ISSN ONLINE(2320-9801) PRINT (2320-9798)

All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.

An Advanced Moving Object Detection Algorithm for Automatic Traffic Monitoring In Real-World Limited Bandwidth Networks

K.G.S. Venkatesan1, Dr. V. Khanaa2, M.Sriram3, Lekha Sri4
  1. Associate Professor, Dept. of C.S.E., Bharath University, Chennai. Tamil Nadu, India.
  2. Dean of Information Technology, Bharath University, Chennai, Tamil Nadu, India.
  3. Assistant Professor, Dept. of C.S.E., Bharath University, Chennai, Tamil Nadu, India.
  4. Dept. of C.S.E., Bharath University, Chennai, Tamil Nadu, India.
Related article at Pubmed, Scholar Google

Visit for more related articles at International Journal of Innovative Research in Computer and Communication Engineering

Abstract

Machine-controlled motion detection technology is Associate in nursing integral element of intelligent transportation systems, and is especially essential for management of traffic and maintenance of traffic police investigation systems. Traffic police investigation systems mistreatment video communication over real-world networks with restricted information measure typically encounter difficulties attributable to network congestion and/or unstable information measure. This is often particularly problematic in wireless video communication. This has necessitated the event of a rate management theme that alters the bit-rate to match the procurable network information measure, thereby manufacturing variable bit-rate video streams. However, complete and correct detection of moving objects beneath variable bit-rate video streams could be a terribly tough task. During this paper, we tend to propose Associate in nursing approach for motion detection that utilizes Associate in nursing analysis - primarily based radial basis perform network as its principal element. This approach is applicable not solely in high bit-rate video streams, however in low bit- rate video streams, as well. The planned approach consists of a varied background generation stage and a moving object detection stage. Throughout the assorted background generation stage, the lower-dimensional Eigen-patterns and also the adjustive background model are established in variable bit -rate video streams by mistreatment the planned approach so as to accommodate the properties of variable bit-rate video streams. Throughout the moving object detection stage, moving objects are extracted via the planned approach in each low bit -rate and high bit- rate video streams; detection results are then generated through the output worth of the planned approach. The detection results created through our approach indicate it to be extremely effective in variable bit-rate video streams over real-world restricted information measure networks. Additionally, the planned methodology will be simply achieved for period of time application. Quantitative and qualitative evaluations demonstrate that it offers blessings over different state- of-the -art ways. For example, and accuracy rates created via the planned approach were up to eighty six.38% and 89.88% beyond those created via different compared ways.