Detecting a large number of objects in real-time using apache storm

Object detection is an important function for intelligent multimedia processing, but its computational complexity prevented its pervasive uses in consumer electronics. To process large-scale datasets in real-time, more resources and reliable infrastructures are required for spreading the data and running the applications across multiple machines in parallel. In order to detect a large number of objects in real-time, a task-parallel processing framework based on Storm is proposed.

[1]  Ting Liu,et al.  Clustering Billions of Images with Large Scale Nearest Neighbor Search , 2007, 2007 IEEE Workshop on Applications of Computer Vision (WACV '07).

[2]  Bo Li,et al.  Parallel K-Means Clustering of Remote Sensing Images Based on MapReduce , 2010, WISM.

[3]  Brian O'Neill,et al.  Storm blueprints : patterns for distributed real-time computation : use Storm design patterns to perform distributed, real-time big data processing, and analytics for real-world use cases , 2014 .

[4]  Jimmy J. Lin,et al.  Web-scale computer vision using MapReduce for multimedia data mining , 2010, MDMKDD '10.

[5]  Guodong Guo,et al.  Learning from examples in the small sample case: face expression recognition , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.