Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for realizing face detection by FPGA

A face detection and detection unit technology, applied in instrumentation, computing, memory architecture access/allocation, etc., can solve the problems of poor stability, high power consumption of the X86 software platform, and the speed of embedded platform computing cannot keep up with the application, etc. The effect of face detection efficiency

Active Publication Date: 2017-07-07
RECONOVA TECH CO LTD
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional face detection runs on X86 software platform or embedded software platform, but both applications have obvious defects
The X86 software platform has high power consumption and poor stability, and the calculation speed of the embedded platform has obviously failed to keep up with the needs of applications.

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
  • Method for realizing face detection by FPGA
  • Method for realizing face detection by FPGA

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The invention discloses a method for realizing human face detection by FPGA, which realizes human face detection in each frame of image in a video through an image scaling module and a detection module, wherein, the detection module divides the image into blocks and develops a plurality of detection units to process people The task of face detection greatly improves the efficiency of face detection. Concrete detection method of the present invention is as follows:

[0022] Step 1. Call a frame of original image in the video through the image scaling module.

[0023] Video can be regarded as frame-by-frame image data, and face detection in video is also face detection in each frame of image.

[0024] Step 2. Compress the retrieved image level by level according to the threshold ratio, that is, the next level is compressed according to the threshold ratio based on the image compressed by the previous level, and the compressed images of each level are sequentially stored ...

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 relates to a method for realizing face detection by an FPGA. Image zooming, image blocking, face detection, and result wiring back are carried out on each frame of image in a video by an image zooming module and a detection module; and processing is carried out in a assembly line manner. The image zooming module opens up to two buffer regions for storing image zooming results, so that an image blocking unit can invoke images in a buffer unit continuously without any interruption; and the detection module opens up a face detection step and a plurality of detection units to process detection tasks of blocked images. Therefore, the face detection efficiency can be improved and all faces in each frame of image of a video stream can be detected rapidly.

Description

technical field [0001] The invention relates to a method for realizing face detection by FPGA. Background technique [0002] Face detection is a direction in which artificial intelligence is currently widely used, and it has a wide range of applications in many fields such as public security, consumption management, and advertising promotion. [0003] Traditional face detection runs on X86 software platform or embedded software platform, but both applications have obvious defects. The X86 software platform has high power consumption and poor stability, and the calculation speed of the embedded platform has obviously failed to keep up with the application requirements. [0004] As a programmable device, FPGA can allow users to change the hardware circuit inside the chip to achieve high-speed parallel output processing. This feature makes FPGA a good platform for low-power high-speed face detection. Face detection is processed in parallel according to FPGA characteristics. ...

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
IPC IPC(8): G06K9/00G06F12/0875
CPCG06F12/0875G06F2212/401G06F2212/455G06V40/161G06V10/94G06V10/955
Inventor 于淼武国勇黄春晖胡燕彬
Owner RECONOVA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com