casa 20(20): e3

Research Article

Reproducibility of AOD Algorithm: An Experimental evaluation for Key-Predictors Identification

Download768 downloads
  • @ARTICLE{10.4108/eai.13-7-2018.164099,
        author={Monika Monika and Kamaldeep Kaur},
        title={Reproducibility of AOD Algorithm: An Experimental evaluation for Key-Predictors Identification},
        journal={EAI Endorsed Transactions on Context-aware Systems and Applications},
        volume={7},
        number={20},
        publisher={EAI},
        journal_a={CASA},
        year={2020},
        month={4},
        keywords={Abandoned Object Detection, AOD Algorithm, Benchmark Dataset, Reproducibility, Video Processing},
        doi={10.4108/eai.13-7-2018.164099}
    }
    
  • Monika Monika
    Kamaldeep Kaur
    Year: 2020
    Reproducibility of AOD Algorithm: An Experimental evaluation for Key-Predictors Identification
    CASA
    EAI
    DOI: 10.4108/eai.13-7-2018.164099
Monika Monika1,*, Kamaldeep Kaur1
  • 1: Department of Computer Science & Engineering, University School of Information and Communication Technology, Guru Gobind Singh Indraprastha University, Sector - 16C, Dwarka, New Delhi – 110078, India
*Contact email: monika.usict.099164@ipu.ac.in

Abstract

INTRODUCTION: Today surveillance systems are widespread across the globe for monitoring of various activities. Abandoned Object Detection (AOD) and identifying its location is one of them. In this paper, we evaluated the reproducibility of an existing AOD algorithm on benchmark video datasets.

OBJECTIVES: The purpose of the study is to identify the key predictors for developing a generalized AOD algorithm.

METHODS: The algorithm selection is performed by a detailed exploration of repositories through various research questions (RQs).

RESULTS: After the study video summarization, Correct Detection Rate (CDR), generalized Region of Interest (ROI), background learning, and interaction factor considered for enhancing the AOD algorithm.

CONCLUSION: Identification of suspiciousness has various measures depending upon perception, on the basis of results explored the existing algorithm can be improved using key-predictors with observational parameters.