Premium
A novel discrete CURVELET transform and modified WHOG for video surveillance services
Author(s) -
Epsiba P.,
Kumaratharan N.,
Suresh G.
Publication year - 2018
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.5046
Subject(s) - computer science , codec , computer vision , artificial intelligence , curvelet , robustness (evolution) , coding (social sciences) , enhanced data rates for gsm evolution , wavelet transform , mathematics , telecommunications , biochemistry , wavelet , chemistry , statistics , gene
Summary Nowadays, with huge advent of mobile technology and surveillance supports there is increase in demand for visual quality rapidly. H.265/HEVC focuses on HDVC techniques with employing edge object detection‐based scheme. This paper proposes a novel discrete curvelet transform and modified WHOG for video surveillance services. The proposed discrete curvelet transform and modified WHOG‐based schemes were ensured optimal performance both in detection of edges and information coding. The decomposition of bit‐depth among two levels establishes the details of intensity components and Codec efficiency in all level. In addition, to improve the robustness of the proposed method in terms of compression/encoding efficiency, frame‐based statistical features were encountered to optimize the intensity level or depth‐map. The simulated results reveal the effectiveness of the projected algorithm in edge‐based video compression for surveillance services, which avoids edge blurring and retains perceptual quality while reconstruction with viable PSNR.