Canny Edge Detection¶

Canny example resides in L2/examples/canny directory.

This benchmark tests the performance of canny function. The Canny edge detector finds the edges in an image or video frame. It is one of the most popular algorithms for edge detection.

The tutorial provides a step-by-step guide that covers commands for building and running kernel.

Executable Usage¶

Work Directory(Step 1)

The steps for library download and environment setup can be found in README file of L2 folder. For getting the design,

cd L2/example/canny

Build kernel(Step 2)

Run the following make command to build your XCLBIN and host binary targeting a specific device. Please be noticed that this process will take a long time, maybe couple of hours.

export OPENCV_INCLUDE=< path-to-opencv-include-folder >
export OPENCV_LIB=< path-to-opencv-lib-folder >
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:< path-to-opencv-lib-folder >
export DEVICE=< path-to-platform-directory >/< platform >.xpfm
make host xclbin TARGET=hw

Run kernel(Step 3)

To get the benchmark results, please run the following command.

make run TARGET=hw

Example output(Step 4)

-----------Canny Design---------------
Found Platform
Platform Name: Xilinx
XCLBIN File Name: krnl_canny
INFO: Importing Vitis_Libraries/vision/L2/examples/canny/Xilinx_Canny_L2_Test_vitis_hw_u200/build_dir.hw.xilinx_u200_xdma_201830_2/krnl_canny.xclbin
Loading: 'Vitis_Libraries/vision/L2/examples/canny/Xilinx_Canny_L2_Test_vitis_hw_u200/build_dir.hw.xilinx_u200_xdma_201830_2/krnl_canny.xclbin'
before kernelafter kernel
before kernelafter kernel
actual number of cols is 3840
Total Execution time 10.5ms
------------------------------------------------------------

Profiling¶

The canny design is validated on Alveo U200 board at 300 MHz frequency. The hardware resource utilizations are listed in the following table.

Table 1 Hardware resources for Canny edge detection¶
Dataset			LUT	BRAM	FF	DSP
Resolution	NPPC	other params	LUT	BRAM	FF	DSP
4K	8	L1 Norm, Filter - 3x3	31408	132	19148	96
FHD	8	L1 Norm, Filter - 3x3	17451	65	11256	63

The performance is shown below

Table 2 Performance numbers in terms of FPS (Frames Per Second) for Canny edge detection¶
Dataset	FPS(CPU)	FPS(FPGA)
4k (3840x2160)	9	95
Full HD(1920x1080)	25	333