江苏大学学报（自然科学版）2018，Vol.39Issue(3)：303-308,329,7.DOI:10.3969/j.issn.1671-7775.2018.03.010
基于改进LRCN模型的驾驶行为图像序列识别方法
Image sequence recognition method for driving behavior based on improved LRCN model
摘要
Abstract
To solve the problems of low recognition accuracy and slow convergence speed for driving behavior in driving assistant technology,a new driving behavior recognition method was proposed based on improved LRCN model. The self driving behavior data sets were adopted as input samples and were processed by Pyramid down sampling and Gauss mixture model feature extraction preprocessing algorithm, and the standard video image sequence was obtained. The image sequence was introduced into the model based on convolutional neural network and gating unit recursive network,and the optimization was conducted to get the final result of convergence. The model was calculated on the GPU with Keras framework,and environment adaptability,preprocessing algorithm and model comparison experiments were carried out respectively. The results show that the pretreatment algorithm can guarantee the convergence of the proposed model and can improve the robustness of the model recognition in different scenes and different test objects. The average recognition accuracy in the self building data set reaches 94. 3% and is 4.7% higher than that of the traditional LRCN model. The model also has faster convergent speed and stronger generalization ability.关键词
驾驶行为识别/高斯混合模型/深度学习/卷积神经网络/GRU递归网络Key words
driving behavior recognition/Gauss mixture model/deep learning/convolution neural network/GRU recurrent network分类
信息技术与安全科学引用本文复制引用
吴昊,平鹏,孙立博,秦文虎..基于改进LRCN模型的驾驶行为图像序列识别方法[J].江苏大学学报（自然科学版）,2018,39(3):303-308,329,7.基金项目
国家科技重大专项项目(2014ZX07405002C) （2014ZX07405002C）
国家自然基金青年科学基金资助项目(61300101) （61300101）
中央高校基本科研业务费专项项目(2242017K40114) （2242017K40114）
