Design and Co-Simulation of Depth Estimation Using Simulink HDL Coder and Modelsim

Farida Memon,Fayaz Ahmed Memon,Rafia Naz Memon,Aamir Hussain Memon,Shahnawaz Talpur

doi:10.22581/muet1982.1603.17

Abstract

In this paper a novel VHDL design procedure of depth estimation algorithm using HDL (Hardware Description Language) Coder is presented. A framework is developed that takes depth estimation algorithm described in MATLAB as input and generates VHDL code, which dramatically decreases the time required to implement an application on FPGAs (Field Programmable Gate Arrays). In the first phase, design is carriedout in MATLAB. Using HDL Coder, MATLAB floating- point design is converted to an efficient fixed-point design and generated VHDL Code and test-bench from fixed point MATLAB code. Further, the generated VHDL code of design is verified with co-simulation using Mentor Graphic ModelSim10.3d software. Simulation results are presented which indicate that VHDL simulations match with the MATLAB simulations and confirm the efficiency of presented methodology.

Highlights

Within the broad area of CV (Computer Vision), depth recovery approaches have been extensively developed and gained significant attention over recent decades
Several focus operators are developed in [10,11] using the statistical analysis of image intensities
A model based design using HDL Coder is proposed in order to develop hardware design of depth estimation on a FPGA platform

Summary

Introduction

Within the broad area of CV (Computer Vision), depth recovery approaches have been extensively developed and gained significant attention over recent decades. Hardware implementation provides greater speed than software, but associated time lengthens the development of hardware design. In literature several focus operators are proposed in spatial and frequency domains. Among which many focus operators are based on image derivatives. Tenenbaum [7], has presented a focus operator based on image gradient. Nayar and Nakagawa [5] have developed the focus measure based on SML (Sum-of-Modified-Laplacian) operator. Several focus operators are developed in [10,11] using the statistical analysis of image intensities. Some focus operators are proposed by researchers in the transform domain. To constitute a more refine depth map several reconstruction techniques have been proposed in literature. Some researchers have used reconstruction techniques taking account for continuous nature of the imaged object. The proposed techniques include neural networks [18], and dynamic programming [19], among others [20,21,22]

Methods

Results

Conclusion