TY - JOUR ID - TI - A System Model Based on Slantlet Transform to Estimate Optical Flow AU - Dr. Atheer A. Sabri1 AU - Hamsa D. Majeed1 PY - 2013 VL - 13 IS - 1 SP - 32 EP - 40 JO - IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING المجلة العراقية لهندسة الحاسبات والاتصالات والسيطرة والنظم SN - 18119212 AB - Abstract–The estimation of optical flow is the basic step for many engineeringapplications that exploit the image processing field as a part of their models. In thispaper a model called Slantlet Based Optical Flow Estimation (SLT_OFE) is proposed toestimate the optical flow. Slantlet Transform (SLT) used as an effective tool, 2D and3D- SLT- Level 2 (SLT2) are computed and employed in the proposed model to providehigh accuracy estimation of the optical flow. By its definition, optical flow is a velocityfield, so the velocities in this paper are computed using the widely used DifferentialTechnique. Two methods from this technique are adopted; Horn-Schunck Method andLucas-Kanade Method. The optical flow is estimated for two types of image sequences;synthetic sequences and real sequences. Unlike the real sequences, the syntheticsequences have known true velocities which are used for evaluating the proposed modelby calculating mean error (Mean Err.), angular error (Ang. Err.) and Standard Deviation(STD). For extreme study of its performance, the proposed SLT_OFE is compared withthree other models that are based on level two (Discrete Wavelet Transform (DWT),Discrete Multi Wavelet Transform (DMWT) and Framelet Transform (FT) ) which areimplemented in this paper and employed in the conventional models, 2D-DWT2_OFE,2D-DMWT2_OFE and 2D-FT2_OFE. The results show that the proposed model offersminimum values in errors and STD when 2D-SLT2 is used, and these results areimproved by using 3D-SLT2. This leads to the fact that the proposed model SLT_OFEthrough both of 2D and 3D approaches possesses an improvement in the optical flowestimation process with higher accuracy, than the other models produced in the samecircumstances. MATLAB Version 7.12 (R2011a) is used to implement the proposedmodel and the conventional models.

ER -