Benchmark: Image Processing Operations on Arm Cortex-A9 in Xilinx Zynq 7000 SoC

This repository contains an implementation of basic image processing operations that are widely used in data intensive video classification and video analytics applications. The code is written in C language and implemented on Xilinx Zynq 7000 SoC. This SoC consists of dual Arm Cortex-A9 CPUs tightly coupled with the Xilinx FPGA programmable logic.

The following is a list of point and area image processing operations considered in this work and benchmarked on Avnet Zedboard Development Kit (Xilinx Zynq 7000 SoC).

List of Image Processing Operations

Point Operations

1. Contrast
2. Threshold
3. Gradient

Area Operations

1. Gaussian Filter
2. Sobel Filters
3. Morphology Filters (Erosion, Dilation)

Usage

Run the ../Benchmarks/TimeMeasurement.c

Important References

[1] F. Siddiqui, S. Amiri, U. Minhas, "FPGA-Based Processor Acceleration for Image Processing Applications" in Journal of Imaging 2019, 5, 16.

[2] F. Siddiqui, M. Russell, B. Bardak, R. Woods and K. Rafferty, "IPPro: FPGA based image processing processor" in IEEE Workshop on Signal Processing Systems (SiPS), Belfast, UK, 2014, pp. 1-6.

[3] M. Amiri, F. Siddiqui, C. Kelly, et al. "FPGA-Based Soft-Core Processors for Image Processing Applications" in Journal of Signal Processing Systems, 87, 139–156 (2017).

[4] C. Kelly, F. M. Siddiqui, B. Bardak and R. Woods, "Histogram of oriented gradients front end processing: An FPGA based processor approach" in IEEE Workshop on Signal Processing Systems (SiPS), Belfast, UK, 2014, pp. 1-6.

[5] F. Siddiqui, "FPGA-based Programmable Embedded Platform for Image Processing Applications", 11 Sep 2018. (PhD Thesis)