数据采集与处理2016，Vol.31Issue(6)：1141-1147,7.
弱监督分层深度学习的车辆识别算法
Vehicle Recognition Algorithm Based on Weakly Supervised Hierarchical Deep Learning
摘要
Abstract
Focusing on the shortage of structure and training methods of existing classifier ,a weakly su‐pervised hierarchical deep learning vehicle recognition algorithm with 2D deep belief networks(2D‐DBN) is proposed .Firstly ,the traditional one‐dimensional deep belief network(DBN) is expanded to 2D‐DBN , thus the pixel matrix of the 2‐D images is taken as the input .Then ,a determination regularization term with proper weight is introduced to the traditional unsupervised training objective function . By this change ,the original unsupervised training is transferred to the weakly supervised training ,so that the ex‐tracted features have more discrimination ability .M ultiple sets of comparative experiments show that the proposed algorithm is better than other deep learning algorithms in respect of recognition rate .关键词
车辆识别/深度学习/弱监督训练/特征提取Key words
vehicle recognition/deep learning/weakly supervised training/feature extraction分类
信息技术与安全科学引用本文复制引用
王海,蔡英凤,陈龙,江浩斌..弱监督分层深度学习的车辆识别算法[J].数据采集与处理,2016,31(6):1141-1147,7.基金项目
国家自然科学基金（61403172，51305167，61203244）资助项目；交通运输部信息化（2013364836900）资助项目；中国博士后基金（2014M561592）资助项目；江苏省“六大人才高峰”（2014-DZXX-040）资助项目；江苏省自然科学基金（BK20140555）资助项目；江苏省博士后基金（1402097C）资助项目；江苏大学高级专业人才科研启动基金（12JDG010，14JDG028）资助项目。 （）
