API Syntax
template <int SRC_T, int HEIGHT, int WIDTH, int NPC, int XFCVDEPTH_OUT>
void pass_2(uint8_t* fwd_in_ptr,
xf::cv::Mat<SRC_T, HEIGHT, WIDTH, NPC, XFCVDEPTH_OUT>& tmp_out_mat,
uint8_t* out_ptr,
int& def_pix,
int height,
int width)
Parameter Descriptions
The following table describes the template and the function parameters.
Parameter | Description |
---|---|
SRC_T | Input Pixel type. The current supported pixel value is XF_8UC1 |
HEIGHT | Maximum height of the image that hardware kernel must be built for |
WIDTH | Maximum width of the image that hardware kernel must be built for |
NPC | Number of Pixels to be processed per cycle. NPPC1 is supported. |
XFCVDEPTH_OUT | Depth of Mat Image |
fwd_in_ptr | Output Image pointer of fw_cca |
tmp_out_mat | Output Image of rev_cca |
out_ptr | Output Image pointer of pass_2 |
def_pix | number of defect pixels |
height | height of Image pointer |
width | width of Image pointer |
Resource Utilization
The following table summarizes the resource utilization in different configurations, generated using Vitis HLS 2022.2 tool for the xcu200-fsgd2104-2-e, to process a FHD image.
Pipelines | Utilization Estimate | ||||
---|---|---|---|---|---|
BRAM_18K | DSP | FF | LUT | URAM | |
Gaussian_Otsu | 12 | 71 | 11703 | 13633 | 0 |
Preprocess | 7 | 9 | 4123 | 5244 | 0 |
Custom CCA | 10 | 10 | 12642 | 13756 | 0 |
Performance Estimate
The following table summarizes the performance estimates in different configurations, generated using Vitis HLS 2022.2 tool for the xcu200-fsgd2104-2-e, to process a FHD image.
Pipelines | Operating Frequency (MHz) |
Latency Estimate |
---|---|---|
Max (ms) | ||
Gaussian_Otsu | 300 | 7.1 |
Preprocess | 300 | 14.4 |
Custom CCA | 300 | 7 |