Application of Gibbs-Markov random field and Hopfield-type neural networks for detecting moving objects from video sequences captured by static camera
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 605469768 | ||
| 003 | CHVBK | ||
| 005 | 20210128100324.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20151001xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s00500-014-1440-4 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s00500-014-1440-4 | ||
| 245 | 0 | 0 | |a Application of Gibbs-Markov random field and Hopfield-type neural networks for detecting moving objects from video sequences captured by static camera |h [Elektronische Daten] |c [Badri Subudhi, Susmita Ghosh, Ashish Ghosh] |
| 520 | 3 | |a In this article, we propose a moving objects detection scheme using Gibbs-Markov random field(GMRF) and Hopfield-type neural network (HTNN) in expectation maximization (EM) framework for video sequences captured by static camera. In the considered technique, the background model is built by considering a running Gaussian average over few past frames. The change vector analysis (CVA) scheme is followed on the considered target frame and the constructed reference frame to generate a difference image. The moving objects in target frame are detected by segmenting the difference image into two classes: changed and unchanged, where the changed class represents moving object regions and the unchanged class the background regions. For segmentation, we have modeled the CVA generated difference image with GMRF and the segmentation problem is solved using the maximum a posteriori probability (MAP) estimation principle. The MAP estimator is found to be exponential in nature; and thus a modified HTNN is exploited for estimating the MAP. The parameters of the GMRF model are estimated using EM algorithm. Experiments are carried out on three video sequences. Results of the proposed change detection scheme are compared with those of the codebook-based background subtraction and GMRF model with graph-cut schemes. It is found that the proposed technique provides better results. | |
| 540 | |a Springer-Verlag Berlin Heidelberg, 2014 | ||
| 690 | 7 | |a Markov random field |2 nationallicence | |
| 690 | 7 | |a MAP estimation |2 nationallicence | |
| 690 | 7 | |a Hopfield neural network |2 nationallicence | |
| 700 | 1 | |a Subudhi |D Badri |u Department of Electronics and Communication Engineering, National Institute of Technology, Farmagudi, 403401, Ponda, Goa, India |4 aut | |
| 700 | 1 | |a Ghosh |D Susmita |u Department of Computer Science and Engineering, Jadavpur University, 700032, Kolkata, India |4 aut | |
| 700 | 1 | |a Ghosh |D Ashish |u Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India |4 aut | |
| 773 | 0 | |t Soft Computing |d Springer Berlin Heidelberg |g 19/10(2015-10-01), 2769-2781 |x 1432-7643 |q 19:10<2769 |1 2015 |2 19 |o 500 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s00500-014-1440-4 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s00500-014-1440-4 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Subudhi |D Badri |u Department of Electronics and Communication Engineering, National Institute of Technology, Farmagudi, 403401, Ponda, Goa, India |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Ghosh |D Susmita |u Department of Computer Science and Engineering, Jadavpur University, 700032, Kolkata, India |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Ghosh |D Ashish |u Machine Intelligence Unit, Indian Statistical Institute, 700108, Kolkata, India |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t Soft Computing |d Springer Berlin Heidelberg |g 19/10(2015-10-01), 2769-2781 |x 1432-7643 |q 19:10<2769 |1 2015 |2 19 |o 500 | ||