Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A platform for verifying the accuracy of infrared video image processing algorithms

A technology for processing algorithms and video images, applied in image communication, electrical digital data processing, television, etc., can solve problems such as low efficiency, long hardware debugging cycle, and loss of life

Active Publication Date: 2020-09-18
NANJING UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantages of this method are obvious: First, the subjective evaluation is inaccurate, the video images are diverse and complex, and it is difficult to find the gap between hardware algorithm processing and software simulation by directly observing the images purely with the naked eye
Secondly, the output of the infrared detector is unpredictable, and the images collected each time are different, so it is impossible to really compare the effect of hardware algorithm processing
In addition, this judgment method is inefficient, the hardware debugging cycle is long, the detector is turned on repeatedly, and the service life is lost

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 platform for verifying the accuracy of infrared video image processing algorithms
  • A platform for verifying the accuracy of infrared video image processing algorithms
  • A platform for verifying the accuracy of infrared video image processing algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] combine Figure 1 to Figure 5 , a platform for verifying the accuracy of infrared video image processing algorithms, including a cross video encoding module 3 , a decoder 5 , a video transmitter 7 and a video receiving comparison module 10 . The cross video encoding module 3 runs on the internal controller of the infrared detector 1 to obtain the original infrared video stream and the infrared video stream processed by the detector hardware. Since the 4-bit width of the parallel output interface is limited, it uses cross encoding to combine the two A video stream is compressed into a video stream, which is output from the parallel output interface 4 to the cross video decoder 5. The cross video decoder 5 decodes the cross video stream to obtain the original infrared video stream and the video stream processed by the hardware algorithm, which are respectively transmitted to the video transmitter 7 through hardware circuits, such as the GPIO interface 6 . The video trans...

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 a platform for verifying infrared video image processing algorithm realization accuracy. The original video image of an infrared detector and the image processed by the hardware can be transmitted to a video receiving and comparing module, the video receiving and comparing module is used for carrying out software simulation processing on the original video image, and then the image subjected to hardware processing and the image subjected to software simulation are compared frame by frame and pixel by pixel, and whether the two images are consistent or not is determined,so that the accuracy of the hardware processing algorithm can be determined. According to the invention, the synchronous output of the original infrared video stream and the infrared video stream after the hardware processing is realized, the video stream is transmitted to the video receiving and comparing module through the Gigabit Ethernet, and the video receiving and comparing module uses a digitalized means, the video image subjected to software simulation and the video image processed by the infrared detector are compared, the difference of the software and hardware processing results isfound, and compared with a traditional manual comparison mode, the platform is more efficient and accurate.

Description

technical field [0001] The invention belongs to the field of hardware algorithm verification tools, in particular to a platform for verifying the accuracy of infrared video image processing algorithms. Background technique [0002] Infrared detection devices currently used generally have non-uniformity and even blind pixels; the original infrared video image directly output by the detector has low contrast and it is difficult to identify targets. Therefore, in the actual application process, the image processing algorithm must be implemented on the hardware to reduce the noise interference in the original infrared video and highlight the detection target. [0003] For the processing algorithm of infrared video, the development process is usually divided into two stages: the first stage is the simulation of the algorithm. At present, the Matlab software developed by The MathWorks is usually used to write the code file, and the simulation is carried out on the computer to veri...

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): H04N17/00G06F9/455
CPCG06F9/45533H04N17/002
Inventor 张佳逊隋修宝徐致东郝玉婷陈宇翔
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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