2D Image Convolution

Overview

The 2D Image Convolution application outputs an image with the edges of the input image, saving the result into edges.png. The user can define what backend will be used for processing.

Note

The output will be in grayscale as convolution is currently only supported for single-channel images.

This sample shows the following VPI features:

• Creating and destroying a VPI device.
• Wrapping an image hosted on CPU (the input) to be used by VPI.
• Creating a VPI-managed 2D image where output will be written to.
• Create a Convolve2D algorithm and call it, passing a custom kernel.
• Simple device synchronization.
• Image locking to access its contents from CPU side.
• Error handling.
• Environment clean up.

Instructions

The usage is:

./vpi_sample_01_convolve_2d <backend> <input image>

where

• backend: either cpu, cuda or pva; it defines the backend that will perform the processing.
• input image: input image file name; it accepts png, jpeg and possibly others.

Here's one example:

./vpi_sample_01_convolve_2d cpu ../assets/kodim8.png

This is using the CUDA backend and one of the provided sample images. You can try with other images, respecting the constraints imposed by the algorithm.

Source code

For convenience, here's the code that is also installed in the samples directory.

/*
* Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*  * Redistributions of source code must retain the above copyright
*    notice, this list of conditions and the following disclaimer.
*  * Redistributions in binary form must reproduce the above copyright
*    notice, this list of conditions and the following disclaimer in the
*    documentation and/or other materials provided with the distribution.
*  * Neither the name of NVIDIA CORPORATION nor the names of its
*    contributors may be used to endorse or promote products derived
*    from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
 
#include <opencv2/core/version.hpp>
#if CV_MAJOR_VERSION >= 3
#    include <opencv2/imgcodecs.hpp>
#else
#    include <opencv2/highgui/highgui.hpp>
#endif
 
#include <vpi/Image.h>
#include <vpi/Stream.h>
#include <vpi/algo/ImageConvolver.h>
 
#include <cstring> // for memset
#include <iostream>
 
#define CHECK_STATUS(STMT)                                      \
    do                                                          \
    {                                                           \
        VPIStatus status = (STMT);                              \
        if (status != VPI_SUCCESS)                              \
        {                                                       \
            throw std::runtime_error(vpiStatusGetName(status)); \
        }                                                       \
    } while (0);
 
int main(int argc, char *argv[])
{
    VPIImage image    = NULL;
    VPIImage gradient = NULL;
    VPIStream stream  = NULL;
 
    int retval = 0;
 
    try
    {
        if (argc != 3)
        {
            throw std::runtime_error(std::string("Usage: ") + argv[0] + " <cpu|pva|cuda> <input image>");
        }
 
        std::string strDevType       = argv[1];
        std::string strInputFileName = argv[2];
 
        // Load the input image
        cv::Mat cvImage = cv::imread(strInputFileName, cv::IMREAD_GRAYSCALE);
        if (cvImage.empty())
        {
            throw std::runtime_error("Can't open '" + strInputFileName + "'");
        }
 
        assert(cvImage.type() == CV_8UC1);
 
        // Now process the device type
        VPIDeviceType devType;
 
        if (strDevType == "cpu")
        {
            devType = VPI_DEVICE_TYPE_CPU;
        }
        else if (strDevType == "cuda")
        {
            devType = VPI_DEVICE_TYPE_CUDA;
        }
        else if (strDevType == "pva")
        {
            devType = VPI_DEVICE_TYPE_PVA;
        }
        else
        {
            throw std::runtime_error("Backend '" + strDevType +
                                     "' not recognized, it must be either cpu, cuda or pva.");
        }
 
        // Create the stream for the given backend.
        CHECK_STATUS(vpiStreamCreate(devType, &stream));
 
        // We now wrap the loaded image into a VPIImage object to be used by VPI.
        {
            // First fill VPIImageData with the, well, image data...
            VPIImageData imgData;
            memset(&imgData, 0, sizeof(imgData));
            imgData.type                = VPI_IMAGE_TYPE_U8;
            imgData.numPlanes           = 1;
            imgData.planes[0].width     = cvImage.cols;
            imgData.planes[0].height    = cvImage.rows;
            imgData.planes[0].rowStride = cvImage.step[0];
            imgData.planes[0].data      = cvImage.data;
 
            // Wrap it into a VPIImage. VPI won't make a copy of it, so the original
            // image must be in scope at all times.
            CHECK_STATUS(vpiImageWrapHostMem(&imgData, 0, &image));
        }
 
        // Now create the output image, single unsigned 8-bit channel.
        CHECK_STATUS(vpiImageCreate(cvImage.cols, cvImage.rows, VPI_IMAGE_TYPE_U8, 0, &gradient));
 
        // Define the convolution filter, a simple edge detector.
        float kernel[3 * 3] = {1, 0, -1, 0, 0, 0, -1, 0, 1};
 
        // Deal with PVA restriction where abs(weight) < 1.
        for (int i = 0; i < 9; ++i)
        {
            kernel[i] /= 1 + FLT_EPSILON;
        }
 
        // Submit it for processing passing the input image the result image that will store the gradient.
        CHECK_STATUS(vpiSubmitImageConvolver(stream, image, gradient, kernel, 3, 3, VPI_BOUNDARY_COND_ZERO));
 
        // Wait until the algorithm finishes processing
        CHECK_STATUS(vpiStreamSync(stream));
 
        // Now let's retrieve the output image contents and output it to disk
        {
            // Lock output image to retrieve its data on cpu memory
            VPIImageData outData;
            CHECK_STATUS(vpiImageLock(gradient, VPI_LOCK_READ, &outData));
 
            cv::Mat cvOut(outData.planes[0].height, outData.planes[0].width, CV_8UC1, outData.planes[0].data,
                          outData.planes[0].rowStride);
            imwrite("edges_" + strDevType + ".png", cvOut);
 
            // Done handling output image, don't forget to unlock it.
            CHECK_STATUS(vpiImageUnlock(gradient));
        }
    }
    catch (std::exception &e)
    {
        std::cerr << e.what() << std::endl;
        retval = 1;
    }
 
    // Clean up
    vpiImageDestroy(image);
    vpiImageDestroy(gradient);
    vpiStreamDestroy(stream);
 
    return retval;
}

Results

Input image	Output image, edges

Known Issues

• This sample doesn't work currently for PVA backend due to a bug in the Image Convolution code implementation.