MapReduce based Big Data Framework for Content Searching of Surveillance System Videos

MapReduce based Big Data Framework for Content Searching of Surveillance System Videos

Zheng Xu (Tsinghua University, Beijing, China & The Third Research Institute of Ministry of Public Security, Shanghai, China), Zhiguo Yan (Fudan University, Shanghai, China) and Huan Du (The Third Research Institute of the Ministry of Public Security, Shanghai, China)
DOI: 10.4018/IJSSCI.2015070104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

CBIR systems go through sets of stages starting from acquiring the new images, representing these images by extracting the image features, describing the key features and eventually computing the similarity distances to get the most relevant results responding to the query image. In this paper, ICBIR an integrated CBIR Hadoop-MapReduce based framework which is split into both offline and online phases is introduced. Visual statements are built using the extracted interest points SIFTs. Later on, these visual statements are used to estimate the similarity distances which in turn are used to create the image dataset clusters. A huge vocabulary of SIFTs describing the interest points of the image is constructed. In this paper, the authors are interested in routing protocols based on clusters that aim to reduce congestion in order to have reliable data transmission and a reduced loss rate. This is achieved by balancing the traffic load, which results into a balanced energy consumption within the network.
Article Preview

1. Introduction

In the last couple of decades, radio-frequency identification (RFID) technology has been widely used in logistics, manufacturing, defense, environment, health care, agriculture, retail, aviation, and information technology (Luo et al., 2011). CBIR systems go through sets of stages starting from acquiring the new images, representing these images by extracting the image features, describing the key features and eventually computing the similarity distances to get the most relevant results responding to the query image. In the manufacturing industry, for example, once an RFID tag is attached to individual parts or products, their location information can be collected in real time, thereby enabling flexible production planning and shipment order placement. Furthermore, if quality issues arise, their causes can be analyzed using corresponding sensor data collected from the relevant manufacturing facility to pinpoint the source of the quality problems. In the food industry, safety management of perishable food has been extended from production to disposal (Y. Liu et al., 2012).

Multimedia systems which enable users to search and retrieve multi types of structured and unstructured data are playing an important role in the IT world. Text, Image and video volumes of data are expanding rapidly. Day after day, this fact attracts the attention of a wide range of researchers and developers trying to enhance the performance of indexing, searching and retrieving these data. As hundreds of words can be summarized by one image, the image retrieval field has become the hot search area for the last decade. A lot of image features extraction approaches were proposed in the literature to describe the image visual content (C. Hu et al., 2014). Considering multiple invariance parameters, many image feature detectors and descriptors were investigated by researchers (X. Liu et al., 2013). IoT-generated data on fuel consumption, carbon emissions, and engine idling can be collected and analyzed in real time in order to plan logistics that minimizes carbon emissions. Multimedia data are characterized by their large volume, and have strict requirements in terms of quality of service (QoS) such as bandwidth, delay, packet loss, delay jitter, etc.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing