A Realtime Framework for Video Object Detection with Storm

Real-time response is a challenging issue for video object detection, especially when the number of cameras is large and correspondingly the video data are big. The existing solutions for object detection fall short in addressing the real-time performance aspect, and can not handle fast response requirements such as fleeing vehicle tracking at run time. Therefore, in this paper we propose a Storm-based real-time framework for video object detection that can scale to handle large number of cameras. To evaluate its performance, we implement the framework in a Storm cluster environment where we test the detection rate and real-time performance of the framework. The results show that the detection rate is relatively acceptable and real-time response is achieved.

[1]  Lin Tian,et al.  A Web Server Cluster Solution Based on Twitter Storm , 2014 .

[2]  Simpal Kumar,et al.  Real Time Data Analysis for Water Distribution Network using Storm , 2014 .

[3]  Myoungjin Kim,et al.  Towards Efficient Design and Implementation of a Hadoop-based Distributed Video Transcoding System in Cloud Computing Environment , 2013 .

[4]  Chia-Chen Hung,et al.  Scaling the Real-Time Traffic Sensing with GPS Equipped Probe Vehicles , 2014, 2014 IEEE 79th Vehicular Technology Conference (VTC Spring).

[5]  John D. Owens,et al.  Three-layer optimizations for fast GMM computations on GPU-like parallel processors , 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

[6]  Liu Jia,et al.  GPU accelerated GMM supervectors for speaker and language recognition , 2012, 2012 IEEE 11th International Conference on Signal Processing.

[7]  Scott Shenker,et al.  Spark: Cluster Computing with Working Sets , 2010, HotCloud.

[8]  Jian Tang,et al.  T-Storm: Traffic-Aware Online Scheduling in Storm , 2014, 2014 IEEE 34th International Conference on Distributed Computing Systems.

[9]  David Schreiber,et al.  GPU-based non-parametric background subtraction for a practical surveillance system , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[10]  Yi Yang,et al.  Parallel Algorithm for Moving Foreground Detection in Dynamic Background , 2012, 2012 Fifth International Symposium on Computational Intelligence and Design.

[11]  Dilpreet Singh,et al.  A survey on platforms for big data analytics , 2014, Journal of Big Data.

[12]  Abraham Bernstein,et al.  Network-Aware Workload Scheduling for Scalable Linked Data Stream Processing , 2013, International Semantic Web Conference.

[13]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[14]  Weishan Zhang,et al.  Food Image Recognition Using Pervasive Cloud Computing , 2013, 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing.

[15]  Jan Vanek,et al.  Full covariance Gaussian mixture models evaluation on GPU , 2012, 2012 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[16]  Borko Furht,et al.  A study of transcoding on cloud environments for video content delivery , 2010, MCMC '10.

[17]  Roberto Baldoni,et al.  Adaptive online scheduling in storm , 2013, DEBS.

[18]  D. Scott Wills,et al.  Accelerating Adaptive Background Modeling on Low-Power Integrated GPUs , 2012, 2012 41st International Conference on Parallel Processing Workshops.