CN109883958A - A kind of agricultural and animal products lossless detection method and device - Google Patents
A kind of agricultural and animal products lossless detection method and device Download PDFInfo
- Publication number
- CN109883958A CN109883958A CN201910139218.8A CN201910139218A CN109883958A CN 109883958 A CN109883958 A CN 109883958A CN 201910139218 A CN201910139218 A CN 201910139218A CN 109883958 A CN109883958 A CN 109883958A
- Authority
- CN
- China
- Prior art keywords
- agricultural
- animal products
- pixel
- video frame
- tone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A kind of agricultural and animal products non-destructive testing and device, this method pass through the agricultural and animal products image that transmits in camera captured in real-time transmission belt, comprising: obtain the video frame images of the video content of current shooting in real time；Article identification is carried out from the video frame images, and extracts domain color information；According to the domain color information, qualified agricultural and animal products are filtered out.The agricultural and animal products lossless detection method and device are to the agricultural and animal products transmitted in transmission belt, image recognition is carried out first with vision technique, a part is filtered out because there may be the agricultural and animal products asked for appearance color, smell reinspection is carried out using electronic olfactory to the agricultural and animal products filtered out again, it can be ensured that the agricultural and animal products after detecting are fresh, healthy.
Description
Technical field
The present invention relates to food inspection engineering device technique fields, and in particular to a kind of agricultural and animal products non-destructive testing and device.
Background technique
Bread is the staff of life, and quality of agricultural and poultry products is the key point of quality control.For realize agricultural and animal products quality it is strong
Health detection, currently, non-destructive testing technology is gradually popularized, for meeting the needs of food production, process scale processing,
Non-destructive testing technology have the characteristics that not destroy measuring samples, detection speed faster, pollution-free or of low pollution, easily realize automatic
Change, Chang Liyong computer smell technology, near-infrared spectral analysis technology or Visual analysis techniques are realized.
Computer smell technology be usually using gas sensor array to smell carry out identification and detection of complex odor and
The technology of volatile component, it is more effective for rotten agricultural and animal products detection, but since the result of detection is only capable of from smell
Judgement, to agricultural and animal products, there are impurity or sordid situation to be difficult to detect.
Near-infrared spectral analysis technology is with not damaged, detection efficiency is high, the measurement of at low cost, favorable reproducibility, sample is general
It is not required to pre-process, is suitable for the advantages such as on-site test and on-line analysis.Agricultural and animal products are quickly detected using near-infrared spectrum technique
When, it first has to select a large amount of representative samples, on the basis of standard detecting method obtains reference value, be built by professional technician
Vertical detection model, and by later period model optimization and examine and qualified could use.If resettling a set of detection device, need same
Process realize that early investment is higher, relatively time-consuming.
With the progress of image analysis technology, the agricultural and animal products quality testing of view-based access control model technology is also gradually answered these years
With, mainly carried out by external appearance characteristics such as the size of agricultural and animal products, shape, texture, color and surface defects Quality Detection and
Sorting, however judge only by surface, often inner case can't detect, moreover, existing image detection is calculated
The accuracy of method is not also high.
Summary of the invention
In view of the shortcomings of the prior art, the application provides a kind of agricultural and animal products non-destructive testing and device, using vision and smells
Feel technology accurately carries out agricultural and animal products non-destructive testing.
According in a first aspect, providing a kind of agricultural and animal products lossless detection method in a kind of embodiment, this method passes through camera shooting
The agricultural and animal products image transmitted in head captured in real-time transmission belt, comprising:
The video frame images of the video content of current shooting are obtained in real time；
Article identification is carried out from the video frame images, and extracts domain color information；
According to the domain color information, qualified agricultural and animal products are filtered out.
In some embodiments, the colouring information that extracts from the video frame images includes:
Calculate the tone average value of the video frame images；
The pixel for traversing the video frame images calculates the tone value of the pixel and the color difference of the tone average value；
Judge whether the color difference is greater than preset threshold；
If the color difference is greater than preset threshold, the pixel is added to dominant hue pixel list, according to the dominant hue
The mass-tone tone pitch of pixel described in pixel list, determines the colouring information.
In some embodiments, according to the domain color information, filtering out qualified agricultural and animal products includes: the traversal video
Whether the difference of the pixel of frame image, the tone value and the mass-tone tone pitch that calculate the pixel is greater than preset threshold；If described
Difference is respectively less than preset threshold, by video frame images labeled as qualification.
In some embodiments, according to the different colours of pixel each in the video frame images, determine that the pixel is corresponding
Weighted value；According to the tone value of the pixel and corresponding weighted value, the tone that the video frame images are calculated is average
Value.
In some embodiments, the method further include: the qualified agricultural and animal products filtered out are rinsed by clear water
Afterwards, the odiferous information that agricultural and animal products distribute is obtained using smell sensor, passes through the odiferous information and preset reference information
It compares, judges whether agricultural and animal products are abnormal, carry out smell reinspection.
According to second aspect, a kind of agricultural and animal products non-destructive testing device, comprising:
Camera, the agricultural and animal products image transmitted in captured in real-time transmission belt；
Processor, the video frame images of the video content for obtaining current shooting in real time；From the video frame images
Extract colouring information；According to the colouring information, qualified agricultural and animal products are filtered out；
First sorting equipment, for sorting the qualified agricultural and animal products filtered out.
In some embodiments, the processor is used for:
Calculate the tone average value of the video frame images；
The pixel for traversing the video frame images calculates the tone value of the pixel and the color difference of the tone average value；
Judge whether the color difference is greater than preset threshold；
If the color difference is greater than preset threshold, the pixel is added to dominant hue pixel list, according to the dominant hue
The mass-tone tone pitch of pixel described in pixel list, determines the colouring information.
In some embodiments, the detection device further include: smell sensor, the smell sensor is for obtaining farming animals production
The odiferous information that product distribute, the processor are used for through the odiferous information with preset compared with information, judge agriculture
Whether livestock products are abnormal；Second sorting equipment is judged as normal agricultural and animal products through smell reinspection for sorting.
According to the third aspect, a kind of computer readable storage medium, including program, described program can be executed by processor
To realize method as described in relation to the first aspect.
The domain color of video frame images is extracted after identifying due to the application by article according to the method for above-described embodiment
Information judges whether there is abnormal pixel using the difference between domain color information and the tone value of video frame images, into
And qualified agricultural and animal products and possible underproof agricultural and animal products are distinguished, such detection method judging result is more accurate.
Detailed description of the invention
Fig. 1 is agricultural and animal products lossless detection method flow chart one provided by one embodiment of the present invention；
Fig. 2 is agricultural and animal products lossless detection method flowchart 2 provided by one embodiment of the present invention；
Fig. 3 is agricultural and animal products lossless detection method flow chart 3 provided by one embodiment of the present invention；
Fig. 4 is agricultural and animal products non-destructive testing device structure chart provided by one embodiment of the present invention；
Fig. 5 is the structural schematic diagram of image collection module provided by one embodiment of the present invention；
Fig. 6 is the structural schematic diagram of the first mechanical stabilization device provided by one embodiment of the present invention；
Fig. 7 is the bottom surface structure schematic diagram of the first movable plate provided by one embodiment of the present invention；
Fig. 8 is the structural schematic diagram of second provided by one embodiment of the present invention mechanical stabilization device；
Fig. 9 is the bottom surface structure schematic diagram of second of movable plate provided by one embodiment of the present invention.
Specific embodiment
Below by specific embodiment combination attached drawing, invention is further described in detail.Wherein different embodiments
Middle similar component uses associated similar element numbers.In the following embodiments, many datail descriptions be in order to
The application is better understood.However, those skilled in the art can recognize without lifting an eyebrow, part of feature
It is dispensed, or can be substituted by other elements, material, method in varied situations.In some cases, this Shen
Please it is relevant it is some operation there is no in the description show or describe, this is the core in order to avoid the application by mistake
More descriptions are flooded, and to those skilled in the art, these relevant operations, which are described in detail, not to be necessary, they
Relevant operation can be completely understood according to the general technology knowledge of description and this field in specification.
It is formed respectively in addition, feature described in this description, operation or feature can combine in any suitable way
Kind embodiment.Meanwhile each step in method description or movement can also can be aobvious and easy according to those skilled in the art institute
The mode carry out sequence exchange or adjustment seen.Therefore, the various sequences in the description and the appended drawings are intended merely to clearly describe a certain
A embodiment is not meant to be necessary sequence, and wherein some sequentially must comply with unless otherwise indicated.
It is herein component institute serialization number itself, such as " first ", " second " etc., is only used for distinguishing described object,
Without any sequence or art-recognized meanings.And " connection ", " connection " described in the application, unless otherwise instructed, include directly and
It is indirectly connected with (connection).
Fig. 1 to Fig. 3 is please referred to, the application provides a kind of agricultural and animal products lossless detection method, and this method passes through camera reality
When shooting transmission belt on the agricultural and animal products image that transmits, this method comprises:
Step S101 obtains the video frame images of the video content of current shooting in real time；
Step S102 carries out article identification from the video frame images, and extracts domain color information；
Step S103 filters out qualified agricultural and animal products according to the colouring information.
In some embodiments, this method includes following sub-step:
Step S1021, the colouring information that extracts from the video frame images includes: to calculate the video frame images
Tone average value.Specifically, it can determine that the pixel is corresponding according to the different colours of pixel each in the video frame images
Weighted value；According to the tone value of the pixel and corresponding weighted value, the tone average value of the video frame images is calculated.
Step S1022 traverses the pixel of the video frame images, and tone value and the tone for calculating the pixel are average
The color difference of value；
Step S1023, judges whether the color difference is greater than preset threshold；
The pixel is added to dominant hue pixel list if the color difference is greater than preset threshold by step S1024, according to
The mass-tone tone pitch of pixel described in the dominant hue pixel list, determines the colouring information.
Specifically, it would be desirable to extract the colouring information of the video frame images, which is to be best able to represent to be somebody's turn to do
The dominant hue of video frame images, which does not imply that color is most, and refers to most eye-catching in the video frame images
Tone.Optionally, tone value can be indicated with rgb value, can also be by present commonplace applicable hexadecimal color value
It indicates.In the present embodiment, each of video frame images pixel is traversed, tone value and the tone for calculating each pixel are flat
The color difference of mean value.When the color difference of the tone value of some pixel and tone average value is greater than preset threshold value, which is added
To dominant hue pixel list.After the completion of all pixels are all compared with tone value, the picture for including in the list of dominant hue pixel is calculated
The average value, is determined as the colouring information of the video frame images by the average value of the tone value of element.
In step S103, according to the domain color information, qualified agricultural and animal products is filtered out, are specifically included:
Step S1030 traverses the pixel of the video frame images, calculates the tone value and the mass-tone tone pitch of the pixel
Difference whether be greater than preset threshold；If the difference is respectively less than preset threshold, i.e., the pixel and mass-tone of the described video frame images
Tune is not much different, by video frame images labeled as qualification；Conversely, being deposited if the difference has the case where being greater than preset threshold
Larger situation is differed with dominant hue in the pixel of the video frame images, that is, there is abnormal pixel, agricultural and animal products may
It is stale or rotten.
The article identification process of step S102 can identify target object using image recognition technology, such as: vegetables and fruits, meat
Deng, can be used the target object image of contours extract, pattern match or the polymorphic type by being stored in preset data Kuku into
Row aspect ratio Peer, the embodiment of the present invention to image recognition technology without limitation.After identifying target object, Ke Yiyan
The obtained profile of target object of identification carry out scratching figure, also can be used image pluck out it is related in technology, such as Photoshop
Stingy diagram technology, target object is extracted from the first picture.
It can be seen that extracting the domain color information of video frame images after the application is identified by article, being believed using domain color
Difference between breath and the tone value of video frame images judges whether there is abnormal pixel, and then distinguishes qualified farming animals
Product and possible underproof agricultural and animal products, such vision screening technique judging result are more accurate.
In some embodiments, this method further includes smell reinspection, it may be assumed that
Step S1041, qualified agricultural and animal products obtain agricultural and animal products using smell sensor and distribute after clear water rinses
Odiferous information, by the odiferous information with preset referring to compared with information, judging that whether agricultural and animal products abnormal, carry out gas
Taste reinspection.
With reference to Fig. 4, correspondingly, a kind of agricultural and animal products non-destructive testing device, which includes:
Camera 200, the agricultural and animal products image transmitted in captured in real-time transmission belt；
Processor 100, the video frame images of the video content for obtaining current shooting in real time；From the video frame images
Middle extraction colouring information；According to the colouring information, qualified agricultural and animal products are filtered out；
First sorting equipment 501, for sorting the qualified agricultural and animal products filtered out.
In some embodiments, the processor 100 is used to calculate the tone average value of the video frame images；Described in traversal
The pixel of video frame images calculates the tone value of the pixel and the color difference of the tone average value；Whether judge the color difference
Greater than preset threshold；If the color difference is greater than preset threshold, the pixel is added to dominant hue pixel list, according to the master
The mass-tone tone pitch of pixel described in tone pixel list, determines the colouring information.
In some embodiments, the device further include: smell sensor 300 and the second sorting equipment 502, the smell sensor
300 for obtaining the odiferous information that agricultural and animal products distribute, and the processor 100 is for passing through the odiferous information and preset ginseng
It compares according to information, judges whether agricultural and animal products are abnormal；Second sorting equipment 502 is judged as normal through smell reinspection for sorting
Agricultural and animal products.
In above-described embodiment, the first sorting equipment 501 and the second sorting equipment 502 are electrically connected with processor 100 respectively, warp
The control of processor 100 is sorted accordingly, can be the gate in existing manipulator or transmission belt in specific embodiment
Control device.
In conclusion the agricultural and animal products lossless detection method and device of the application, to the agricultural and animal products transmitted in transmission belt,
Image recognition is carried out first with vision technique, filters out a part because appearance color is there may be the agricultural and animal products asked, then right
The agricultural and animal products filtered out carry out smell reinspection using electronic olfactory, it is ensured that the agricultural and animal products after detecting are fresh, healthy.
As shown in figure 5, the camera 200 of the present embodiment is anti-including camera lens 1000, automatic Focus voice coil motor 2000, machinery
Device 3000 and imaging sensor 4000 are trembled, the camera lens 1000 is packed on the automatic Focus voice coil motor 2000, described
Camera lens 1000 is packed on the automatic Focus voice coil motor 2000, and the camera lens 1000 is passed for obtaining image, described image
The image transmitting that sensor 4000 obtains the camera lens 1000 to the identification module, the automatic Focus voice coil motor 2000 is pacified
On the mechanical stabilization device 3000, the camera lens 1000 that the processing module is detected according to the gyroscope in camera lens 1000 is trembled
The movement of the dynamic feedback driving mechanical stabilization device 3000, realizes the jitter compensation of camera lens 1000, so that camera 200 is shot
Agricultural and animal products image it is apparent.
It is mobile that existing stabilization device is generated long-range navigation magnetic drive camera lens 1000 by hot-wire coil in magnetic field mostly, and wants real
Existing optical anti-vibration, needs to drive camera lens 1000 at least two directions, it means that need to arrange multiple coils, it can be to whole
The micromation of structure brings certain challenge, and is easy to be interfered by external magnetic field, and then influence anti-shake effect, therefore Publication No.
The Chinese patent of CN106131435A provides a kind of micro-optical stabilization camera module, is realized and is remembered by temperature change
The stretching and shortening of alloy wire pull automatic Focus voice coil motor 2000 mobile, realize the jitter compensation of camera lens 1000 with this, micro-
The control chip of type memorial alloy optical anti-vibration actuator can control the variation of driving signal to change the temperature of memory alloy wire
Degree, the elongation and shortening of memory alloy wire is controlled with this, and the position of actuator is calculated according to the resistance of memory alloy wire
And moving distance.Memory alloy wire is fed back at this time when be moved to designated position on minisize memory alloy optical anti-vibration actuator after
Resistance can correct on minisize memory alloy optical anti-vibration actuator by comparing the deviation of this resistance value and target value
Movement deviation.
Applicant have discovered that relying solely on the structure of above-mentioned technical proposal due to the randomness and uncertainty of shake
It is that cannot achieve to precisely compensate for camera lens 1000 in the case where multiple shake occurs, this is because shape memory
The heating and cooling of alloy are required to the regular hour, and when shake occurs to first direction, above-mentioned technical proposal be may be implemented
The compensation that camera lens 1000 shakes first direction, but when the shake of the following second direction occurs, since memory is closed
Spun gold has little time in short time set, therefore be easy to cause compensation not in time, can not precisely realize to multiple shake and different directions
1000 jitter compensation of camera lens continuously shaken, it is therefore desirable to being improved in its structure.
In conjunction with attached drawing, shown in 6-9, the present embodiment improves optical anti-vibration device, is designed to mechanical stabilization device
3000, specific structure is as follows:
The embodiment of the present invention machinery stabilization device 3000 includes movable plate 3100, activity box 3200, elastic return mechanism
3300, substrate 3400 and compensation mechanism 3500；The middle part of the movable plate 3100 and substrate 3400 is equipped with for the camera lens
The through-hole 3700 passed through, the automatic Focus voice coil motor are mounted on the movable plate 3100, and the movable plate 3100 is installed
In the activity box 3200, as can be seen from Figure, the width of the left and right directions of the movable plate 3100 of the present embodiment and activity
The inner width of frame 3200 is roughly the same, so that the opposite sides (left and right sides) of the movable plate 3100 and the activity box
The inner wall of 3200 opposite sides (left and right sides) is slidably matched, so that the movable plate 3100 can be along in activity box 3200
One direction reciprocatingly slides, the up and down direction in the first direction, that is, figure of the present embodiment.
Specifically, the size of the embodiment of the present invention activity box 3200 is less than the size of the substrate 3400, the activity
The opposite sides of frame 3200 passes through two elastic return mechanisms 3300 respectively and is connected with the substrate 3400, the bullet of the present embodiment
Property response agency 3300 be adjustable spring or other elastic components, and it should be noted that the present embodiment elastic recovery machine
Structure 3300 allow it to have along the ability that left and right directions in figure (i.e. following second directions) are flexible and spring back, can not be along
First direction movement, the purpose of design flexibility response agency 3300 are also to be to be convenient for after compensation displacement occurs for activity box 3200
Activity box 3200 drives movable plate 3100 to reset, and specific action process the present embodiment can be had in following courses of work
Body description.
The embodiment of the present invention compensation mechanism 3500 (can be the dynamic of processing module transmission in the driving of the processing module
Instruct) under drive the camera lens on the movable plate 3100 and movable plate 3100 to act, to realize the jitter compensation of camera lens.
Specifically, the embodiment of the present invention compensation mechanism 3500 includes drive shaft 3510, gear 3520, gear track 3530
And limit track 3540, the drive shaft 3510 are mounted on the substrate 3400, are specifically mounted in the upper of substrate 3400
Surface, the drive shaft 3510 are sequentially connected with the gear 3520, and drive shaft 3510 (can not shown by micromotor in figure
The structures driving such as out), and micromotor is controlled by above-mentioned processing module；The gear track 3530 is arranged in the activity
On plate 3100, the gear 3520 is mounted in the gear track 3530 and along the preset direction of the gear track 3530
Movement enables the movable plate 3100 to generate to first party when the gear 3520 rotates by the gear track 3530
To displacement and second direction displacement, wherein the first direction is vertical with the second direction；The limit track 3540
Setting is on the movable plate 3100 or on the substrate 3400, and the limit track 3540 is for preventing the gear 3520 de-
From the gear track 3530.
Specifically, the gear track 3530 and limit track 3540 of the present embodiment have following two structure type:
As shown in figures 5-9, a waist-shaped hole 3550, the waist-shaped hole are equipped on the downside of the embodiment of the present invention movable plate 3100
3550 are equipped with multiple teeth 3560 being meshed with the gear 3520 along its circumferential (i.e. circular direction of waist-shaped hole 3550), described
Waist-shaped hole 3550 and multiple teeth 3560 collectively form the gear track 3530, and the gear 3520 is located at the waist-shaped hole
It is meshed, is moved so that gear 3520 is able to drive gear track 3530 in rotation, in turn in 3550 and with the tooth 3560
Directly drive the movement of movable plate 3100；And in order to enable gear 3520 rotation when the moment can guarantee and gear track 3530
Moment keeps engagement, and the limit track 3540 is arranged on the substrate 3400 the present embodiment, 3100 bottom of movable plate
Portion is equipped with the locating part 3570 being mounted in the limit track 3540, and the limit track 3540 makes the locating part 3570 exist
Motion profile therein is in waist type, i.e., locating part 3570 is the motion profile of motion profile and movable plate 3100 in track now
It is identical, specifically, the embodiment of the present invention locating part 3570 is the protrusion being arranged on 3100 bottom surface of movable plate.
In conjunction with shown in attached drawing 8 and 9, the embodiment of the present invention gear track 3530 can also be by being arranged in the movable plate
Multiple cylindrical projections 3580 on 3100 form, and multiple cylindrical projections 3580 are laid along the second direction uniform intervals,
The gear 3520 is meshed with multiple protrusions；And the limit track 3540 is to be arranged on the movable plate 3100
First arc-shaped limit part 3590 and the second arc-shaped limit part 3600, the first arc-shaped limit part 3590 and the second arc-shaped limit part
3600 are separately positioned on opposite sides of the gear track 3530 on first direction, prevent, move in movable plate 3100 pre-
If when position, gear 3520 is located at the side of gear track 3530, gear 3520 is easily separated from the tooth of the composition of cylindrical projection 3580
Wheel track 3530, therefore guiding function can be played by the first arc-shaped limit part 3590 or the second arc-shaped limit part 3600, make
Obtaining movable plate 3100 can move along the preset direction of gear track 3530, i.e., the described first arc-shaped limit part 3590 and second
Arc-shaped limit part 3600 and multiple protrusions match so that the motion profile of the movable plate 3100 is in waist type.
It is described in detail below with reference to the course of work of the above structure to the mechanical stabilization device 3000 of the present embodiment, with
For 1000 double pump of camera lens, double pump is contrary, and it is required that movable plate 3100 to first direction motion compensation
Once, and it is primary then to second direction motion compensation.Need movable plate 3100 to when first direction motion compensation, gyroscope thing
1000 jitter direction of camera lens and distance that first will test feed back to the processing module, and processing module, which calculates, needs movable plate
3100 move distance so that drive shaft 3510 with moving gear 3520 rotate, gear 3520 by with gear track 3530
With the cooperation of limit track 3540, processing module transmits wirelessly driving signal, and then movable plate 3100 is driven to transport to first direction
It moves to compensation position, drives movable plate 3100 to reset again by drive shaft 3510 after compensation, in reseting procedure, elastic recovery
Reset of the mechanism 3300 also for movable plate 3100 provides reset force, easily facilitates movable plate 3100 and is restored to initial position.It needs
Movable plate 3100 is to when second direction motion compensation, and processing mode is identical as the compensation process of above-mentioned first direction, here only
It repeats more.
Certainly above-mentioned is only simple double pump, and when repeatedly shake occurs, or the direction of shake is not reciprocal
It, can be by driving multiple compensation components to compensate shake when movement, element task process is identical as foregoing description principle, this
In do not repeat excessively, sending control instruction etc. to drive shaft 3510 further with regards to the detection feedback of gyroscope, processing module is
The prior art, here only more descriptions.
In conjunction with above description it is found that mechanical compensator provided in this embodiment not will receive external magnetic field interference not only, prevent
It is good to tremble effect, and may be implemented to precisely compensate for camera lens 1000 in the case where multiple shake occurs, compensates
Promptly and accurately.In addition, the mechanical stabilization device using the present embodiment is not only simple in structure, installation space needed for all parts is small,
Convenient for the integrated of entire stabilization device, and compensation precision with higher.
The application also provides a kind of computer readable storage medium, including program, and described program can be held by processor 100
Row is to realize above-mentioned method.
It will be understood by those skilled in the art that all or part of function of various methods can pass through in above embodiment
The mode of hardware is realized, can also be realized by way of computer program.When function all or part of in above embodiment
When being realized by way of computer program, which be can store in memory 400, and memory 400 may include: read-only
The storage mediums such as memory, random access memory, disk, CD, hard disk execute the program by computer to realize above-mentioned function
Energy.For example, program is stored in the memory of equipment, when executing program in memory by processor, can be realized above-mentioned
All or part of function.In addition, when function all or part of in above embodiment is realized by way of computer program,
The program also can store in the storage mediums such as server, another computer, disk, CD, flash disk or mobile hard disk, lead to
Downloading or copying and saving are crossed into the memory of local device, or version updating is carried out to the system of local device, is located when passing through
When managing the program in device execution memory, all or part of function in above embodiment can be realized.
Use above specific case is illustrated the present invention, is merely used to help understand the present invention, not to limit
The system present invention.For those skilled in the art, according to the thought of the present invention, can also make several simple
It deduces, deform or replaces.
Claims (9)
1. a kind of agricultural and animal products lossless detection method, this method passes through the agricultural and animal products transmitted in camera captured in real-time transmission belt
Image characterized by comprising
The video frame images of the video content of current shooting are obtained in real time；
Article identification is carried out from the video frame images, and extracts domain color information；
According to the domain color information, qualified agricultural and animal products are filtered out.
2. the method as described in claim 1, which is characterized in that described to extract colouring information packet from the video frame images
It includes:
Calculate the tone average value of the video frame images；
The pixel for traversing the video frame images calculates the tone value of the pixel and the color difference of the tone average value；
Judge whether the color difference is greater than preset threshold；
If the color difference is greater than preset threshold, the pixel is added to dominant hue pixel list, according to the dominant hue pixel
The mass-tone tone pitch of pixel described in list, determines the colouring information.
3. method according to claim 2, which is characterized in that according to the domain color information, filter out qualified farming animals and produce
Product include: the pixel for traversing the video frame images, calculate the pixel tone value and the mass-tone tone pitch difference whether
Greater than preset threshold；If the difference is respectively less than preset threshold, by video frame images labeled as qualification.
4. method according to claim 2, which is characterized in that according to the different face of pixel each in the video frame images
Color determines the corresponding weighted value of the pixel；According to the tone value of the pixel and corresponding weighted value, the view is calculated
The tone average value of frequency frame image.
5. method according to any one of claims 1 to 4, which is characterized in that further include: the qualified agriculture filtered out
Livestock products obtain the odiferous information that agricultural and animal products distribute after clear water rinses, using smell sensor, are believed by the smell
Breath compared with information, judges whether agricultural and animal products are abnormal, carry out smell reinspection with preset.
6. a kind of agricultural and animal products non-destructive testing device characterized by comprising
Camera, the agricultural and animal products image transmitted in captured in real-time transmission belt；
Processor, the video frame images of the video content for obtaining current shooting in real time；It is extracted from the video frame images
Colouring information；According to the colouring information, qualified agricultural and animal products are filtered out；
First sorting equipment, for sorting the qualified agricultural and animal products filtered out.
7. non-destructive testing device as claimed in claim 6, which is characterized in that the processor is used for:
Calculate the tone average value of the video frame images；
The pixel for traversing the video frame images calculates the tone value of the pixel and the color difference of the tone average value；
Judge whether the color difference is greater than preset threshold；
If the color difference is greater than preset threshold, the pixel is added to dominant hue pixel list, according to the dominant hue pixel
The mass-tone tone pitch of pixel described in list, determines the colouring information.
8. non-destructive testing device as claimed in claim 6, which is characterized in that further include: smell sensor, the odor sensing
Device is used to believe by the odiferous information and preset reference for obtaining the odiferous information that agricultural and animal products distribute, the processor
Manner of breathing compares, and judges whether agricultural and animal products are abnormal；Second sorting equipment is judged as normal farming animals through smell reinspection for sorting
Product.
9. a kind of computer readable storage medium, which is characterized in that including program, described program can be executed by processor with reality
Existing method according to any one of claims 1 to 5.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811315729 | 2018-11-06 | ||
| CN2018113157292 | 2018-11-06 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109883958A true CN109883958A (en) | 2019-06-14 |
| CN109883958B CN109883958B (en) | 2022-03-11 |
Family
ID=66929294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910139218.8A Active CN109883958B (en) | 2018-11-06 | 2019-02-25 | Nondestructive testing method and device for agricultural and livestock products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109883958B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102728563A (en) * | 2012-05-15 | 2012-10-17 | 陈延鹏 | Intelligent winter jujube sorting machine |
| CN105224588A (en) * | 2015-06-29 | 2016-01-06 | 深圳市美贝壳科技有限公司 | According to method and the device of photo dominant hue generation background music |
| CN106238342A (en) * | 2016-09-14 | 2016-12-21 | 郑州轻工业学院 | The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof |
| CN107350172A (en) * | 2017-07-31 | 2017-11-17 | 中国农业科学院兰州畜牧与兽药研究所 | A kind of beef acid lipidic component monitors product control device |
| CN207057047U (en) * | 2017-08-07 | 2018-03-02 | 华中农业大学 | A kind of Chinese chestnut automatic sorting device |
-
2019
- 2019-02-25 CN CN201910139218.8A patent/CN109883958B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102728563A (en) * | 2012-05-15 | 2012-10-17 | 陈延鹏 | Intelligent winter jujube sorting machine |
| CN105224588A (en) * | 2015-06-29 | 2016-01-06 | 深圳市美贝壳科技有限公司 | According to method and the device of photo dominant hue generation background music |
| CN106238342A (en) * | 2016-09-14 | 2016-12-21 | 郑州轻工业学院 | The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof |
| CN107350172A (en) * | 2017-07-31 | 2017-11-17 | 中国农业科学院兰州畜牧与兽药研究所 | A kind of beef acid lipidic component monitors product control device |
| CN207057047U (en) * | 2017-08-07 | 2018-03-02 | 华中农业大学 | A kind of Chinese chestnut automatic sorting device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109883958B (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Giselsson et al. | A public image database for benchmark of plant seedling classification algorithms | |
| Mollah et al. | Digital image analysis to estimate the live weight of broiler | |
| JP6067093B2 (en) | Method and apparatus for evaluating eye tracking results | |
| US10997501B2 (en) | System and method for noise-based training of a prediction model | |
| CN102792145B (en) | Systems and methods for calculating drop delay of a flow cytometry | |
| KR20180057785A (en) | A system of measuring fish number for image analysis and that of measure method | |
| CN109285149A (en) | Appraisal procedure, device and the calculating equipment of quality of human face image | |
| DE102012110375A1 (en) | Method and apparatus for executing various decoding algorithms at different positions | |
| JP5738564B2 (en) | Image processing system | |
| Zaborowicz et al. | Use of artificial neural networks in the identification and classification of tomatoes | |
| Molina et al. | Automatic detection of early blight infection on tomato crops using a color based classification strategy | |
| CN107330403A (en) | A kind of yak method of counting based on video data | |
| CN108765405A (en) | A kind of image authenticating method and system | |
| CN107529963A (en) | Image processing apparatus, image processing method and image processing program | |
| JP2020129439A (en) | Information processing system and information processing method | |
| Ghebreab et al. | A biologically plausible model for rapid natural scene identification | |
| EP3769036B1 (en) | Method and system for extraction of statistical sample of moving fish | |
| Pike | Egg recognition in Japanese quail | |
| CN109883958A (en) | A kind of agricultural and animal products lossless detection method and device | |
| US4780907A (en) | Method of measuring the types of motion and configuration of biological and non-biological objects | |
| US10638667B2 (en) | Augmented-human field inspection tools for automated phenotyping systems and agronomy tools | |
| CN110705698B (en) | Target counting depth network design method for scale self-adaptive perception | |
| CN116630327A (en) | Boiler state abnormity monitoring system based on thermodynamic diagram | |
| WO2022129362A1 (en) | A system for monitoring of dead fish | |
| US11756214B2 (en) | Method and apparatus for tracking nematode worms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |