The boundingbox function highlights the region of interest (ROI)
from the input image using below equations.
P(X,Y) ≤ P(xi, yi) ≤ P(X,Y’)
P(X’,Y) ≤ P(xi, yi) ≤ P(X’,Y’)
Where,
- P(xi, yi) - Current pixel location
- P(X,Y) - Top left corner of ROI
- P(X,Y’) - Top right corner of ROI
- P(X’,Y) - Bottom left corner of ROI
- P(X’,Y’) - Bottom Right of ROI
API Syntax
template<int SRC_T, int ROWS, int COLS, int MAX_BOXES=1, int NPC=1, int XFCVDEPTH_IN = _XFCVDEPTH_DEFAULT>
void boundingbox(xf::cv::Mat<SRC_T, ROWS, COLS, NPC, XFCVDEPTH_IN> & _src_mat, xf::cv::Rect_<int> *roi , xf::cv::Scalar<4,unsigned char > *color, int num_box)
Parameter Descriptions
The following table describes the template and the function parameters.
| Parameter | Description |
|---|---|
| SRC_T | Input pixel Type. Only 8-bit, unsigned, 1 channel and 4 channel is supported (XF_8UC1,XF_8UC4). |
| ROWS | Maximum height of input and output image. |
| COLS | Maximum width of input and output image. Must be multiple of NPC. |
| MAX_BOXES | Maximum number of boxes, fixed to 5. |
| NPC | Number of pixels to be processed per cycle, possible options are XF_NPPC1 only. |
| XFCVDEPTH_IN | Depth of input image |
| _src_mat | Input image |
| roi | ROI is a xf::cv::Rect object that consists of
the top left corner of the rectangle along with
the height and width of the rectangle. |
| color | The xf::cv::Scalar object consists of color
information for each box (ROI). |
| num_box | Number of boxes to be detected. It should be equal or less than MAX_BOXES. |
Resource Utilization
The following table summarizes the resource utilization in different configurations, generated using Vivado HLS 2019.1 tool for the Xczu9eg-ffvb1156-1-i-es1 FPGA.
| Operating Mode | Operating Frequency (MHz) | Utilization Estimate | ||||
|---|---|---|---|---|---|---|
| BRAM_18K | DSP_48Es | FF | LUT | CLB | ||
| 1 Pixel | 300 | 5 | 4 | 2521 | 1649 | 409 |
Performance Estimate
The following table summarizes the performance of the kernel in 1-pixel mode as generated using Vivado HLS 2019.1 tool for the Xilinx xczu9eg-ffvb1156-2-i-es2 FPGA to process a grayscale 4K (2160x3840) image for highlighting 3 different boundaries (480x640, 100x200, 300x300).
| Operating Mode | Latency Estimate |
|---|---|
| Max Latency (ms) | |
| 1 pixel operation (300 MHz) | 0.15 |
Vitis Vision Reference
The xf::cv::boundingbox is complaint with below Vitis Vision function:
void rectangle(Mat& img, Rect rec, const Scalar& color, int thickness=1, int lineType=8, int shift=0 )