摘要
针对目前行人重识别技术的缺点,提出一种基于Siamese网络的行人重识别方法.首先使用Dropout算法对卷积神经网络进行改良,降低发生过拟合问题的概率;而后构造一个Siamese网络,将CNN (Convolution Neural Network)中特征提取和检验相融合,提高图像识别的效率和准确率;最后利用度量学习算法中的马氏距离作为检索图像匹配相似度的评价指标.实验结果表明:针对Market-1501数据集,该方法可以有效提高采用卷积神经网络的行人重识别方法识别效率和准确率.
Aiming at the shortcomings of the current pedestrian re-identification technology, this paper presents a pedestrian re-identification method based on Siamese network. First, Dropout algorithm is used to improve the performance of Convolutional Neural Network (CNN), which can reduce the incidence of the fitting problem. By integration of classification and inspection in the CNN, Siamese network is constructed to improve the efficiency and accuracy of image recognition. Finally, Markov distance for metric learning algorithm is used as the evaluation index of image matching similarity. Experiments are conducted on the Market-1501, and the experimental results show that this method is effective in terms of improving the efficiency and accuracy of pedestrian re-identification algorithm.
作者
叶锋
刘天璐
李诗颖
华笃伟
陈星宇
林文忠
YE Feng;LIU Tian-Lu;LI Shi-Ying;HUA Du-Wei;CHEN Xing-Yu;LIN Wen-Zhong(College of Mathematics and Informatics,Fujian Normal University,Fuzhou 350117,China;Digital Fujian Big Data Security Technology Institute,Fuzhou 350117,China;Fujian Provincial Key Laboratory of Information Processing and Intelligent Control,Minjiang University,Fuzhou 350108,China)
出处
《计算机系统应用》
2020年第4期209-213,共5页
Computer Systems & Applications
基金
福建省自然科学基金面上项目(2017J01739,2018J01779)
闽江学院福建省信息处理与智能控制重点实验室开放基金(MJUKF-IPIC201810)
福州市科技重大项目(榕科(2017)325号)。