A method, system and computer storage medium for extracting target image area

Through the methods of inductive signal encoding and image information superposition, the problems of low efficiency and low accuracy of solid waste recognition are solved, and efficient and accurate distinction between metal and non-metal are achieved, meeting the requirements of high-speed identification and classification.

CN112115765BActive Publication Date: 2024-11-05NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010736852.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-28
Publication Date
2024-11-05
Estimated Expiration
2040-07-28

AI Technical Summary

Technical Problem

The existing solid waste recognition methods are inefficient and have low accuracy, especially in the process of distinguishing between metals and non-metals. Physical means are inefficient and image recognition can only be distinguished by color, so the accuracy is not high.

Method used

By obtaining the inductance signal of the detected area and performing encoding processing, combining image information, extracting the current pulse signal and converting it into a digital signal, using an encoder to synchronize it with the image information, using the contour extraction method to obtain the target image area, and realizing the inductance signal and The superposition of image information can further improve the recognition accuracy.

Benefits of technology

This method combines physical means and image recognition to reduce the calculation amount, fast speed and high accuracy, and can meet the high-speed identification and classification needs of metal materials in solid waste.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112115765B_ABST
    Figure CN112115765B_ABST
Patent Text Reader

Abstract

The invention discloses a method, system and computer storage medium for extracting a target image area, belonging to the technical field of image area recognition, wherein the extraction method comprises acquiring an inductance signal of a detected area; acquiring image information of the detected area; extracting a current pulse signal of the inductance signal, converting the current pulse signal into a digital signal, and arranging the digital signal in a coding order; superimposing the digital signal with the image information to obtain a final target area; the extraction method can effectively realize the real-time acquisition of the inductance signal and the image information according to the synchronization effect of an encoder through the target image area extraction method based on the inductance signal, and the method combines physical means with image recognition means, not only has the advantages of reducing the amount of calculation and fast speed, but also has the advantages of high accuracy by combining the two, and can meet the requirements of high-speed recognition and classification of metal materials in solid waste.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image region recognition, and in particular to a method and system for extracting a target image region and a computer storage medium. Background Art

[0002] Solid waste treatment generally refers to the process of converting solid waste into a material suitable for transportation, storage, utilization or disposal through physical, chemical, biological, physicochemical and biochemical methods. The goal of solid waste treatment is to render it harmless, reduce its volume and make it a resource. The main methods currently used include compaction, crushing, sorting, solidification, incineration and biological treatment.

[0003] In the process of solid waste sorting, the differentiation and screening of metals and non-metals is an important link. The existing methods for screening metals and non-metals mainly include two methods. One is screening by physical means, such as manual picking, gravity sorting, magnetic sorting, eddy current sorting, optical sorting, etc.; the other is to distinguish metals by image recognition.

[0004] Among them, the method of screening by physical means is inefficient and the screening accuracy is not high. The method of image recognition requires a lot of calculations, and the distinction between metals and non-metals can only be made by color, and the accuracy is not high. Summary of the invention

[0005] In order to solve the problem of low efficiency and low accuracy of existing solid waste identification methods, the present invention provides a method and system for extracting target image areas with high efficiency and high identification accuracy. In order to achieve the above-mentioned purpose, the present invention provides a method for extracting target image areas, comprising the following steps:

[0006] Acquire the inductance signal of the detected area, and encode the inductance signal using an encoder;

[0007] Acquire image information of the detected area; wherein the position of the image information of the detected area corresponds to the position of the area occupied by the inductance signal;

[0008] Extracting a current pulse signal of the inductance signal, converting the current pulse signal into a digital signal, and arranging the digital signal in a coding order;

[0009] The digital signal is superimposed on the image information to obtain a final target area.

[0010] Furthermore, the step of acquiring the inductance signal of the detected area and encoding the inductance signal using an encoder further includes:

[0011] Using an inductive sensor to obtain an inductive signal of the detected area;

[0012] Encoding the inductance signal according to displacement so that the inductance signal is expanded along the moving direction of the target area;

[0013] The encoder is configured to trigger the image sensor to capture an image every a certain number of square waves, so that the captured image is synchronized with the inductance signal.

[0014] Optionally, the converting of the current pulse signal into a digital signal further includes: setting a threshold; and converting the current pulse signal into a digital signal by comparing the value of the current pulse signal with the threshold.

[0015] Optionally, the superimposing the digital signal with the image information to obtain the target area further includes:

[0016] Acquire the area occupied by all target images of the image information by using a contour extraction method;

[0017] The values ​​of all pixels included in the area are multiplied by the value of the digital signal of the corresponding area to obtain the superimposed target area.

[0018] On the other hand, the present invention also provides a system for extracting a target image region, comprising:

[0019] A first acquisition unit, used to acquire an inductance signal of a detected area;

[0020] A second acquisition unit, used to acquire image information of the detected area;

[0021] An encoder, used for encoding the inductance signal;

[0022] A conversion unit, used for extracting a current pulse signal of the inductance signal and converting the current pulse signal into a digital signal;

[0023] An image superimposing unit is used to superimpose the digital signal with the image information.

[0024] In the above extraction system, optionally, the first acquisition unit is an inductive sensor.

[0025] Optionally, the inductive sensors are placed in an array below the material conveyor belt, and randomly arranged targets passing over the inductive sensors cause current changes, and the inductive sensors output inductive signals in the form of current.

[0026] Optionally, the second acquisition unit is an image collector.

[0027] Optionally, the image superposition unit is specifically used to: obtain the area occupied by all target images of the image information by a contour extraction method; multiply the values ​​of all pixels contained in the area by the value of the digital signal of the corresponding area to obtain the superimposed target area.

[0028] The beneficial effect of the present invention compared with the prior art is that the extraction method can effectively realize the real-time acquisition of inductance signals and image information according to the synchronization effect of the encoder through the target image area extraction method based on the inductance signal. The method combines physical means with image recognition means, which not only has the advantages of reducing the amount of calculation and fast speed, but also combines the two with high accuracy, which can meet the requirements of high-speed identification and classification of metal materials in solid waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of a method for extracting a target image region in the present invention;

[0030] Figure 2 It is a schematic diagram of the encoder synchronization signal acting on the image and inductive sensors;

[0031] Figure 3 It is a schematic diagram of A / D conversion of current pulses;

[0032] Figure 4 is a structural diagram of a target image region extraction system in the invention;

[0033] Figure 5 It is a schematic diagram of the acquisition method of the inductive sensor. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0036] Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to the actual proportional relationship. The technology, method and equipment known to those of ordinary skill in the relevant field may not be discussed in detail, but in appropriate cases, the technology, method and equipment should be considered as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so that once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0037] In addition, it should be noted that the use of words such as "first" and "second" to define components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above words have no special meaning and cannot be understood as limiting the scope of protection of this application. In addition, although the terms used in this application are selected from well-known and commonly used terms, some terms mentioned in the specification of this application may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this article. In addition, it is required to understand this application not only by the actual terms used, but also by the meaning implied by each term.

[0038] like Figure 1 As shown, this embodiment provides a method for extracting a target image area, comprising the following steps:

[0039] S10: acquiring an inductance signal of the detected area, and encoding the inductance signal using an encoder;

[0040] Specifically, the inductive sensor is used to obtain the inductance signal of the area to be detected. The inductive sensor is a device that uses the change of the self-inductance or mutual inductance coefficient of the coil to realize the electrical measurement of non-electrical quantities. It uses the principle of electromagnetic induction to convert the measured non-electrical quantities such as displacement, pressure, liquid volume, vibration, etc. into changes in the self-inductance or mutual inductance of the coil, and then converts it into a change in voltage or current output by the measuring circuit. Inductive sensors cannot detect non-metallic objects, but can only detect objects with conductivity or magnetism. The inductive sensor can detect whether there is a metal material directly above it by the size of the output current. If there is a metal material, the output current will be significantly reduced. If it is other non-metallic materials or no material, the current will only change slightly or not.

[0041] After the inductive sensor acquires the inductance signal of the detected area, the encoder encodes the inductance signal by counting the square waves of the encoder to determine the position of each inductance signal, and expands the inductance signal along the direction of material movement to facilitate subsequent analysis and processing.

[0042] S20: Acquire image information of the detected area; wherein the position of the image information of the detected area corresponds to the position of the area occupied by the inductance signal;

[0043] Specifically, an image collector is used to collect image information of the detected area. The time for collecting the image is the same as the time for collecting the inductance signal, and the synchronization effect of the encoder signal is used to make the area occupied by the inductance signal correspond to the corresponding image pixel position in the collected image. The purpose is to ensure zero error in subsequent processing.

[0044] It should be noted that, in this embodiment, the encoder is installed at the end of the servo motor spindle. Every time the motor spindle rotates a certain angle, the encoder generates a square wave, that is, each square wave represents a certain distance the conveyor belt moves. Figure 2 As shown, the current signal of the inductive sensor is collected according to a certain number of encoder square waves, and the encoder signal is matched to the inductive signal to encode the inductive signal according to the displacement, so that the inductive signal is expanded along the material movement direction. At the same time, the encoder is set to trigger the image sensor to collect an image every certain number of square waves, so that the collected image and the inductive signal have the same corresponding position, that is, the position information of the material in each image captured and the material position information (that is, the detected area) detected by the inductive sensor are one-to-one corresponding.

[0045] S30: extracting a current pulse signal of the inductance signal, converting the current pulse signal into a digital signal, and arranging the digital signal in a coding order;

[0046] Specifically, a threshold is first set; then the value of the current pulse signal is compared with the threshold so as to convert the current pulse signal into a digital signal.

[0047] like Figure 3 As shown in the figure, the current pulse of the inductive sensor expands along the direction of material movement after being encoded by the encoder, and the position where the current suddenly changes indicates that the inductive sensor has detected a metal material. The inductive signal is detected using the above conversion method, and independent current pulses are extracted to generate a sequence of 0 and 1, where 0 indicates that there is no metal material at the current position, and 1 indicates the position where the inductive sensor has detected a metal.

[0048] S40: superimposing the digital signal and the image information to obtain a final target area.

[0049] The digital signal and image superposition process is achieved by combining the contour extraction method of image processing and the mapping method of digital signals. Specifically, after the image sensor obtains a complete frame of image, the contour extraction method is used to obtain the area occupied by all materials in the image; then the values ​​of all pixels contained in these areas are multiplied by the digital signals of the corresponding areas, and all pixel values ​​become 0 except for the area where the metal material is located.

[0050] After superposition, the pixels of the area containing metal materials (ie, the final target area) remain unchanged, and the pixels of the non-metal area (ie, the non-final target area) are 0, thus obtaining the final target area.

[0051] This extraction method is based on the characteristic that inductive signals are insensitive to non-metals. First, the location of the metal is identified by an inductive sensor, and then the target image is acquired by an image sensor to accurately extract the area where the metal is located. This method combines physical means with image recognition means, which not only has the advantages of reducing the amount of calculation and fast speed, but also combines the two with high accuracy, which can meet the requirements of high-speed identification and classification of metal materials in solid waste.

[0052] In some embodiments, the present invention further provides a system for extracting a target image region. Figure 4 As shown, the extraction system comprises:

[0053] The first acquisition unit 10 is used to acquire the inductance signal of the detected area. In this embodiment, the first acquisition unit adopts an inductive sensor, such as Figure 5 As shown, the inductive sensors are placed in an array under the material conveyor belt. The scattered targets pass over the inductive sensors, causing current changes. The inductive sensors output inductive signals in the form of current.

[0054] The second acquisition unit 20 is used to acquire image information of the detected area. In this embodiment, the second acquisition unit adopts an image collector, such as a video camera, a still camera, etc.

[0055] The encoder 30 is used to encode the inductance signal; the encoder is installed at the end of the servo motor main shaft. Every time the motor main shaft rotates a certain angle, the encoder generates a square wave, that is, each square wave represents a certain distance of the conveyor belt movement. The current signal of the inductive sensor is collected according to a certain number of encoder square waves, and the encoder signal is matched to the inductance signal to encode the inductance signal according to the displacement, so that the inductance signal is expanded along the material movement direction. At the same time, the encoder is set to trigger the image sensor to collect an image every certain number of square waves, so that the collected image and the inductance signal have the same corresponding position, that is, the position information of the material in each image captured and the material position information detected by the inductive sensor are one-to-one corresponding.

[0056] The conversion unit 40 is used to extract the current pulse signal of the inductance signal and convert the current pulse signal into a digital signal, thereby realizing A / D conversion. Specifically, a threshold value must be set first. Then, the current pulse signal is converted into a digital signal by comparing the value of the current pulse signal with the threshold value, and the current value below the threshold value is set to 1, and the current value above the threshold value is set to 0. The obtained digital signal generates a binary grid in sequence.

[0057] The image superposition unit 50 is used to superimpose the digital signal with the image information. Specifically, the digital signal and image superposition process is achieved by combining the contour extraction method of image processing and the mapping method of digital signals. After the image sensor obtains a complete frame of image, it first obtains the area occupied by all materials in the image through the contour extraction method; then the values ​​of all pixels contained in these areas are multiplied by the digital signals accordingly, and all pixel values ​​become 0 except for the area where the metal material is located. After superposition, the pixels of the area containing metal materials (i.e., the final target area) remain unchanged, and the pixels of the non-metal area (i.e., the non-final target area) are 0, so that the final target area is obtained.

[0058] In addition, an embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program includes part or all of the steps of any one of the target image area extraction methods recorded in the above method embodiments.

[0059] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0060] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0061] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0062] The above description is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for extracting a target image area, characterized in that: include: Acquire the inductance signal of the detected area, and encode the inductance signal using an encoder, including acquiring the inductance signal of the detected area using an inductive sensor; Encoding the inductance signal according to displacement so that the inductance signal is expanded along the moving direction of the target area; The encoder is set to trigger the image sensor to collect an image every certain number of square waves, so that the collected image is synchronized with the inductance signal; Acquire image information of the detected area; wherein the position of the image information of the detected area corresponds to the position of the area occupied by the inductance signal; Extracting a current pulse signal of the inductance signal, converting the current pulse signal into a digital signal, and arranging the digital signal in a coding order, wherein converting the current pulse signal into a digital signal includes setting a threshold; Comparing the value of the current pulse signal with the threshold value to convert the current pulse signal into a digital signal; Superimposing the digital signal with the image information to obtain a final target area, including obtaining the area occupied by all target images of the image information by a contour extraction method; The values ​​of all pixels included in the area are multiplied by the value of the digital signal of the corresponding area to obtain the superimposed target area.

2. A target image region extraction system, characterized in that: include: A first acquisition unit, used to acquire an inductance signal of the detected area, including acquiring the inductance signal of the detected area by using an inductive sensor; A second acquisition unit is used to acquire image information of the detected area; wherein the position of the image information of the detected area corresponds to the position of the area occupied by the inductance signal; An encoder, used for encoding the inductance signal, including encoding the inductance signal according to displacement so that the inductance signal is expanded along the movement direction of the target area; The encoder is set to trigger the image sensor to collect an image every certain number of square waves, so that the collected image is synchronized with the inductance signal; a conversion unit, used for extracting a current pulse signal of the inductance signal, converting the current pulse signal into a digital signal, and arranging the digital signal in a coding order, wherein converting the current pulse signal into a digital signal includes setting a threshold; Comparing the value of the current pulse signal with the threshold value to convert the current pulse signal into a digital signal; An image superposition unit, used for superimposing the digital signal with the image information to obtain a final target area, including obtaining an area occupied by all target images of the image information by a contour extraction method; The values ​​of all pixels included in the area are multiplied by the value of the digital signal of the corresponding area to obtain the superimposed target area.

3. The extraction system according to claim 2, characterized in that: The inductive sensors are placed in an array below the material conveyor belt. The randomly arranged targets passing over the inductive sensors cause current changes, and the inductive sensors output inductive signals in the form of current.

4. The extraction system according to claim 2, characterized in that: The second acquisition unit is an image collector.

5. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for extracting a target image area as claimed in claim 1 are implemented.