Extraction of MapReduce-based features from spectrograms for audio-based surveillance

Manjunath Mulimani, Shashidhar G. Koolagudi

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)


In this paper, we proposed a novel parallel method for extraction of significant information from spectrograms using MapReduce programming model for the audio-based surveillance system, which effectively recognizes critical acoustic events in the surrounding environment. Extraction of reliable information as features from spectrograms of big noisy audio event dataset demands high computational time. Parallelizing the feature extraction using MapReduce programming model on Hadoop improves the efficiency of the overall system. The acoustic events with real-time background noise from Mivia lab audio event data set are used for surveillance applications. The proposed approach is time efficient and achieves high performance of recognizing critical acoustic events with the average recognition rate of 96.5% in different noisy conditions.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalDigital Signal Processing: A Review Journal
Publication statusPublished - 04-2019

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Statistics, Probability and Uncertainty
  • Computational Theory and Mathematics
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Extraction of MapReduce-based features from spectrograms for audio-based surveillance'. Together they form a unique fingerprint.

Cite this