Box Image Filter

Overview

Box Image Filter is a low-pass filter that smooths the image by making each output pixel the average of the surrounding ones, removing details, noise and and edges from images.

Input	Window size	Output
	5x5

Implementation

Box image filter is implemented as a convolution operation on the input image using the following kernel:

\[ box_{m,n} = \frac{1}{mn} \begin{bmatrix} 1 & 1 & \dots & 1 \\ 1 & 1 & \dots & 1 \\ \vdots & \vdots & \ddots & \vdots \\ 1 & 1 & \dots & 1 \end{bmatrix}_{m \times n} \]

Usage

1. Initialization phase
   1. Include the header that defines the box filter function.

      #include <vpi/algo/BoxImageFilter.h>

   2. Define the stream on which the algorithm will be executed, the input and output images.

          VPIStream stream = /*...*/;
          VPIImage input   = /*...*/;

   3. Create the output image.

          uint32_t w, h;
          vpiImageGetSize(input, &w, &h);
       
          VPIImageType type;
          vpiImageGetType(input, &type);
       
          VPIImage output;
          vpiImageCreate(w, h, type, 0, &output);

2. Processing phase
   1. Submit the algorithm to the stream, input, output images, window size and boundary condition.

          vpiSubmitBoxImageFilter(stream, input, output, 5, 5, VPI_BOUNDARY_COND_ZERO);

   2. Optionally, wait until the processing is done.

          vpiStreamSync(stream);

For more details, consult the API reference.

Limitations and Constraints

Constraints for specific backends supersede the ones specified for all backends.

All Backends

• Kernel size must be at least 1x1 and at most 11x11.
• Accepted boundary conditions:
  • VPI_BOUNDARY_COND_CLAMP
  • VPI_BOUNDARY_COND_ZERO
• Input and output images must have same image type and size.
• Accepted input image type:
  • VPI_IMAGE_TYPE_U8
  • VPI_IMAGE_TYPE_S8
  • VPI_IMAGE_TYPE_U16
  • VPI_IMAGE_TYPE_S16

PVA

• Minimum kernel size is 2x2.
• Accepted boundary conditions:
  • VPI_BOUNDARY_COND_ZERO
  • VPI_BOUNDARY_COND_CLAMP only if kernel size is 3x3.

Performance

For further information on how performance was benchmarked, see Performance Measurement.

Jetson AGX Xavier

size	type	kernel	boundary	CPU	CUDA	PVA
1920x1080	u8	3x3	zero	0.35 ms	0.06516 ms	1.004 ms
1920x1080	u8	3x3	clamp	0.354 ms	0.0640 ms	1.135 ms
1920x1080	u8	5x5	zero	0.44 ms	0.0686 ms	1.310 ms
1920x1080	u8	7x7	zero	0.99 ms	0.0876 ms	1.930 ms
1920x1080	u8	11x11	zero	1.29 ms	0.0987 ms	3.440 ms
1920x1080	u16	3x3	zero	0.43 ms	0.10668 ms	1.108 ms
1920x1080	u16	3x3	clamp	0.42 ms	0.1066 ms	1.098 ms
1920x1080	u16	5x5	zero	0.58 ms	0.1146 ms	1.598 ms
1920x1080	u16	7x7	zero	1.110 ms	0.13415 ms	2.52 ms
1920x1080	u16	11x11	zero	1.289 ms	0.1575 ms	4.833 ms

Jetson TX2

size	type	kernel	boundary	CPU	CUDA	PVA
1920x1080	u8	3x3	zero	1.48 ms	0.260 ms	n/a
1920x1080	u8	3x3	clamp	1.45 ms	0.257 ms	n/a
1920x1080	u8	5x5	zero	1.8 ms	0.292 ms	n/a
1920x1080	u8	7x7	zero	2.25 ms	0.396 ms	n/a
1920x1080	u8	11x11	zero	3.03 ms	0.474 ms	n/a
1920x1080	u16	3x3	zero	1.80 ms	0.387 ms	n/a
1920x1080	u16	3x3	clamp	1.80 ms	0.385 ms	n/a
1920x1080	u16	5x5	zero	2.14 ms	0.420 ms	n/a
1920x1080	u16	7x7	zero	2.70 ms	0.586 ms	n/a
1920x1080	u16	11x11	zero	3.43 ms	0.680 ms	n/a

Jetson Nano

size	type	kernel	boundary	CPU	CUDA	PVA
1920x1080	u8	3x3	zero	3.047 ms	0.673 ms	n/a
1920x1080	u8	3x3	clamp	3.10 ms	0.664 ms	n/a
1920x1080	u8	5x5	zero	3.80 ms	0.746 ms	n/a
1920x1080	u8	7x7	zero	4.699 ms	1.027 ms	n/a
1920x1080	u8	11x11	zero	6.91 ms	1.2364 ms	n/a
1920x1080	u16	3x3	zero	3.588 ms	0.969 ms	n/a
1920x1080	u16	3x3	clamp	3.56 ms	0.978 ms	n/a
1920x1080	u16	5x5	zero	4.21 ms	1.018 ms	n/a
1920x1080	u16	7x7	zero	5.44 ms	1.393 ms	n/a
1920x1080	u16	11x11	zero	7.33 ms	1.662 ms	n/a