Channel Combine - 2023.2 English

Vitis Libraries

Release Date
2023-12-20
Version
2023.2 English

The merge function, merges single channel images into a multi-channel image. The number of channels to be merged should be two, three or four.

API Syntax

template<int SRC_T, int DST_T, int ROWS, int COLS, int NPC=1, int XFCVDEPTH_IN_1 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_IN_2 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_IN_3 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_IN_4 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_OUT_1 = _XFCVDEPTH_DEFAULT>
void merge(xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_1> &_src1, xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_2> &_src2, xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_3> &_src3, xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_4> &_src4, xf::cv::Mat<DST_T, ROWS, COLS, NPC, XFCVDEPTH_OUT_1> &_dst)

template<int SRC_T, int DST_T, int ROWS, int COLS, int NPC=1, int XFCVDEPTH_IN_1 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_IN_2 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_IN_3 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_OUT_1 = _XFCVDEPTH_DEFAULT>
void merge(xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_1> &_src1, xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_2> &_src2, xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_3> &_src3, xf::cv::Mat<DST_T, ROWS, COLS, NPC, XFCVDEPTH_OUT_1> &_dst)

template<int SRC_T, int DST_T, int ROWS, int COLS, int NPC=1, int XFCVDEPTH_IN_1 = _XFCVDEPTH_DEFAULT,int XFCVDEPTH_IN_2 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_OUT_1 = _XFCVDEPTH_DEFAULT>
void merge(xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_1> &_src1, xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN_2> &_src2, xf::cv::Mat<DST_T, ROWS, COLS, NPC, XFCVDEPTH_OUT_1> &_dst)

Parameter Descriptions

The following table describes the template and the function parameters.

Table 339 Table 69. merge Parameter Description
Paramete r Description
SRC_T Input pixel type. Only 8-bit, unsigned, 1, channel is supported (XF_8UC1)
DST_T Output pixel type. 8-bit, unsigned,2,3 and 4 channels are supported (XF_8UC2, XF_8UC3 and XF_8UC4)
ROWS Maximum height of input and output image.
COLS Maximum width of input and output image. Must be multiple of 8 for 8 pixel mode.
NPC Number of pixels to be processed per cycle; possible options are XF_NPPC1,XF_NPPC2,XF_NPPC4 and XF_NPPC8 for 1,2,4 pixel and 8 pixel operations respectively.
XFCVDEPTH_IN_1 Depth of input image
XFCVDEPTH_IN_2 Depth of input image
XFCVDEPTH_IN_3 Depth of input image
XFCVDEPTH_IN_4 Depth of input image
XFCVDEPTH_OUT_1 Depth of output image
_src1 Input single-channel image
_src2 Input single-channel image
_src3 Input single-channel image (only for 3 and 4 input config)
_src4 Input single-channel image (only for 4 input config)
_dst Output multi-channel image

Resource Utilization

The following table summarizes the resource utilization of the merge function, generated using Vivado HLS 2019.1 tool for the Xczu9eg-ffvb1156-1-i-es1 FPGA, to process 4 single-channel HD (1080x1920) images.

Table 340 Table 70. merge Function Resource Utilization Summary
Operating Mode Operating Frequency (MHz) Utilization Estimate
BRAM_18K DSP_48Es FF LUT CLB
1 Pixel 300 0 8 494 386 85

Performance Estimate

The following table summarizes the performance in different configurations, as generated using Vivado HLS 2019.1 tool for the Xczu9eg-ffvb1156-1-i-es1, to process 4 single channel HD (1080x1920) images.

Table 341 Table 71. merge Function Performance Estimate Summary
Operating Mode Latency Estimate
Max Latency (ms)
1 pixel operation (300 MHz) 6.92