abstract: | Motion detection has a wide range of applications in many artificial intelligence implementations. An improved motion detection algorithm was proposed. Gaussian mixture model of classical algorithm was used, and background and foreground were classified by using Pulse Couple Neural Network (PCNN). PCNN was modified, multi-threshold was adopted to detect object and simple maximum entropy rule was applied to end iteration. Also, a new learning rate was proposed in the model updating stage. Experimental results show that the proposed algorithm improves the ability of detection, noise restraining, stability and so on. |
| |
| Keywords: | motion detection Pulse Couple Neural Network (PCNN) multi-threshold simple maximum entropy learning rate |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
