RFID tag image motion deblurring method based on mixed deep prior

An RFID tag and deblurring technology, which is applied in the field of RFID tag image motion deblurring, can solve the problems of inability to adapt and blur the depth prior, and achieve the effects of good generalization, effective removal, and good deblurring effect

Pending Publication Date: 2022-02-15
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the depth prior cannot adapt to arbitrary blur

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
  • RFID tag image motion deblurring method based on mixed deep prior
  • RFID tag image motion deblurring method based on mixed deep prior
  • RFID tag image motion deblurring method based on mixed deep prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0050] Such as figure 1 Shown is the general flowchart of the RFID tag image motion deblurring method of the present invention, and the implementation process includes the following steps:

[0051] Step 1, data set generation, use industrial cameras to collect 10100 clear label images, then randomly generate 100 fuzzy kernels, convolve the randomly generated fuzzy kernels with 100 randomly selected clear label images, and generate 10000 labels The blurred image dataset is used as the positive sample for training (marked as 1), while the remaining 10,000 clear labeled images are used as the negative sample set (marked as 0). Among them, the label blurred image such as figure 2 As shown, the original clear label image as image 3 shown.

[0052] The implementation steps of generating a label blurred image are as follows:

[0053] ...

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 tag image motion deblurring method based on mixed deep prior. The method comprises the following steps: (1) carrying out convolution on a randomly generated blurring kernel and randomly selected partial clear tag images to generate a tag blurred image data set; (2) constructing tag image deep priori; (3) selecting a cross entropy as a loss function, taking the tag blurred image data set as a training set, and carrying out tag image deep prior training; (4) constructing mixed deep prior of the tag images; (5) inserting the mixed deep prior into a maximum posterior framework solving model, and solving a potential clear image; (6) estimating a blurring kernel in blind deconvolution of a tag motion blurred image; and (7) repeating the step (5) and the step (6) until an optimal clear image is solved. According to the method, the problem of motion blur existing in a tag image can be effectively solved, and a foundation is laid for subsequent high-precision measurement of a tag position based on the image.

Description

technical field [0001] The invention relates to a motion deblurring method for an RFID tag image, in particular to a motion deblurring method for an RFID tag image based on a mixed deep prior. Background technique [0002] Radio Frequency Identification (RFID) is a non-contact automatic identification technology. It automatically recognizes the target object and acquires data through radio frequency signals. The recognition process does not require human intervention and can work in various harsh environments. RFID technology has been widely used in intelligent transportation, warehousing logistics, target positioning and other fields. However, in smart logistics, due to the popularity of online shopping, a large number of RFID tags need to be used for the collection of inbound and outbound information and inventory of bulk goods. In the batch application of RFID tags, the geometric position distribution of the tags will have an impact on the overall reading performance o...

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 & AuthorityApplications(China)
IPC IPC(8): G06T5/00G06K9/62G06V10/764G06V10/774
CPCG06T2207/20081G06F18/241G06F18/214G06T5/73
Inventor庄笑俞晓磊赵志敏刘振鲁
OwnerNANJING UNIV OF AERONAUTICS & ASTRONAUTICS