An image sensor may have a certain number of defective/bad pixels that may be the result of manufacturing faults or variations in pixel voltage levels based on temperature or exposure. The Badpixelcorrection module removes the defective pixels in the image using below operation.
If the middle pixel value is lesser than minimum neighborhood value, will consider minimum neighborhood value as mid pixel, otherwise mid pixel value is greater than maximum neighborhood value, will consider maximum neighborhood as mid pixel.
API Syntax
template<int TYPE, int ROWS, int COLS, int NPPC=1, int USE_URAM=0, int XFCVDEPTH_IN_1 = _XFCVDEPTH_DEFAULT, int XFCVDEPTH_OUT_1 = _XFCVDEPTH_DEFAULT, int BORDER_T=XF_BORDER_CONSTANT>
void badpixelcorrection(xf::cv::Mat<TYPE, ROWS, COLS, NPPC, XFCVDEPTH_IN_1> & _src,xf::cv::Mat<TYPE, ROWS, COLS, NPPC, XFCVDEPTH_OUT_1> & _dst)
The following table describes the template and the function parameters.
| Parameter | Description |
|---|---|
| TYPE | Input and Output Pixel Type.XF_8UC1,XF_16UC1 are supported |
| ROWS | Maximum height of input and output image (Must be multiple of NPPC) |
| COLS | Maximum width of input and output image (Must be multiple of NPPC) |
| NPPC | Number of Pixels to be processed per cycle.XF_NPPC1,XF_NPPC2 ,XF_NPPC4 and XF_NPPC8. |
| BORDER_T | Border Type supported is XF_BORDER_CONSTANT |
| USE_URAM | Enable to map storage structures to UltraRAM. |
| XFCVDEPTH_IN_1 | Depth of input image |
| XFCVDEPTH_OUT_1 | Depth of output image |
| _src | Input Bayer image |
| _dst | Output Bayer image |
Resource Utilization
The following table summarizes the resource utilization of the kernel in different configurations, generated using Vivado HLS 2019.2 tool for the Xilinx xc7vx485t-ffg1157-1 FPGA, to process a 4K image.
| Operating Mode | Operating Frequency (MHz) |
Utilization Estimate | ||||
|---|---|---|---|---|---|---|
| BRAM_18K | DSP_48Es | FF | LUT | SLICE | ||
| 1 pixel | 300 | 10 | 0 | 979 | 744 | 355 |
| 2 pixel | 300 | 10 | 0 | 1148 | 1177 | 458 |
Performance Estimate
The following table summarizes a performance estimate of the kernel in different configurations, as generated using Vivado HLS 2019.2 tool for the Xilinx xc7vx485t-ffg1157-1, to process 4K image.
| Operating Mode | Operating Frequency (MHz) |
Latency Estimate |
|---|---|---|
| Max (ms) | ||
| 1 pixel | 300 | 27.8 |
| 2 pixel | 300 | 14.2 |