Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment

摘要

In general, a distributed processing is not suitable for dealing with image data stream due to thenetwork load problem caused by communications of frames. For this reason, image data streamprocessing has operated in just one node commonly. However, we need to process image datastream in a distributed environment in a big data era due to increase in quantity and quality ofmultimedia data. In this paper, we shall present a real-time pedestrian detection methodology ina distributed environment which processes image data stream in real-time on Apache Stormframework. It achieves sharp speed up by distributing frames onto several nodes called bolts,each of which processes different regions of image frames. Moreover, it can reduce theoverhead caused by synchronization by computation bolts which returns only the processingresults to the merging bolts.