Autonomous Space Robotics Lab Speeded Up SURF GpuIntegralImage_kernel.h Go to the documentation of this file. /* Copyright (c) 2010, Paul Furgale and Chi Hay Tong 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. * The names of its contributors may not be used to endorse or promote products derived from this software without specific prior written permission. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "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 HOLDER 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. */ #ifndef ASRL_GPU_INTEGRAL_IMAGE_KERNEL #define ASRL_GPU_INTEGRAL_IMAGE_KERNEL #include <cuda_runtime_api.h> #include <cudpp.h> // Matrix transpose block dimension #define ASRL_TRANSPOSE_BLOCK_DIM 16 namespace asrl { void call_integral_kernel(size_t width, size_t height, unsigned char * char_data, float *norm_data, float *trans_data, cudaArray *output_int_img, size_t norm_pitch, size_t trans_pitch, size_t char_pitch, CUDPPHandle & rowPlan, CUDPPHandle & colPlan, cudaStream_t stream); void run_transpose_kernel_uchar(dim3 grid, dim3 block, float *odata, size_t o_pitch, unsigned char *idata, size_t i_pitch, size_t width, size_t height); void run_transpose_kernel_float(dim3 grid, dim3 block, float *odata, size_t o_pitch, float *idata, size_t i_pitch, size_t width, size_t height); } // namespace asrl #endif // ASRL_GPU_INTEGRAL_IMAGE_KERNEL