Unlock instant, AI-driven research and patent intelligence for your innovation.

A linear feature extraction system based on fpga

A technology for extracting system and straight line features, applied in the field of measurement, can solve problems such as hardware has not been implemented, difficult to embed images and vision systems, and achieve the effects of less time consumption, less memory usage, and high accuracy

Active Publication Date: 2019-11-08
山东正晨科技股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The LSD algorithm is implemented in software by the open source software OPENCV, but it is difficult to directly apply it to embedded image and vision systems
The straight line detection in the present invention is based on the hardware implementation of the LSD algorithm, which has not been implemented on the hardware at present

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A linear feature extraction system based on fpga
  • A linear feature extraction system based on fpga
  • A linear feature extraction system based on fpga

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0132] The present invention selects multiple types of images to test and evaluate the system, and at the same time selects a software system based on the LSD algorithm to extract linear features from the same image to be tested, and compares the extraction results, and from the stability of the system, hardware resources The test results are evaluated in terms of consumption and time consumption. Among them, the parameters of the straight line finally obtained by the system of the present invention are transmitted to the PC through the USB controller of CY7C68013 (with 16 data lines), and the detected straight line is displayed on a blank image with the same size as the input image.

[0133] Image selection: adopt multiple types of noisy images and noise-free images to verify the effectiveness and stability of the system of the present invention, wherein the noise-free images include natural images and hand-drawn linear images (such as Figure 20-Figure 22 ), natural images i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an FPGA-based straight line feature extraction system, which includes a Gaussian filter unit, a gradient modulus and horizontal angle calculation unit, a gradient pseudo-sorting unit, an area growth unit and a rectangle approximation unit. The beneficial effects of the present invention are: the hardware system of the present invention not only ensures a good extraction effect, but also has the advantages of good stability, high accuracy, less time consumption and less memory usage. The present invention adopts a parallel pipeline structure, and straight line feature extraction The speed can meet the requirements of embedded vision measurement system.

Description

technical field [0001] The invention relates to the technical field of measurement, in particular to an FPGA-based linear feature extraction system. Background technique [0002] Since most target objects contain planar features, the straight line can be used as the most important feature to describe the shape of the target object. In addition, in visual measurement, straight line fitting is also an important feature adopted by the vision system, because the straight line is the most important feature in the image. One of the important geometric features. Line detection has been widely used in image recognition and computational vision fields, such as stereo vision, image analysis, intelligent robots, intelligent transportation and pattern recognition. Existing straight line detection algorithms, such as Hough transform, have slow detection speed and high false detection rate. There are other line detection methods, such as some gradient direction-based methods that requir...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T1/20G06T1/60
CPCG06T1/20G06T1/60
Inventor 周富强王新明高鹤王伟
Owner 山东正晨科技股份有限公司