DOC PREVIEW
UT Arlington EE 5359 - Evaluation of moving object detection in H.264 compressed domain

This preview shows page 1-2-3-4-5 out of 15 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 15 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Evaluation of moving object detection in H.264 compressed domainKey parameter:Compressed Domain Object detectionSlide 4Slide 5Slide 6Slide 7Finding motion from frame to frameSlide 9Slide 10Scope of the projectReferences:Slide 13Slide 14Slide 15Instructor : Dr. K. R. RaoPresented by : Vigneshwaran SivaravindiranEmail : [email protected] The key parameter to perform object detection in compressed domain is to determine motion vector estimate. Motion vector estimate is used to predict the moving object block.Algorithm: Rearrange the frames from bit stream order to display order. Consider three pairs of arrays present, past and future for storing the motion vectors. The process of inputting the motion vectors into correct arrays and reordering frames were incorporated into the decoder.Each video sequence is divided into one or more group of pictures (GOPs), the display order of the GOPs will be of the form given in fig . 1,  Here I , B and P are intra-coded, bidirectional prediction and predicted frames.Fig 1: MPEG group of pictures – Display order [9].But the encoder output in bit stream order will be of the form I P B B P B B I P B B P B B. [9] If a P frame is encountered, place it in a temporary storage called future. P frame will be left in the future until another I or P frame comes in, on arrival of a new I or P frame, the already existing I or P frame is removed from the future and put in the display order. All B frames are immediately put in display order.Next step is to obtain the motion vectors from these frames.Fig.2. Flow chart of the operational program. [7]Frame handling- Program OperationEach incoming frames are placed in a past, present or future array locations based on their type (i.e) either a P, I or B frame.The size of the array will be equal to the frame size in macro blocks, (i.e) the frame size used in this project is 240x320, for a motion vector of block size 8x8, array size would be 30x40. Once the motion vectors are stored, the next step is to find the motion from frame to frame. The output of the present and past frame array motion vectors are used to find the motion from frame to frame.Past Present Vector types that can be subtractedI B or P Forward onlyI I NoneP B or P Forward onlyP I NoneB B or P Forward and backwardTable 1: Constraints to be taken into account. For example, consider a transition from B frame to a P or B frame, it has both the forward and backward vector to be considered.  let a B frame macro block motion vector have values (4, -6) for forward prediction and (-6,1) for backward prediction. Let a P frame macro block motion vector have values (9,-7) for forward and (0,0) for backward, as P frame doesn’t have a backward prediction. Total motion will be average of forward and backward prediction. Forward = (9,-7) – (4,-6)=(5,-1) , backward = (0,0) – (-6,1) = (6,-1) The corresponding motion vector values are written into a file one for horizontal and another for vertical and its values were plotted using MATLAB. The motion vector which gave a maximum direction was spotted and its corresponding spatial domain coordinate location was noted. For example, suppose the array location (16,24) gave the maximum motion vector magnitude, then the corresponding spatial coordinates was marked as (128,192). Two essential modules are required to obtain the study of the moving object detection in compressed domain First is the manual annotation of hand locations using a GUI to get the co-ordinate location of the hand in every frame. Second is to obtain time series of hand locations based on compressed domain algorithm.[1] Z.Qiya and L. Zhicheng, “Moving object detection algorithm for H.264/AVC compressed video stream”, ISECS International Colloquium on Computing Communication, control and management,vol .7,pp. 186-189, Sep. 2009. [2] K.Kapotas and A. N. Skodras,” Moving object detection in the H.264 compressed domain”, International Conference on Imaging systems and techniques, vol. 5, pp. 325-328, Aug. 2010.[3] S. Y. Elhabian, K. M. El-Sayed,” Moving object detection in spatial domain using background removal techniques- state of the art”, Recent patents on computer science, vol. 6, pp. 32-54, Apr. 2008.[4] O. Sukmarg and K.R Rao,” Fast object detection and segmentation in MPEG compressed domain”, proceedings of the 10th IEEE Region Annual International Conference, vol. 3, pp. 364-368, Mar. 2000.[5] W.B. Thompson and P Ting Chuen ,” Detecting moving objects”, International journal of computer vision,vol.6, pp. 39-57, Jun. 1990. [6] JM software - http://iphome.hhi.de/suehring/tml/[7] V. Y. Mariano, et al,”Performance evaluation of object detection algorithms” International conference on pattern recognition, Vol.3, pp. 965 – 969, June. 2002.N[8] J. C Nascimento and J. S Marques,” Performance evalaution of object detection algorithms for video survillance”, IEEE Transactions on multimedia, vol. 8, pp. 761-774, Dec. 2006..[9] J Gilvarry,”Calculation of motion using motion vectors extracted from an MPEG stream”, Proc. ACM Multimedia 99, Boston MA, vol. 4,pp. 3-50, Sept . 1999.Thank


View Full Document

UT Arlington EE 5359 - Evaluation of moving object detection in H.264 compressed domain

Documents in this Course
JPEG 2000

JPEG 2000

27 pages

MPEG-II

MPEG-II

45 pages

MATLAB

MATLAB

22 pages

AVS China

AVS China

22 pages

Load more
Download Evaluation of moving object detection in H.264 compressed domain
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Evaluation of moving object detection in H.264 compressed domain and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Evaluation of moving object detection in H.264 compressed domain 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?