Edge Detector

Find edges of objects in grayscale pixel stream

• 

Libraries:
Vision HDL Toolbox / Analysis & Enhancement

Description

The Edge Detector block finds the edges in a grayscale pixel stream by using the Sobel, Prewitt, or Roberts method. The block convolves the input pixels with derivative approximation matrices to find the gradient of pixel magnitude along two orthogonal directions. It then compares the sum of the squares of the gradients to the square of a configurable threshold to determine if the gradients represent an edge.

By default, the block returns a binary image as a stream of pixel values. A pixel value of 1 indicates that the pixel is an edge. You can disable the edge output. You can also enable output of the gradient values in the two orthogonal directions at each pixel.

Examples

Edge Detection and Image Overlay

Detect and highlight object edges in a video stream. The behavior of the pixel-stream Sobel Edge Detector block, video stream alignment, and overlay, is verified by comparing the results with the same algorithm calculated by the full-frame blocks from the Computer Vision Toolbox™.

• Open Model

Filter Multipixel Video Streams

Design filters that operate on a multipixel input video stream. Use multipixel streaming to process high-resolution or high-frame-rate video with the same synthesized clock frequency as a single-pixel streaming interface. Multipixel streaming also improves simulation speed and throughput because fewer iterations are required to process each frame, while maintaining the hardware benefits of a streaming interface.

• Open Model

Ports

This block uses a streaming pixel interface with a bus for frame control signals. This interface enables the block to operate independently of image size and format. The pixel, Edge, and gradient ports on this block support single pixel streaming or multipixel streaming. Single pixel streaming accepts and returns a single pixel value each clock cycle. Multipixel streaming accepts and returns a vector of M pixels per clock cycle to support high-frame-rate or high-resolution formats. The M value corresponds to the Number of pixels parameter of the Frame To Pixels block. Along with the pixel, the block accepts and returns a pixelcontrol bus containing five control signals. The control signals indicate the validity of each pixel and their location in the frame. For multipixel streaming, one set of control signals applies to all pixels in the vector. To convert a frame (pixel matrix) into a serial pixel stream and control signals, use the Frame To Pixels block. For a full description of the interface, see Streaming Pixel Interface.

Input

pixel — Input pixel stream

scalar | vector

This block supports single pixel streaming or multipixel streaming. For single pixel streaming, specify a single input pixel as a scalar intensity value. For multipixel streaming, specify a vector of two, four, or eight pixel intensity values. For details of how to set up your model for multipixel streaming, see Filter Multipixel Video Streams.

This block does not support multicomponent streaming. To process multicomponent streams, replicate the block for each component. The pixelcontrol bus for all components is identical, so you can connect a single bus to multiple replicated blocks.

The software supports double and single data types for simulation, but not for HDL code generation.

Data Types: uint | int | fixed point | double | single

ctrl — Control signals associated with pixel stream

pixelcontrol bus

The pixelcontrol bus contains five signals. The signals describe the validity of the pixel and its location in the frame. For more information, see Pixel Control Bus.

For multipixel streaming, each vector of pixel values has one set of control signals. Because the vector has only one valid signal, the pixels in the vector must be either all valid or all invalid. The hStart and vStart signals apply to the pixel with the lowest index in the vector. The hEnd and vEnd signals apply to the pixel with the highest index in the vector.

Data Types: bus

Th — Threshold value

scalar

Threshold value that defines an edge, specified as a scalar. The block compares the square of this value to the sum of the squares of the gradients.

The software supports double and single data types for simulation, but not for HDL code generation.

Data Types: single | double | int | uint | fixed point

Output

Edge — Boolean pixel value, indicating whether pixel is an edge

scalar | vector

For single pixel streaming, Edge is a Boolean scalar. For multipixel streaming, Edge is a vector of M-by-1 Boolean values. Each pixel value indicates whether the pixel is an edge.

Data Types: Boolean

Gv,Gh — Vertical and horizontal gradient

scalar | vector

Vertical and horizontal gradient values calculated over the kernel centered at a pixel location.

For single pixel streaming, the block returns Gv and Gh as scalar values. For multipixel streaming, the block returns Gv and Gh as vectors of M-by-1 values.

The software supports double and single data types for simulation, but not for HDL code generation.

Dependencies

To enable these ports, set Method to Sobel or Prewitt.

Data Types: single | double | int | uint | fixed point

G45,G135 — Orthogonal gradient

scalar | vector

Orthogonal gradient values calculated over the kernel centered at a pixel location.

For single pixel streaming, the block returns G45 and G135 as scalar values. For multipixel streaming, the block returns G45 and G135 as vectors of M-by-1 values.

The software supports double and single data types for simulation, but not for HDL code generation.

Dependencies

To enable these ports set Method to Roberts.

Data Types: single | double | int | uint | fixed point

ctrl — Control signals associated with pixel stream

pixelcontrol bus

The pixelcontrol bus contains five signals. The signals describe the validity of the pixel and its location in the frame. For more information, see Pixel Control Bus.

For multipixel streaming, each vector of pixel values has one set of control signals. Because the vector has only one valid signal, the pixels in the vector must be either all valid or all invalid. The hStart and vStart signals apply to the pixel with the lowest index in the vector. The hEnd and vEnd signals apply to the pixel with the highest index in the vector.

Data Types: bus

Parameters

Main

Method — Edge detection algorithm

Sobel (default) | Prewitt | Roberts

When you select Sobel or Prewitt, the block calculates horizontal and vertical gradients, Gv and Gh. When you select Roberts, the block calculates orthogonal gradients, G45 and G135. For details of each method, see Algorithms.

Note

If you select Prewitt, the full-precision internal data type is large due to the 1/6 coefficient. Consider selecting Output the gradient components, so that you can customize the data type to a smaller size.

Output the binary image — Enable edge output port

on (default) | off

When this parameter is selected, the block returns a stream of binary pixels representing the edges detected in the input frame.

You must select at least one of Output the binary image and Output the gradient components.

Output the gradient components — Enable gradient output ports

off (default) | on

When this parameter is selected, the block returns a stream of values representing the gradients calculated in the two orthogonal directions at each pixel. When you set Method to Sobel or Prewitt, the output ports Gv and Gh appear on the block. When you set Method to Roberts, the output ports G45 and G135 appear on the block.

You must select at least one of Output the binary image and Output the gradient components.

Source of threshold value — Source for gradient threshold that indicates an edge

Property (default) | Input port

You can set the threshold from an input port or from the dialog box. The default value is Property. Selecting Input port enables the Th port.

Threshold value — Gradient threshold value that indicates an edge

20 (default) | scalar

The block compares the square of this value to the sum of the squares of the gradients. The block casts this value to the data type of the gradients.

Dependencies

This option is visible when you set Source of threshold value to Property.

Line buffer size — Size of the line memory buffer

2048 (default) | integer

Size of the line memory buffer, specified as a positive integer. Choose a power of two that accommodates the number of active pixels in a horizontal line. If you specify a value that is not a power of two, the buffer uses the next largest power of two.

When you use multipixel input, this value must accommodate (Active pixels per line)/(Number of pixels) + 2.

The block allocates (N – 1)-by-Line buffer size memory locations to store the pixels, where N is the number of lines in the differential approximation matrix. If you set Method to Sobel or Prewitt, then N is 3. If you set Method to Roberts, then N is 2.

Padding method — Method for padding

Symmetric (default) | None

Select one of these methods for padding the boundary of the input image. For more information about these methods, see Edge Padding.

• Symmetric — Set the value of the padding pixels to mirror the edge of the image. This option prevents edges from being detected at the boundaries of the active frame.

• None — Exclude padding logic. The block does not set the pixels outside the image frame to any particular value. This option reduces the hardware resources used by the block and the blanking required between frames but affects the accuracy of the output pixels at the edges of the frame. To maintain pixel stream timing, the output frame is the same size as the input frame. However, to avoid using pixels calculated from undefined padding values, mask off the KernelSize/2 pixels around the edge of the frame for downstream operations. For details, see Increase Throughput by Omitting Padding.

Data Types

Rounding mode — Rounding method for internal fixed-point calculations

Floor (default) | Ceiling | Convergent | Nearest | Round | Zero

Specify a rounding method for internal fixed-point calculations.

Saturate on integer overflow — Overflow action for internal fixed-point calculations

off (default) | on

When you clear this parameter, fixed-point and integer values wrap around to zero when the value overflows what is representable with that data type. When you select this parameter, the value saturates at the maximum representable value.

Gradient Data Type — Data type for gradient output ports

Inherit via internal rule (default) | data type expression

Data type for the two gradient output ports. By default, the block automatically chooses full-precision data types.

Dependencies

To enable this parameter, on the Main tab, select Output the gradient components.

Tips

• When you use a block with an internal line buffer inside an Enabled Subsystem (Simulink), the enable signal pattern must maintain the timing of the pixel stream, including the minimum blanking intervals. If the enable pattern corrupts the timing of the pixel stream, you might see partial output frames, corrupted pixel stream control signals, or mismatches between Simulink^® and HDL simulation results. You may need to extend the blanking intervals to accommodate for cycles when the enable is low. For more information, see Configure Blanking Intervals.

Algorithms

The Edge Detector block provides three methods for detecting edges in an input image. The methods use different derivative approximation matrices to find two orthogonal gradients. The Sobel and Prewitt methods calculate the gradient in horizontal and vertical directions. The Roberts method calculates the gradients at 45 degrees and 135 degrees. The block uses the same matrices as the Edge Detection block in Computer Vision Toolbox™.

When you use multipixel streaming, the block uses a single line memory and implements one filter for each of the M input pixels, in parallel. This increase in hardware resources is a trade off for increasing throughput compared to single-pixel streaming.

Method	Direction 1	Direction 2
Sobel	$$\frac{1}{8}\left[\begin{array}{ccc}1& 0& -1\\ 2& 0& -2\\ 1& 0& -1\end{array}\right]$$	$$\frac{1}{8}\left[\begin{array}{ccc}1& 2& 1\\ 0& 0& 0\\ -1& -2& -1\end{array}\right]$$
Prewitt	$$\frac{1}{6}\left[\begin{array}{ccc}1& 0& -1\\ 1& 0& -1\\ 1& 0& -1\end{array}\right]$$	$$\frac{1}{6}\left[\begin{array}{ccc}1& 1& 1\\ 0& 0& 0\\ -1& -1& -1\end{array}\right]$$
Roberts	$$\frac{1}{2}\left[\begin{array}{cc}1& 0\\ 0& -1\end{array}\right]$$	$$\frac{1}{2}\left[\begin{array}{cc}0& 1\\ -1& 0\end{array}\right]$$

Note

The Prewitt coefficients require extra bits of precision because they are not powers of two. The block uses 16 bits to represent the Prewitt coefficients. For 8-bit input, the default size of the full-precision gradients is 27 bits. When using the Prewitt method, a good practice is to reduce the word length used for the gradient calculation. Select the Output the gradient components check box, and then on the Data Types tab, specify a smaller word length using Gradient Data Type.

The block convolves the neighborhood of the input pixel with the derivative matrices, D1 and D2. It then compares the sum of the squares of the gradients to the square of the threshold. Computing the square of the threshold avoids constructing a square root circuit. The block casts the gradients to the type you specified on the Data Types tab. The type conversion on the square of the threshold matches the type of the sum of the squares of the gradients.

Latency

The latency of the block is the line buffer latency plus the latency of the kernel calculation. The line buffer latency includes edge padding by default. The latency of the padding operation depends on the size of the kernel. If edge padding is not necessary for your design, you can reduce the latency by setting the Padding method parameter to None. When you use this option, the block latency does not depend on your kernel size. To determine the exact latency for any configuration of the block, measure the number of time steps between the input and output control signals.

Note

When you use edge padding, use a horizontal blanking interval of at least twice the kernel width. This interval lets the block finish processing one line before it starts processing the next one, including adding padding pixels before and after the active pixels in the line.

The horizontal blanking interval is equal to TotalPixelsPerLine – ActivePixelsPerLine or, equivalently, FrontPorch + BackPorch. Standard streaming video formats use a horizontal blanking interval of about 25% of the frame width. This interval is much larger than the filters applied to each frame.

The horizontal blanking interval must also meet these minimums:

• If the kernel size is less than 4, and you use edge padding, the total porch must be at least 8 pixels.

• When you disable edge padding, the horizontal blanking interval must be at least 12 cycles and is independent of the kernel size.

• The BackPorch must be at least 6 pixels. This parameter is the number of inactive pixels before the first valid pixel in a frame.

For more information, see Configure Blanking Intervals.

Performance

This table shows the resource use after synthesis of the block for the Xilinx^® Zynq^®-7000 SoC ZC706 Evaluation Kit with single-pixel uint8 input and the default parameter settings. The design achieves a clock frequency of 323 MHz.

Resource	Usage
Slice LUTs	453
Slice Registers	1043
DSP48	2
Block RAM	1

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using Simulink® Coder™.

This block supports C/C++ code generation for Simulink accelerator and rapid accelerator modes and for DPI component generation.

HDL Code Generation

Generate VHDL, Verilog and SystemVerilog code for FPGA and ASIC designs using HDL Coder™.

HDL Coder™ provides additional configuration options that affect HDL implementation and synthesized logic.

HDL Architecture

This block has one default HDL architecture.

HDL Block Properties

ConstrainedOutputPipeline	Number of registers to place at the outputs by moving existing delays within your design. Distributed pipelining does not redistribute these registers. The default is 0. For more details, see ConstrainedOutputPipeline (HDL Coder).
InputPipeline	Number of input pipeline stages to insert in the generated code. Distributed pipelining and constrained output pipelining can move these registers. The default is 0. For more details, see InputPipeline (HDL Coder).
OutputPipeline	Number of output pipeline stages to insert in the generated code. Distributed pipelining and constrained output pipelining can move these registers. The default is 0. For more details, see OutputPipeline (HDL Coder).

Restrictions

You cannot generate HDL for this block inside a Resettable Synchronous Subsystem (HDL Coder).

Version History

Introduced in R2015a

R2023a: Two pixels-per-clock streaming

The block now supports multipixel streams that have 2 pixels per clock cycle.

R2020a: Option to omit padding

You can now configure the block to not add padding around the boundaries of the active frame. This option reduces the hardware resources used by the block and the blanking required between frames but affects the accuracy of the output pixels at the edges of the frame. To use this option, set the Padding method parameter to None. For an example, see Increase Throughput by Omitting Padding.

R2019b: Multipixel streaming

The Edge Detector block now supports multipixel streams. The HDL implementation replicates the algorithm for each pixel in parallel.

For multipixel streaming, the block supports input and output column vectors of 4 or 8 pixels. The ctrl port remains scalar, and the control signals in the pixelcontrol bus apply to all pixels in the vector.

R2018b: Improved line buffer

The internal line buffer in this block now handles bursty data, that is, noncontiguous valid signals within a pixel line. This implementation uses fewer hardware resources due to improved padding logic and native support for kernel sizes with an even number of lines. This change affects the Line Buffer block and blocks that use an internal line buffer.

The latency of the line buffer is now reduced by a few cycles for some configurations. You might need to rebalance parallel path delays in your model. A best practice is to synchronize parallel paths in your model by using the pixel stream control signals rather than by inserting a specific number of delays.