Parallelizing Convolutional Neural Networks for Action Event Recognition in Surveillance Videos
Parallelizing Convolutional Neural Networks for Action Event Recognition in Surveillance Videos
复制标题
并行卷积神经网络用于监控视频中的动作事件识别
DOI：
10.1007/s10766-016-0451-4
复制
发表时间：
2016-08
影响因子：
1.5
通讯作者：
Yunqi Lei
中科院分区：
文献类型：
--
作者：
Qicong Wang;Jinhao Zhao;Dingxi Gong;Yehu Shen;Maozhen Li;Yunqi Lei
为了解决大规模视频数据的动作识别问题，针对稀疏自组合时空卷积神经网络SASTCNN，提出了一种基于MapReduce的并行算法。设计并实现了一种基于MapReduce的并行矩阵乘法算法。在Hadoop平台上，利用MapReduce编程模型实现了SASTCNN的并行化。为了充分利用多核CPU的计算能力，采用多线程技术实现了MapReduceMap和Reduces进程。在Weizman和第k个数据集上进行了一系列实验。与传统的串行算法相比，验证了并行SASTCNN算法的可行性、稳定性和正确性，并在计算上获得了加速比。实验结果还表明，与其他基准方法相比，该方法在两个数据集上都能提供更具竞争力的结果。
In order to deal with action recognition for large scale video data, this paper presents a MapReduce based parallel algorithm for SASTCNN, a sparse auto-combination spatio-temporal convolutional neural network. We design and implement a parallel matrix multiplication algorithm based on MapReduce. We use the MapReduce programming model to parallelize SASTCNN on a Hadoop platform. In order to take advantage of the computing power of multi-core CPU, the Map and Reduce processes of MapReduce are implemented using a multi-thread technique. A series of experiments on both WEIZMAN and KTH data sets are carried out. Compared with traditional serial algorithms, the feasibility, stability and correctness of the parallel SASTCNN are validated and a speedup in computation is obtained. Experimental results also show that the proposed method could provide more competitive results on the two data sets than other benchmark methods.
登录
查看更多内容
DOI：
10.1109/wacv.2015.124
发表时间：
2015-01
期刊：
2015 IEEE Winter Conference on Applications of Computer Vision
影响因子：
--
作者：
I. Atmosukarto;N. Ahuja;Bernard Ghanem
通讯作者：
I. Atmosukarto;N. Ahuja;Bernard Ghanem
DOI：
--
发表时间：
2006
期刊：
--
影响因子：
--
作者：
S. Akhter
通讯作者：
S. Akhter
DOI：
10.1109/icsess.2013.6615438
发表时间：
2013-05
期刊：
2013 IEEE 4th International Conference on Software Engineering and Service Science
影响因子：
--
作者：
Jiawei Han;Yanheng Liu;Xin Sun
通讯作者：
Jiawei Han;Yanheng Liu;Xin Sun
DOI：
10.1109/bigdata.2013.6691747
发表时间：
2013-10
期刊：
2013 IEEE International Conference on Big Data
影响因子：
--
作者：
N. C. Tewari;H. M. Koduvely;S. Guha;Arun Yadav;Gladbin David
通讯作者：
N. C. Tewari;H. M. Koduvely;S. Guha;Arun Yadav;Gladbin David
DOI：
10.1109/cvpr.2007.383132
发表时间：
2007-06
期刊：
2007 IEEE Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Juan Carlos Niebles;Li Fei-Fei-Li-Fei-Fei-48004138
通讯作者：
Juan Carlos Niebles;Li Fei-Fei-Li-Fei-Fei-48004138